bring in two tricks from the cogview paper for reducing the chances of overflow, for attention and layernorm

* Overhauled the tracker system
Separated the logging and saving capabilities
Changed creation to be consistent and initializing behavior to be defined by a class initializer instead of in the training script
Added class separation between different types of loaders and savers to make the system more verbose

* Changed the saver system to only save the checkpoint once

* Added better error handling for saving checkpoints

* Fixed an error where wandb would error when passed arbitrary kwargs

* Fixed variable naming issues for improved saver
Added more logging during long pauses

* Fixed which methods need to be dummy to immediatly return
Added the ability to set whether you find unused parameters

* Added more logging for when a wandb loader fails

README.md

@@ -20,16 +20,35 @@ As of 5/23/22, it is no longer SOTA. SOTA will be <a href="https://github.com/lu
 
 - Decoder is now verified working for unconditional generation on my experimental setup for Oxford flowers. 2 researchers have also confirmed Decoder is working for them.
 
-<img src="./samples/oxford.png" width="600px" />
+<img src="./samples/oxford.png" width="450px" />
 
 *ongoing at 21k steps*
 
 - <a href="https://twitter.com/Buntworthy/status/1529475416775434240?t=0GEge3Kr9I36cjcUVCQUTg">Justin Pinkney</a> successfully trained the diffusion prior in the repository for his CLIP to Stylegan2 text-to-image application
 
+- <a href="https://github.com/rom1504">Romain</a> has scaled up training to 800 GPUs with the available scripts without any issues
+
 ## Pre-Trained Models
+
 - LAION is training prior models. Checkpoints are available on <a href="https://huggingface.co/zenglishuci/conditioned-prior">🤗huggingface</a> and the training statistics are available on <a href="https://wandb.ai/nousr_laion/conditioned-prior/reports/LAION-DALLE2-PyTorch-Prior--VmlldzoyMDI2OTIx">🐝WANDB</a>.
 - Decoder - <a href="https://wandb.ai/veldrovive/dalle2_train_decoder/runs/jkrtg0so?workspace=user-veldrovive">In-progress test run</a> 🚧
-- DALL-E 2 🚧
+- Decoder - <a href="https://wandb.ai/veldrovive/dalle2_train_decoder/runs/3d5rytsa?workspace=">Another test run with sparse attention</a>
+- DALL-E 2 🚧 - <a href="https://github.com/LAION-AI/dalle2-laion">DALL-E 2 Laion repository</a>
+
+## Appreciation
+
+This library would not have gotten to this working state without the help of
+
+- <a href="https://github.com/nousr">Zion</a> for the distributed training code for the diffusion prior
+- <a href="https://github.com/Veldrovive">Aidan</a> for the distributed training code for the decoder as well as the dataloaders
+- <a href="https://github.com/krish240574">Kumar</a> for working on the initial diffusion training script
+- <a href="https://github.com/rom1504">Romain</a> for the pull request reviews and project management
+- <a href="https://github.com/Ciaohe">He Cao</a> and <a href="https://github.com/xiankgx">xiankgx</a> for the Q&A and for identifying of critical bugs
+- <a href="https://github.com/crowsonkb">Katherine</a> for her advice
+- <a href="https://stability.ai/">Stability AI</a> for the generous sponsorship
+- <a href="https://huggingface.co">🤗 Huggingface</a> and in particular <a href="https://github.com/sgugger">Sylvain</a> for the <a href="https://github.com/huggingface/accelerate">Accelerate</a> library
+
+... and many others. Thank you! 🙏
 
 ## Install
 
@@ -351,7 +370,8 @@ unet1 = Unet(
     image_embed_dim = 512,
     cond_dim = 128,
     channels = 3,
-    dim_mults=(1, 2, 4, 8)
+    dim_mults=(1, 2, 4, 8),
+    cond_on_text_encodings = True    # set to True for any unets that need to be conditioned on text encodings
 ).cuda()
 
 unet2 = Unet(
@@ -368,8 +388,7 @@ decoder = Decoder(
     clip = clip,
     timesteps = 100,
     image_cond_drop_prob = 0.1,
-    text_cond_drop_prob = 0.5,
-    condition_on_text_encodings = False  # set this to True if you wish to condition on text during training and sampling
+    text_cond_drop_prob = 0.5
 ).cuda()
 
 for unet_number in (1, 2):
@@ -943,7 +962,7 @@ from dalle2_pytorch.dataloaders import ImageEmbeddingDataset, create_image_embed
 
 # Create a dataloader directly.
 dataloader = create_image_embedding_dataloader(
-    tar_url="/path/or/url/to/webdataset/{0000..9999}.tar", # Uses braket expanding notation. This specifies to read all tars from 0000.tar to 9999.tar
+    tar_url="/path/or/url/to/webdataset/{0000..9999}.tar", # Uses bracket expanding notation. This specifies to read all tars from 0000.tar to 9999.tar
     embeddings_url="path/or/url/to/embeddings/folder",     # Included if .npy files are not in webdataset. Left out or set to None otherwise
     num_workers=4,
     batch_size=32,
@@ -1000,33 +1019,6 @@ The most significant parameters for the script are as follows:
 
 - `clip`, default = `None` # Signals the prior to use pre-computed embeddings
 
-#### Loading and Saving the DiffusionPrior model
-
-Two methods are provided, load_diffusion_model and save_diffusion_model, the names being self-explanatory. 
-
-```python
-from dalle2_pytorch.train import load_diffusion_model, save_diffusion_model
-```
-
-##### Loading
-
-    load_diffusion_model(dprior_path, device) 
-        dprior_path : path to saved model(.pth)
-        device      : the cuda device you're running on
-    
-##### Saving
-
-    save_diffusion_model(save_path, model, optimizer, scaler, config, image_embed_dim)
-        save_path : path to save at
-        model     : object of Diffusion_Prior
-        optimizer : optimizer object - see train_diffusion_prior.py for how to create one. 
-            e.g: optimizer = get_optimizer(diffusion_prior.net.parameters(), wd=weight_decay, lr=learning_rate)
-        scaler    : a GradScaler object.
-            e.g: scaler = GradScaler(enabled=amp)
-        config    : config object created in train_diffusion_prior.py - see file for example. 
-        image_embed_dim - the dimension of the image_embedding
-            e.g: 768
-
 ## CLI (wip)
 
 ```bash
@@ -1041,19 +1033,6 @@ Once built, images will be saved to the same directory the command is invoked
 
 <a href="https://github.com/lucidrains/stylegan2-pytorch">template</a>
 
-## Appreciation
-
-This library would not have gotten to this working state without the help of
-
-- <a href="https://github.com/nousr">Zion</a> and <a href="https://github.com/krish240574">Kumar</a> for the diffusion training script
-- <a href="https://github.com/Veldrovive">Aidan</a> for the decoder training script and dataloaders
-- <a href="https://github.com/rom1504">Romain</a> for the pull request reviews and project management
-- <a href="https://github.com/Ciaohe">He Cao</a> and <a href="https://github.com/xiankgx">xiankgx</a> for the Q&A and for identifying of critical bugs
-- <a href="https://github.com/crowsonkb">Katherine</a> for her advice
-- <a href="https://stability.ai/">Stability AI</a> for the generous sponsorship
-
-... and many others. Thank you! 🙏
-
 ## Todo
 
 - [x] finish off gaussian diffusion class for latent embedding - allow for prediction of epsilon
@@ -1088,19 +1067,14 @@ This library would not have gotten to this working state without the help of
 - [x] for both diffusion prior and decoder, all exponential moving averaged models needs to be saved and restored as well (as well as the step number)
 - [x] offer save / load methods on the trainer classes to automatically take care of state dicts for scalers / optimizers / saving versions and checking for breaking changes
 - [x] allow for creation of diffusion prior model off pydantic config classes - consider the same for tracker configs
+- [x] bring in skip-layer excitations (from lightweight gan paper) to see if it helps for either decoder of unet or vqgan-vae training (doesnt work well)
+- [x] test out grid attention in cascading ddpm locally, decide whether to keep or remove https://arxiv.org/abs/2204.01697 (keeping, seems to be fine)
+- [x] allow for unet to be able to condition non-cross attention style as well
 - [ ] become an expert with unets, cleanup unet code, make it fully configurable, port all learnings over to https://github.com/lucidrains/x-unet (test out unet² in ddpm repo) - consider https://github.com/lucidrains/uformer-pytorch attention-based unet
-- [ ] transcribe code to Jax, which lowers the activation energy for distributed training, given access to TPUs
-- [ ] train on a toy task, offer in colab
-- [ ] think about how best to design a declarative training config that handles preencoding for prior and training of multiple networks in decoder
-- [ ] extend diffusion head to use diffusion-gan (potentially using lightweight-gan) to speed up inference
+- [ ] speed up inference, read up on papers (ddim or diffusion-gan, etc)
 - [ ] figure out if possible to augment with external memory, as described in https://arxiv.org/abs/2204.11824
-- [ ] test out grid attention in cascading ddpm locally, decide whether to keep or remove https://arxiv.org/abs/2204.01697
 - [ ] interface out the vqgan-vae so a pretrained one can be pulled off the shelf to validate latent diffusion + DALL-E2
-- [ ] make sure FILIP works with DALL-E2 from x-clip https://arxiv.org/abs/2111.07783
-- [ ] bring in skip-layer excitatons (from lightweight gan paper) to see if it helps for either decoder of unet or vqgan-vae training
-- [ ] decoder needs one day worth of refactor for tech debt
-- [ ] allow for unet to be able to condition non-cross attention style as well
-- [ ] read the paper, figure it out, and build it https://github.com/lucidrains/DALLE2-pytorch/issues/89
+- [ ] add inpainting ability using resampler from repaint paper https://arxiv.org/abs/2201.09865
 
 ## Citations
 
@@ -1140,15 +1114,6 @@ This library would not have gotten to this working state without the help of
 }
 ```
 
-```bibtex
-@inproceedings{Tu2022MaxViTMV,
-    title   = {MaxViT: Multi-Axis Vision Transformer},
-    author  = {Zhengzhong Tu and Hossein Talebi and Han Zhang and Feng Yang and Peyman Milanfar and Alan Conrad Bovik and Yinxiao Li},
-    year    = {2022},
-    url     = {https://arxiv.org/abs/2204.01697}
-}
-```
-
 ```bibtex
 @article{Yu2021VectorquantizedIM,
     title   = {Vector-quantized Image Modeling with Improved VQGAN},
@@ -1207,4 +1172,24 @@ This library would not have gotten to this working state without the help of
 }
 ```
 
+```bibtex
+@article{Choi2022PerceptionPT,
+    title   = {Perception Prioritized Training of Diffusion Models},
+    author  = {Jooyoung Choi and Jungbeom Lee and Chaehun Shin and Sungwon Kim and Hyunwoo J. Kim and Sung-Hoon Yoon},
+    journal = {ArXiv},
+    year    = {2022},
+    volume  = {abs/2204.00227}
+}
+```
+
+```bibtex
+@article{Saharia2021PaletteID,
+    title   = {Palette: Image-to-Image Diffusion Models},
+    author  = {Chitwan Saharia and William Chan and Huiwen Chang and Chris A. Lee and Jonathan Ho and Tim Salimans and David J. Fleet and Mohammad Norouzi},
+    journal = {ArXiv},
+    year    = {2021},
+    volume  = {abs/2111.05826}
+}
+```
+
 *Creating noise from data is easy; creating data from noise is generative modeling.* - <a href="https://arxiv.org/abs/2011.13456">Yang Song's paper</a>

configs/README.md

@@ -83,7 +83,7 @@ Defines which evaluation metrics will be used to test the model.
 Each metric can be enabled by setting its configuration. The configuration keys for each metric are defined by the torchmetrics constructors which will be linked.
 | Option | Required | Default | Description |
 | ------ | -------- | ------- | ----------- |
-| `n_evalation_samples` | No | `1000` | The number of samples to generate to test the model. |
+| `n_evaluation_samples` | No | `1000` | The number of samples to generate to test the model. |
 | `FID` | No | `None` | Setting to an object enables the [Frechet Inception Distance](https://torchmetrics.readthedocs.io/en/stable/image/frechet_inception_distance.html) metric. 
 | `IS` | No | `None` | Setting to an object enables the [Inception Score](https://torchmetrics.readthedocs.io/en/stable/image/inception_score.html) metric.
 | `KID` | No | `None` | Setting to an object enables the [Kernel Inception Distance](https://torchmetrics.readthedocs.io/en/stable/image/kernel_inception_distance.html) metric. |
@@ -91,21 +91,83 @@ Each metric can be enabled by setting its configuration. The configuration keys
 
 **<ins>Tracker</ins>:**
 
-Selects which tracker to use and configures it.
+Selects how the experiment will be tracked.
 | Option | Required | Default | Description |
 | ------ | -------- | ------- | ----------- |
-| `tracker_type` | No | `console` | Which tracker to use. Currently accepts `console` or `wandb`. |
-| `data_path` | No | `./models` | Where the tracker will store local data. |
-| `verbose` | No | `False` | Enables console logging for non-console trackers. |
+| `data_path` | No | `./.tracker-data` | The path to the folder where temporary tracker data will be saved. |
+| `overwrite_data_path` | No | `False` | If true, the data path will be overwritten. Otherwise, you need to delete it yourself. |
+| `log` | Yes | N/A | Logging configuration. |
+| `load` | No | `None` | Checkpoint loading configuration. |
+| `save` | Yes | N/A | Checkpoint/Model saving configuration. |
+Tracking is split up into three sections:
+* Log: Where to save run metadata and image output. Options are `console` or `wandb`.
+* Load: Where to load a checkpoint from. Options are `local`, `url`, or `wandb`.
+* Save: Where to save a checkpoint to. Options are `local`, `huggingface`, or `wandb`.
 
-Other configuration options are required for the specific trackers. To see which are required, reference the initializer parameters of each [tracker](../dalle2_pytorch/trackers.py).
+**Logging:**
 
-**<ins>Load</ins>:**
-
-Selects where to load a pretrained model from.
+If using `console` there is no further configuration than setting `log_type` to `console`.
 | Option | Required | Default | Description |
 | ------ | -------- | ------- | ----------- |
-| `source` | No | `None` | Supports `file` or `wandb`. |
-| `resume` | No | `False` | If the tracker support resuming the run, resume it. |
+| `log_type` | Yes | N/A | Must be `console`. |
 
-Other configuration options are required for loading from a specific source. To see which are required, reference the load methods at the top of the [tracker file](../dalle2_pytorch/trackers.py).
+If using `wandb`
+| Option | Required | Default | Description |
+| ------ | -------- | ------- | ----------- |
+| `log_type` | Yes | N/A | Must be `wandb`. |
+| `wandb_entity` | Yes | N/A | The wandb entity to log to. |
+| `wandb_project` | Yes | N/A | The wandb project save the run to. |
+| `wandb_run_name` | No | `None` | The wandb run name. |
+| `wandb_run_id` | No | `None` | The wandb run id. Used if resuming an old run. |
+| `wandb_resume` | No | `False` | Whether to resume an old run. |
+
+**Loading:**
+
+If using `local`
+| Option | Required | Default | Description |
+| ------ | -------- | ------- | ----------- |
+| `load_from` | Yes | N/A | Must be `local`. |
+| `file_path` | Yes | N/A | The path to the checkpoint file. |
+
+If using `url`
+| Option | Required | Default | Description |
+| ------ | -------- | ------- | ----------- |
+| `load_from` | Yes | N/A | Must be `url`. |
+| `url` | Yes | N/A | The url of the checkpoint file. |
+
+If using `wandb`
+| Option | Required | Default | Description |
+| ------ | -------- | ------- | ----------- |
+| `load_from` | Yes | N/A | Must be `wandb`. |
+| `wandb_run_path` | No | `None` | The wandb run path. If `None`, uses the run that is being resumed. |
+| `wandb_file_path` | Yes | N/A | The path to the checkpoint file in the W&B file system. |
+
+**Saving:**
+Unlike `log` and `load`, `save` may be an array of options so that you can save to different locations in a run.
+
+All save locations have these configuration options
+| Option | Required | Default | Description |
+| ------ | -------- | ------- | ----------- |
+| `save_to` | Yes | N/A | Must be `local`, `huggingface`, or `wandb`. |
+| `save_latest_to` | No | `latest.pth` | Sets the relative path to save the latest model to. |
+| `save_best_to` | No | `best.pth` | Sets the relative path to save the best model to every time the model has a lower validation loss than all previous models. |
+| `save_type` | No | `'checkpoint'` | The type of save. `'checkpoint'` saves a checkpoint, `'model'` saves a model without any fluff (Saves with ema if ema is enabled). |
+
+If using `local`
+| Option | Required | Default | Description |
+| ------ | -------- | ------- | ----------- |
+| `save_to` | Yes | N/A | Must be `local`. |
+
+If using `huggingface`
+| Option | Required | Default | Description |
+| ------ | -------- | ------- | ----------- |
+| `save_to` | Yes | N/A | Must be `huggingface`. |
+| `huggingface_repo` | Yes | N/A | The huggingface repository to save to. |
+| `huggingface_base_path` | Yes | N/A | The base path that checkpoints will be saved under. |
+| `token_path` | No | `None` | If logging in with the huggingface cli is not possible, point to a token file instead. |
+
+If using `wandb`
+| Option | Required | Default | Description |
+| ------ | -------- | ------- | ----------- |
+| `save_to` | Yes | N/A | Must be `wandb`. |
+| `wandb_run_path` | No | `None` | The wandb run path. If `None`, uses the current run. You will almost always want this to be `None`. |

configs/train_decoder_config.example.json

@@ -15,7 +15,7 @@
         "channels": 3,
         "timesteps": 1000,
         "loss_type": "l2",
-        "beta_schedule": "cosine",
+        "beta_schedule": ["cosine"],
         "learned_variance": true
     },
     "data": {
@@ -80,20 +80,32 @@
         }
     },
     "tracker": {
-        "tracker_type": "console",
-        "data_path": "./models",
+        "overwrite_data_path": true,
 
-        "wandb_entity": "",
-        "wandb_project": "",
+        "log": {
+            "log_type": "wandb",
 
-        "verbose": false
-    },
-    "load": {
-        "source": null,
+            "wandb_entity": "your_wandb",
+            "wandb_project": "your_project",
 
-        "run_path": "",
-        "file_path": "",
+            "verbose": true
+        },
 
-        "resume": false
+        "load": {
+            "load_from": null
+        },
+
+        "save": [{
+            "save_to": "wandb"
+        }, {
+            "save_to": "huggingface",
+            "huggingface_repo": "Veldrovive/test_model",
+
+            "save_all": true,
+            "save_latest": true,
+            "save_best": true,
+
+            "save_type": "model"
+        }]
     }
 }

dalle2_pytorch/__init__.py

@@ -1,3 +1,4 @@
+from dalle2_pytorch.version import __version__
 from dalle2_pytorch.dalle2_pytorch import DALLE2, DiffusionPriorNetwork, DiffusionPrior, Unet, Decoder
 from dalle2_pytorch.dalle2_pytorch import OpenAIClipAdapter
 from dalle2_pytorch.trainer import DecoderTrainer, DiffusionPriorTrainer

dalle2_pytorch/dalle2_pytorch.py

@@ -1,6 +1,6 @@
 import math
-from tqdm import tqdm
-from inspect import isfunction
+import random
+from tqdm.auto import tqdm
 from functools import partial, wraps
 from contextlib import contextmanager
 from collections import namedtuple
@@ -11,7 +11,7 @@ import torch.nn.functional as F
 from torch import nn, einsum
 import torchvision.transforms as T
 
-from einops import rearrange, repeat
+from einops import rearrange, repeat, reduce
 from einops.layers.torch import Rearrange
 from einops_exts import rearrange_many, repeat_many, check_shape
 from einops_exts.torch import EinopsToAndFrom
@@ -45,6 +45,11 @@ def exists(val):
 def identity(t, *args, **kwargs):
     return t
 
+def first(arr, d = None):
+    if len(arr) == 0:
+        return d
+    return arr[0]
+
 def maybe(fn):
     @wraps(fn)
     def inner(x):
@@ -56,13 +61,18 @@ def maybe(fn):
 def default(val, d):
     if exists(val):
         return val
-    return d() if isfunction(d) else d
+    return d() if callable(d) else d
 
-def cast_tuple(val, length = 1):
+def cast_tuple(val, length = None):
     if isinstance(val, list):
         val = tuple(val)
 
-    return val if isinstance(val, tuple) else ((val,) * length)
+    out = val if isinstance(val, tuple) else ((val,) * default(length, 1))
+
+    if exists(length):
+        assert len(out) == length
+
+    return out
 
 def module_device(module):
     return next(module.parameters()).device
@@ -313,11 +323,6 @@ def extract(a, t, x_shape):
     out = a.gather(-1, t)
     return out.reshape(b, *((1,) * (len(x_shape) - 1)))
 
-def noise_like(shape, device, repeat=False):
-    repeat_noise = lambda: torch.randn((1, *shape[1:]), device=device).repeat(shape[0], *((1,) * (len(shape) - 1)))
-    noise = lambda: torch.randn(shape, device=device)
-    return repeat_noise() if repeat else noise()
-
 def meanflat(x):
     return x.mean(dim = tuple(range(1, len(x.shape))))
 
@@ -356,7 +361,7 @@ def cosine_beta_schedule(timesteps, s = 0.008):
     steps = timesteps + 1
     x = torch.linspace(0, timesteps, steps, dtype = torch.float64)
     alphas_cumprod = torch.cos(((x / timesteps) + s) / (1 + s) * torch.pi * 0.5) ** 2
-    alphas_cumprod = alphas_cumprod / alphas_cumprod[0]
+    alphas_cumprod = alphas_cumprod / first(alphas_cumprod)
     betas = 1 - (alphas_cumprod[1:] / alphas_cumprod[:-1])
     return torch.clip(betas, 0, 0.999)
 
@@ -372,7 +377,7 @@ def quadratic_beta_schedule(timesteps):
     scale = 1000 / timesteps
     beta_start = scale * 0.0001
     beta_end = scale * 0.02
-    return torch.linspace(beta_start**2, beta_end**2, timesteps, dtype = torch.float64) ** 2
+    return torch.linspace(beta_start**0.5, beta_end**0.5, timesteps, dtype = torch.float64) ** 2
 
 
 def sigmoid_beta_schedule(timesteps):
@@ -383,8 +388,8 @@ def sigmoid_beta_schedule(timesteps):
     return torch.sigmoid(betas) * (beta_end - beta_start) + beta_start
 
 
-class BaseGaussianDiffusion(nn.Module):
-    def __init__(self, *, beta_schedule, timesteps, loss_type):
+class NoiseScheduler(nn.Module):
+    def __init__(self, *, beta_schedule, timesteps, loss_type, p2_loss_weight_gamma = 0., p2_loss_weight_k = 1):
         super().__init__()
 
         if beta_schedule == "cosine":
@@ -449,6 +454,11 @@ class BaseGaussianDiffusion(nn.Module):
         register_buffer('posterior_mean_coef1', betas * torch.sqrt(alphas_cumprod_prev) / (1. - alphas_cumprod))
         register_buffer('posterior_mean_coef2', (1. - alphas_cumprod_prev) * torch.sqrt(alphas) / (1. - alphas_cumprod))
 
+        # p2 loss reweighting
+
+        self.has_p2_loss_reweighting = p2_loss_weight_gamma > 0.
+        register_buffer('p2_loss_weight', (p2_loss_weight_k + alphas_cumprod / (1 - alphas_cumprod)) ** -p2_loss_weight_gamma)
+
     def q_posterior(self, x_start, x_t, t):
         posterior_mean = (
             extract(self.posterior_mean_coef1, t, x_t.shape) * x_start +
@@ -472,23 +482,23 @@ class BaseGaussianDiffusion(nn.Module):
             extract(self.sqrt_recipm1_alphas_cumprod, t, x_t.shape) * noise
         )
 
-    def sample(self, *args, **kwargs):
-        raise NotImplementedError
-
-    def forward(self, *args, **kwargs):
-        raise NotImplementedError
+    def p2_reweigh_loss(self, loss, times):
+        if not self.has_p2_loss_reweighting:
+            return loss
+        return loss * extract(self.p2_loss_weight, times, loss.shape)
 
 # diffusion prior
 
 class LayerNorm(nn.Module):
-    def __init__(self, dim):
+    def __init__(self, dim, eps = 1e-5):
         super().__init__()
-        self.gamma = nn.Parameter(torch.ones(dim))
-        self.register_buffer("beta", torch.zeros(dim))
+        self.eps = eps
+        self.g = nn.Parameter(torch.ones(dim))
 
     def forward(self, x):
-        return F.layer_norm(x, x.shape[-1:], self.gamma, self.beta)
-
+        var = torch.var(x, dim = -1, unbiased = False, keepdim = True)
+        mean = torch.mean(x, dim = -1, keepdim = True)
+        return (x - mean) * (var + self.eps).rsqrt() * self.g
 
 class ChanLayerNorm(nn.Module):
     def __init__(self, dim, eps = 1e-5):
@@ -499,8 +509,7 @@ class ChanLayerNorm(nn.Module):
     def forward(self, x):
         var = torch.var(x, dim = 1, unbiased = False, keepdim = True)
         mean = torch.mean(x, dim = 1, keepdim = True)
-        return (x - mean) / (var + self.eps).sqrt() * self.g
-
+        return (x - mean) * (var + self.eps).rsqrt() * self.g
 
 class Residual(nn.Module):
     def __init__(self, fn):
@@ -620,10 +629,13 @@ class Attention(nn.Module):
         heads = 8,
         dropout = 0.,
         causal = False,
-        rotary_emb = None
+        rotary_emb = None,
+        pb_relax_alpha = 32 ** 2
     ):
         super().__init__()
-        self.scale = dim_head ** -0.5
+        self.pb_relax_alpha = pb_relax_alpha
+        self.scale = dim_head ** -0.5 * (pb_relax_alpha ** -1)
+
         self.heads = heads
         inner_dim = dim_head * heads
 
@@ -688,7 +700,9 @@ class Attention(nn.Module):
         # attention
 
         sim = sim - sim.amax(dim = -1, keepdim = True).detach()
-        attn = sim.softmax(dim = -1)
+        sim = sim * self.pb_relax_alpha
+
+        attn = sim.softmax(dim = -1, dtype = torch.float32)
         attn = self.dropout(attn)
 
         # aggregate values
@@ -862,7 +876,7 @@ class DiffusionPriorNetwork(nn.Module):
 
         return pred_image_embed
 
-class DiffusionPrior(BaseGaussianDiffusion):
+class DiffusionPrior(nn.Module):
     def __init__(
         self,
         net,
@@ -883,7 +897,9 @@ class DiffusionPrior(BaseGaussianDiffusion):
         image_embed_scale = None,           # this is for scaling the l2-normed image embedding, so it is more suitable for gaussian diffusion, as outlined by Katherine (@crowsonkb) https://github.com/lucidrains/DALLE2-pytorch/issues/60#issue-1226116132
         clip_adapter_overrides = dict()
     ):
-        super().__init__(
+        super().__init__()
+
+        self.noise_scheduler = NoiseScheduler(
             beta_schedule = beta_schedule,
             timesteps = timesteps,
             loss_type = loss_type
@@ -923,6 +939,13 @@ class DiffusionPrior(BaseGaussianDiffusion):
         self.training_clamp_l2norm = training_clamp_l2norm
         self.init_image_embed_l2norm = init_image_embed_l2norm
 
+        # device tracker
+        self.register_buffer('_dummy', torch.tensor([True]), persistent = False)
+
+    @property
+    def device(self):
+        return self._dummy.device
+
     def p_mean_variance(self, x, t, text_cond, clip_denoised = False, cond_scale = 1.):
         assert not (cond_scale != 1. and not self.can_classifier_guidance), 'the model was not trained with conditional dropout, and thus one cannot use classifier free guidance (cond_scale anything other than 1)'
 
@@ -933,7 +956,7 @@ class DiffusionPrior(BaseGaussianDiffusion):
             # not 100% sure of this above line - for any spectators, let me know in the github issues (or through a pull request) if you know how to correctly do this
             # i'll be rereading https://arxiv.org/abs/2111.14822, where i think a similar approach is taken
         else:
-            x_recon = self.predict_start_from_noise(x, t = t, noise = pred)
+            x_recon = self.noise_scheduler.predict_start_from_noise(x, t = t, noise = pred)
 
         if clip_denoised and not self.predict_x_start:
             x_recon.clamp_(-1., 1.)
@@ -941,21 +964,21 @@ class DiffusionPrior(BaseGaussianDiffusion):
         if self.predict_x_start and self.sampling_clamp_l2norm:
             x_recon = l2norm(x_recon) * self.image_embed_scale
 
-        model_mean, posterior_variance, posterior_log_variance = self.q_posterior(x_start=x_recon, x_t=x, t=t)
+        model_mean, posterior_variance, posterior_log_variance = self.noise_scheduler.q_posterior(x_start=x_recon, x_t=x, t=t)
         return model_mean, posterior_variance, posterior_log_variance
 
     @torch.no_grad()
-    def p_sample(self, x, t, text_cond = None, clip_denoised = True, repeat_noise = False, cond_scale = 1.):
+    def p_sample(self, x, t, text_cond = None, clip_denoised = True, cond_scale = 1.):
         b, *_, device = *x.shape, x.device
         model_mean, _, model_log_variance = self.p_mean_variance(x = x, t = t, text_cond = text_cond, clip_denoised = clip_denoised, cond_scale = cond_scale)
-        noise = noise_like(x.shape, device, repeat_noise)
+        noise = torch.randn_like(x)
         # no noise when t == 0
         nonzero_mask = (1 - (t == 0).float()).reshape(b, *((1,) * (len(x.shape) - 1)))
         return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise
 
     @torch.no_grad()
     def p_sample_loop(self, shape, text_cond, cond_scale = 1.):
-        device = self.betas.device
+        device = self.device
 
         b = shape[0]
         image_embed = torch.randn(shape, device=device)
@@ -963,7 +986,7 @@ class DiffusionPrior(BaseGaussianDiffusion):
         if self.init_image_embed_l2norm:
             image_embed = l2norm(image_embed) * self.image_embed_scale
 
-        for i in tqdm(reversed(range(0, self.num_timesteps)), desc='sampling loop time step', total=self.num_timesteps):
+        for i in tqdm(reversed(range(0, self.noise_scheduler.num_timesteps)), desc='sampling loop time step', total=self.noise_scheduler.num_timesteps):
             times = torch.full((b,), i, device = device, dtype = torch.long)
             image_embed = self.p_sample(image_embed, times, text_cond = text_cond, cond_scale = cond_scale)
 
@@ -972,7 +995,7 @@ class DiffusionPrior(BaseGaussianDiffusion):
     def p_losses(self, image_embed, times, text_cond, noise = None):
         noise = default(noise, lambda: torch.randn_like(image_embed))
 
-        image_embed_noisy = self.q_sample(x_start = image_embed, t = times, noise = noise)
+        image_embed_noisy = self.noise_scheduler.q_sample(x_start = image_embed, t = times, noise = noise)
 
         pred = self.net(
             image_embed_noisy,
@@ -986,7 +1009,7 @@ class DiffusionPrior(BaseGaussianDiffusion):
 
         target = noise if not self.predict_x_start else image_embed
 
-        loss = self.loss_fn(pred, target)
+        loss = self.noise_scheduler.loss_fn(pred, target)
         return loss
 
     @torch.no_grad()
@@ -997,7 +1020,7 @@ class DiffusionPrior(BaseGaussianDiffusion):
 
         img = torch.randn(shape, device = device)
 
-        for i in tqdm(reversed(range(0, self.num_timesteps)), desc = 'sampling loop time step', total = self.num_timesteps):
+        for i in tqdm(reversed(range(0, self.noise_scheduler.num_timesteps)), desc = 'sampling loop time step', total = self.noise_scheduler.num_timesteps):
             img = self.p_sample(img, torch.full((batch_size,), i, device = device, dtype = torch.long), text_cond = text_cond, cond_scale = cond_scale)
         return img
 
@@ -1069,7 +1092,7 @@ class DiffusionPrior(BaseGaussianDiffusion):
         # timestep conditioning from ddpm
 
         batch, device = image_embed.shape[0], image_embed.device
-        times = torch.randint(0, self.num_timesteps, (batch,), device = device, dtype = torch.long)
+        times = torch.randint(0, self.noise_scheduler.num_timesteps, (batch,), device = device, dtype = torch.long)
 
         # scale image embed (Katherine)
 
@@ -1081,11 +1104,20 @@ class DiffusionPrior(BaseGaussianDiffusion):
 
 # decoder
 
-def Upsample(dim):
-    return nn.ConvTranspose2d(dim, dim, 4, 2, 1)
+def ConvTransposeUpsample(dim, dim_out = None):
+    dim_out = default(dim_out, dim)
+    return nn.ConvTranspose2d(dim, dim_out, 4, 2, 1)
 
-def Downsample(dim):
-    return nn.Conv2d(dim, dim, 4, 2, 1)
+def NearestUpsample(dim, dim_out = None):
+    dim_out = default(dim_out, dim)
+    return nn.Sequential(
+        nn.Upsample(scale_factor = 2, mode = 'nearest'),
+        nn.Conv2d(dim, dim_out, 3, padding = 1)
+    )
+
+def Downsample(dim, *, dim_out = None):
+    dim_out = default(dim_out, dim)
+    return nn.Conv2d(dim, dim_out, 4, 2, 1)
 
 class SinusoidalPosEmb(nn.Module):
     def __init__(self, dim):
@@ -1158,7 +1190,7 @@ class ResnetBlock(nn.Module):
         self.block2 = Block(dim_out, dim_out, groups = groups)
         self.res_conv = nn.Conv2d(dim, dim_out, 1) if dim != dim_out else nn.Identity()
 
-    def forward(self, x, cond = None, time_emb = None):
+    def forward(self, x, time_emb = None, cond = None):
 
         scale_shift = None
         if exists(self.time_mlp) and exists(time_emb):
@@ -1184,10 +1216,12 @@ class CrossAttention(nn.Module):
         dim_head = 64,
         heads = 8,
         dropout = 0.,
-        norm_context = False
+        norm_context = False,
+        pb_relax_alpha = 32 ** 2
     ):
         super().__init__()
-        self.scale = dim_head ** -0.5
+        self.pb_relax_alpha = pb_relax_alpha
+        self.scale = dim_head ** -0.5 * (pb_relax_alpha ** -1)
         self.heads = heads
         inner_dim = dim_head * heads
 
@@ -1234,26 +1268,14 @@ class CrossAttention(nn.Module):
             sim = sim.masked_fill(~mask, max_neg_value)
 
         sim = sim - sim.amax(dim = -1, keepdim = True).detach()
-        attn = sim.softmax(dim = -1)
+        sim = sim * self.pb_relax_alpha
+
+        attn = sim.softmax(dim = -1, dtype = torch.float32)
 
         out = einsum('b h i j, b h j d -> b h i d', attn, v)
         out = rearrange(out, 'b h n d -> b n (h d)')
         return self.to_out(out)
 
-class GridAttention(nn.Module):
-    def __init__(self, *args, window_size = 8, **kwargs):
-        super().__init__()
-        self.window_size = window_size
-        self.attn = Attention(*args, **kwargs)
-
-    def forward(self, x):
-        h, w = x.shape[-2:]
-        wsz = self.window_size
-        x = rearrange(x, 'b c (w1 h) (w2 w) -> (b h w) (w1 w2) c', w1 = wsz, w2 = wsz)
-        out = self.attn(x)
-        out = rearrange(out, '(b h w) (w1 w2) c -> b c (w1 h) (w2 w)', w1 = wsz, w2 = wsz, h = h // wsz, w = w // wsz)
-        return out
-
 class LinearAttention(nn.Module):
     def __init__(
         self,
@@ -1335,6 +1357,7 @@ class Unet(nn.Module):
         dim_mults=(1, 2, 4, 8),
         channels = 3,
         channels_out = None,
+        self_attn = False,
         attn_dim_head = 32,
         attn_heads = 16,
         lowres_cond = False, # for cascading diffusion - https://cascaded-diffusion.github.io/
@@ -1343,13 +1366,18 @@ class Unet(nn.Module):
         cond_on_text_encodings = False,
         max_text_len = 256,
         cond_on_image_embeds = False,
+        add_image_embeds_to_time = True, # alerted by @mhh0318 to a phrase in the paper - "Specifically, we modify the architecture described in Nichol et al. (2021) by projecting and adding CLIP embeddings to the existing timestep embedding"
         init_dim = None,
         init_conv_kernel_size = 7,
         resnet_groups = 8,
-        num_resnet_blocks = 1,
+        num_resnet_blocks = 2,
         init_cross_embed_kernel_sizes = (3, 7, 15),
         cross_embed_downsample = False,
         cross_embed_downsample_kernel_sizes = (2, 4),
+        memory_efficient = False,
+        scale_skip_connection = False,
+        nearest_upsample = False,
+        final_conv_kernel_size = 1,
         **kwargs
     ):
         super().__init__()
@@ -1369,13 +1397,15 @@ class Unet(nn.Module):
         self.channels_out = default(channels_out, channels)
 
         init_channels = channels if not lowres_cond else channels * 2 # in cascading diffusion, one concats the low resolution image, blurred, for conditioning the higher resolution synthesis
-        init_dim = default(init_dim, dim // 3 * 2)
+        init_dim = default(init_dim, dim)
 
         self.init_conv = CrossEmbedLayer(init_channels, dim_out = init_dim, kernel_sizes = init_cross_embed_kernel_sizes, stride = 1)
 
         dims = [init_dim, *map(lambda m: dim * m, dim_mults)]
         in_out = list(zip(dims[:-1], dims[1:]))
 
+        num_stages = len(in_out)
+
         # time, image embeddings, and optional text encoding
 
         cond_dim = default(cond_dim, dim)
@@ -1396,11 +1426,16 @@ class Unet(nn.Module):
             nn.Linear(time_cond_dim, time_cond_dim)
         )
 
-        self.image_to_cond = nn.Sequential(
+        self.image_to_tokens = nn.Sequential(
             nn.Linear(image_embed_dim, cond_dim * num_image_tokens),
             Rearrange('b (n d) -> b n d', n = num_image_tokens)
         ) if cond_on_image_embeds and image_embed_dim != cond_dim else nn.Identity()
 
+        self.to_image_hiddens = nn.Sequential(
+            nn.Linear(image_embed_dim, time_cond_dim),
+            nn.GELU()
+        ) if cond_on_image_embeds and add_image_embeds_to_time else None
+
         self.norm_cond = nn.LayerNorm(cond_dim)
         self.norm_mid_cond = nn.LayerNorm(cond_dim)
 
@@ -1421,20 +1456,29 @@ class Unet(nn.Module):
         # for classifier free guidance
 
         self.null_image_embed = nn.Parameter(torch.randn(1, num_image_tokens, cond_dim))
+        self.null_image_hiddens = nn.Parameter(torch.randn(1, time_cond_dim))
 
         self.max_text_len = max_text_len
         self.null_text_embed = nn.Parameter(torch.randn(1, max_text_len, cond_dim))
 
+        # whether to scale skip connection, adopted in Imagen
+
+        self.skip_connect_scale = 1. if not scale_skip_connection else (2 ** -0.5)
+
         # attention related params
 
         attn_kwargs = dict(heads = attn_heads, dim_head = attn_dim_head)
 
+        self_attn = cast_tuple(self_attn, num_stages)
+
+        create_self_attn = lambda dim: EinopsToAndFrom('b c h w', 'b (h w) c', Residual(Attention(dim, **attn_kwargs)))
+
         # resnet block klass
 
-        resnet_groups = cast_tuple(resnet_groups, len(in_out))
-        num_resnet_blocks = cast_tuple(num_resnet_blocks, len(in_out))
+        resnet_groups = cast_tuple(resnet_groups, num_stages)
+        top_level_resnet_group = first(resnet_groups)
 
-        assert len(resnet_groups) == len(in_out)
+        num_resnet_blocks = cast_tuple(num_resnet_blocks, num_stages)
 
         # downsample klass
 
@@ -1442,45 +1486,71 @@ class Unet(nn.Module):
         if cross_embed_downsample:
             downsample_klass = partial(CrossEmbedLayer, kernel_sizes = cross_embed_downsample_kernel_sizes)
 
+        # upsample klass
+
+        upsample_klass = ConvTransposeUpsample if not nearest_upsample else NearestUpsample
+
+        # give memory efficient unet an initial resnet block
+
+        self.init_resnet_block = ResnetBlock(init_dim, init_dim, time_cond_dim = time_cond_dim, groups = top_level_resnet_group) if memory_efficient else None
+
         # layers
 
         self.downs = nn.ModuleList([])
         self.ups = nn.ModuleList([])
         num_resolutions = len(in_out)
 
-        for ind, ((dim_in, dim_out), groups, layer_num_resnet_blocks) in enumerate(zip(in_out, resnet_groups, num_resnet_blocks)):
+        skip_connect_dims = [] # keeping track of skip connection dimensions
+
+        for ind, ((dim_in, dim_out), groups, layer_num_resnet_blocks, layer_self_attn) in enumerate(zip(in_out, resnet_groups, num_resnet_blocks, self_attn)):
             is_first = ind == 0
             is_last = ind >= (num_resolutions - 1)
             layer_cond_dim = cond_dim if not is_first else None
 
+            dim_layer = dim_out if memory_efficient else dim_in
+            skip_connect_dims.append(dim_layer)
+
+            attention = nn.Identity()
+            if layer_self_attn:
+                attention = create_self_attn(dim_layer)
+            elif sparse_attn:
+                attention = Residual(LinearAttention(dim_layer, **attn_kwargs))
+
             self.downs.append(nn.ModuleList([
-                ResnetBlock(dim_in, dim_out, time_cond_dim = time_cond_dim, groups = groups),
-                Residual(LinearAttention(dim_out, **attn_kwargs)) if sparse_attn else nn.Identity(),
-                nn.ModuleList([ResnetBlock(dim_out, dim_out, cond_dim = layer_cond_dim, time_cond_dim = time_cond_dim, groups = groups) for _ in range(layer_num_resnet_blocks)]),
-                downsample_klass(dim_out) if not is_last else nn.Identity()
+                downsample_klass(dim_in, dim_out = dim_out) if memory_efficient else None,
+                ResnetBlock(dim_layer, dim_layer, time_cond_dim = time_cond_dim, groups = groups),
+                nn.ModuleList([ResnetBlock(dim_layer, dim_layer, cond_dim = layer_cond_dim, time_cond_dim = time_cond_dim, groups = groups) for _ in range(layer_num_resnet_blocks)]),
+                attention,
+                downsample_klass(dim_layer, dim_out = dim_out) if not is_last and not memory_efficient else nn.Conv2d(dim_layer, dim_out, 1)
             ]))
 
         mid_dim = dims[-1]
 
         self.mid_block1 = ResnetBlock(mid_dim, mid_dim, cond_dim = cond_dim, time_cond_dim = time_cond_dim, groups = resnet_groups[-1])
-        self.mid_attn = EinopsToAndFrom('b c h w', 'b (h w) c', Residual(Attention(mid_dim, **attn_kwargs))) if attend_at_middle else None
+        self.mid_attn = create_self_attn(mid_dim)
         self.mid_block2 = ResnetBlock(mid_dim, mid_dim, cond_dim = cond_dim, time_cond_dim = time_cond_dim, groups = resnet_groups[-1])
 
-        for ind, ((dim_in, dim_out), groups, layer_num_resnet_blocks) in enumerate(zip(reversed(in_out[1:]), reversed(resnet_groups), reversed(num_resnet_blocks))):
-            is_last = ind >= (num_resolutions - 2)
+        for ind, ((dim_in, dim_out), groups, layer_num_resnet_blocks, layer_self_attn) in enumerate(zip(reversed(in_out), reversed(resnet_groups), reversed(num_resnet_blocks), reversed(self_attn))):
+            is_last = ind >= (len(in_out) - 1)
             layer_cond_dim = cond_dim if not is_last else None
 
+            skip_connect_dim = skip_connect_dims.pop()
+
+            attention = nn.Identity()
+            if layer_self_attn:
+                attention = create_self_attn(dim_out)
+            elif sparse_attn:
+                attention = Residual(LinearAttention(dim_out, **attn_kwargs))
+
             self.ups.append(nn.ModuleList([
-                ResnetBlock(dim_out * 2, dim_in, cond_dim = layer_cond_dim, time_cond_dim = time_cond_dim, groups = groups),
-                Residual(LinearAttention(dim_in, **attn_kwargs)) if sparse_attn else nn.Identity(),
-                nn.ModuleList([ResnetBlock(dim_in, dim_in, cond_dim = layer_cond_dim, time_cond_dim = time_cond_dim, groups = groups)  for _ in range(layer_num_resnet_blocks)]),
-                Upsample(dim_in)
+                ResnetBlock(dim_out + skip_connect_dim, dim_out, cond_dim = layer_cond_dim, time_cond_dim = time_cond_dim, groups = groups),
+                nn.ModuleList([ResnetBlock(dim_out + skip_connect_dim, dim_out, cond_dim = layer_cond_dim, time_cond_dim = time_cond_dim, groups = groups)  for _ in range(layer_num_resnet_blocks)]),
+                attention,
+                upsample_klass(dim_out, dim_in) if not is_last or memory_efficient else nn.Identity()
             ]))
 
-        self.final_conv = nn.Sequential(
-            ResnetBlock(dim, dim, groups = resnet_groups[0]),
-            nn.Conv2d(dim, self.channels_out, 1)
-        )
+        self.final_resnet_block = ResnetBlock(dim * 2, dim, time_cond_dim = time_cond_dim, groups = top_level_resnet_group)
+        self.to_out = nn.Conv2d(dim, self.channels_out, kernel_size = final_conv_kernel_size, padding = final_conv_kernel_size // 2)
 
     # if the current settings for the unet are not correct
     # for cascading DDPM, then reinit the unet with the right settings
@@ -1550,6 +1620,7 @@ class Unet(nn.Module):
         # initial convolution
 
         x = self.init_conv(x)
+        r = x.clone() # final residual
 
         # time conditioning
 
@@ -1563,7 +1634,23 @@ class Unet(nn.Module):
         image_keep_mask = prob_mask_like((batch_size,), 1 - image_cond_drop_prob, device = device)
         text_keep_mask = prob_mask_like((batch_size,), 1 - text_cond_drop_prob, device = device)
 
-        image_keep_mask, text_keep_mask = rearrange_many((image_keep_mask, text_keep_mask), 'b -> b 1 1')
+        text_keep_mask = rearrange(text_keep_mask, 'b -> b 1 1')
+
+        # image embedding to be summed to time embedding
+        # discovered by @mhh0318 in the paper
+
+        if exists(image_embed) and exists(self.to_image_hiddens):
+            image_hiddens = self.to_image_hiddens(image_embed)
+            image_keep_mask_hidden = rearrange(image_keep_mask, 'b -> b 1')
+            null_image_hiddens = self.null_image_hiddens.to(image_hiddens.dtype)
+
+            image_hiddens = torch.where(
+                image_keep_mask_hidden,
+                image_hiddens,
+                null_image_hiddens
+            )
+
+            t = t + image_hiddens
 
         # mask out image embedding depending on condition dropout
         # for classifier free guidance
@@ -1571,11 +1658,12 @@ class Unet(nn.Module):
         image_tokens = None
 
         if self.cond_on_image_embeds:
-            image_tokens = self.image_to_cond(image_embed)
+            image_keep_mask_embed = rearrange(image_keep_mask, 'b -> b 1 1')
+            image_tokens = self.image_to_tokens(image_embed)
             null_image_embed = self.null_image_embed.to(image_tokens.dtype) # for some reason pytorch AMP not working
 
             image_tokens = torch.where(
-                image_keep_mask,
+                image_keep_mask_embed,
                 image_tokens,
                 null_image_embed
             )
@@ -1626,44 +1714,61 @@ class Unet(nn.Module):
         c = self.norm_cond(c)
         mid_c = self.norm_mid_cond(mid_c)
 
+        # initial resnet block
+
+        if exists(self.init_resnet_block):
+            x = self.init_resnet_block(x, t)
+
         # go through the layers of the unet, down and up
 
         hiddens = []
 
-        for init_block, sparse_attn, resnet_blocks, downsample in self.downs:
-            x = init_block(x, c, t)
-            x = sparse_attn(x)
+        for pre_downsample, init_block, resnet_blocks, attn, post_downsample in self.downs:
+            if exists(pre_downsample):
+                x = pre_downsample(x)
+
+            x = init_block(x, t, c)
 
             for resnet_block in resnet_blocks:
-                x = resnet_block(x, c, t)
+                x = resnet_block(x, t, c)
+                hiddens.append(x)
 
+            x = attn(x)
             hiddens.append(x)
-            x = downsample(x)
 
-        x = self.mid_block1(x, mid_c, t)
+            if exists(post_downsample):
+                x = post_downsample(x)
+
+        x = self.mid_block1(x, t, mid_c)
 
         if exists(self.mid_attn):
             x = self.mid_attn(x)
 
-        x = self.mid_block2(x, mid_c, t)
+        x = self.mid_block2(x, t, mid_c)
 
-        for init_block, sparse_attn, resnet_blocks, upsample in self.ups:
-            x = torch.cat((x, hiddens.pop()), dim=1)
-            x = init_block(x, c, t)
-            x = sparse_attn(x)
+        connect_skip = lambda fmap: torch.cat((fmap, hiddens.pop() * self.skip_connect_scale), dim = 1)
+
+        for init_block, resnet_blocks, attn, upsample in self.ups:
+            x = connect_skip(x)
+            x = init_block(x, t, c)
 
             for resnet_block in resnet_blocks:
-                x = resnet_block(x, c, t)
+                x = connect_skip(x)
+                x = resnet_block(x, t, c)
 
+            x = attn(x)
             x = upsample(x)
 
-        return self.final_conv(x)
+        x = torch.cat((x, r), dim = 1)
+
+        x = self.final_resnet_block(x, t)
+        return self.to_out(x)
 
 class LowresConditioner(nn.Module):
     def __init__(
         self,
         downsample_first = True,
-        blur_sigma = 0.1,
+        blur_sigma = 0.6,
         blur_kernel_size = 3,
     ):
         super().__init__()
@@ -1687,13 +1792,25 @@ class LowresConditioner(nn.Module):
             # when training, blur the low resolution conditional image
             blur_sigma = default(blur_sigma, self.blur_sigma)
             blur_kernel_size = default(blur_kernel_size, self.blur_kernel_size)
+
+            # allow for drawing a random sigma between lo and hi float values
+            if isinstance(blur_sigma, tuple):
+                blur_sigma = tuple(map(float, blur_sigma))
+                blur_sigma = random.uniform(*blur_sigma)
+
+            # allow for drawing a random kernel size between lo and hi int values
+            if isinstance(blur_kernel_size, tuple):
+                blur_kernel_size = tuple(map(int, blur_kernel_size))
+                kernel_size_lo, kernel_size_hi = blur_kernel_size
+                blur_kernel_size = random.randrange(kernel_size_lo, kernel_size_hi + 1)
+
             cond_fmap = gaussian_blur2d(cond_fmap, cast_tuple(blur_kernel_size, 2), cast_tuple(blur_sigma, 2))
 
         cond_fmap = resize_image_to(cond_fmap, target_image_size)
 
         return cond_fmap
 
-class Decoder(BaseGaussianDiffusion):
+class Decoder(nn.Module):
     def __init__(
         self,
         unet,
@@ -1706,37 +1823,28 @@ class Decoder(BaseGaussianDiffusion):
         image_cond_drop_prob = 0.1,
         text_cond_drop_prob = 0.5,
         loss_type = 'l2',
-        beta_schedule = 'cosine',
+        beta_schedule = None,
         predict_x_start = False,
         predict_x_start_for_latent_diffusion = False,
         image_sizes = None,                         # for cascading ddpm, image size at each stage
         random_crop_sizes = None,                   # whether to random crop the image at that stage in the cascade (super resoluting convolutions at the end may be able to generalize on smaller crops)
         lowres_downsample_first = True,             # cascading ddpm - resizes to lower resolution, then to next conditional resolution + blur
-        blur_sigma = 0.1,                           # cascading ddpm - blur sigma
+        blur_sigma = 0.6,                           # cascading ddpm - blur sigma
         blur_kernel_size = 3,                       # cascading ddpm - blur kernel size
-        condition_on_text_encodings = False,        # the paper suggested that this didn't do much in the decoder, but i'm allowing the option for experimentation
         clip_denoised = True,
         clip_x_start = True,
         clip_adapter_overrides = dict(),
         learned_variance = True,
+        learned_variance_constrain_frac = False,
         vb_loss_weight = 0.001,
-        unconditional = False,
+        unconditional = False,                      # set to True for generating images without conditioning
         auto_normalize_img = True,                  # whether to take care of normalizing the image from [0, 1] to [-1, 1] and back automatically - you can turn this off if you want to pass in the [-1, 1] ranged image yourself from the dataloader
         use_dynamic_thres = False,                  # from the Imagen paper
-        dynamic_thres_percentile = 0.9
+        dynamic_thres_percentile = 0.9,
+        p2_loss_weight_gamma = 0.,                  # p2 loss weight, from https://arxiv.org/abs/2204.00227 - 0 is equivalent to weight of 1 across time - 1. is recommended
+        p2_loss_weight_k = 1
     ):
-        super().__init__(
-            beta_schedule = beta_schedule,
-            timesteps = timesteps,
-            loss_type = loss_type
-        )
-
-        self.unconditional = unconditional
-
-        # text conditioning
-
-        assert not (condition_on_text_encodings and unconditional), 'unconditional decoder image generation cannot be set to True if conditioning on text is present'
-        self.condition_on_text_encodings = condition_on_text_encodings
+        super().__init__()
 
         # clip
 
@@ -1769,16 +1877,23 @@ class Decoder(BaseGaussianDiffusion):
 
         self.channels = channels
 
+        # verify conditioning method
+
+        unets = cast_tuple(unet)
+        num_unets = len(unets)
+
+        self.unconditional = unconditional
+
         # automatically take care of ensuring that first unet is unconditional
         # while the rest of the unets are conditioned on the low resolution image produced by previous unet
 
-        unets = cast_tuple(unet)
         vaes = pad_tuple_to_length(cast_tuple(vae), len(unets), fillvalue = NullVQGanVAE(channels = self.channels))
 
         # whether to use learned variance, defaults to True for the first unet in the cascade, as in paper
 
         learned_variance = pad_tuple_to_length(cast_tuple(learned_variance), len(unets), fillvalue = False)
         self.learned_variance = learned_variance
+        self.learned_variance_constrain_frac = learned_variance_constrain_frac # whether to constrain the output of the network (the interpolation fraction) from 0 to 1
         self.vb_loss_weight = vb_loss_weight
 
         # construct unets and vaes
@@ -1798,8 +1913,8 @@ class Decoder(BaseGaussianDiffusion):
 
             one_unet = one_unet.cast_model_parameters(
                 lowres_cond = not is_first,
-                cond_on_image_embeds = is_first and not unconditional,
-                cond_on_text_encodings = one_unet.cond_on_text_encodings and not unconditional,
+                cond_on_image_embeds = not unconditional and is_first,
+                cond_on_text_encodings = not unconditional and one_unet.cond_on_text_encodings,
                 channels = unet_channels,
                 channels_out = unet_channels_out
             )
@@ -1807,6 +1922,31 @@ class Decoder(BaseGaussianDiffusion):
             self.unets.append(one_unet)
             self.vaes.append(one_vae.copy_for_eval())
 
+        # determine from unets whether conditioning on text encoding is needed
+
+        self.condition_on_text_encodings = any([unet.cond_on_text_encodings for unet in self.unets])
+
+        # create noise schedulers per unet
+
+        if not exists(beta_schedule):
+            beta_schedule = ('cosine', *(('cosine',) * max(num_unets - 2, 0)), *(('linear',) * int(num_unets > 1)))
+
+        beta_schedule = cast_tuple(beta_schedule, num_unets)
+        p2_loss_weight_gamma = cast_tuple(p2_loss_weight_gamma, num_unets)
+
+        self.noise_schedulers = nn.ModuleList([])
+
+        for unet_beta_schedule, unet_p2_loss_weight_gamma in zip(beta_schedule, p2_loss_weight_gamma):
+            noise_scheduler = NoiseScheduler(
+                beta_schedule = unet_beta_schedule,
+                timesteps = timesteps,
+                loss_type = loss_type,
+                p2_loss_weight_gamma = unet_p2_loss_weight_gamma,
+                p2_loss_weight_k = p2_loss_weight_k
+            )
+
+            self.noise_schedulers.append(noise_scheduler)
+
         # unet image sizes
 
         image_sizes = default(image_sizes, (image_size,))
@@ -1856,6 +1996,14 @@ class Decoder(BaseGaussianDiffusion):
         self.normalize_img = normalize_neg_one_to_one if auto_normalize_img else identity
         self.unnormalize_img = unnormalize_zero_to_one if auto_normalize_img else identity
 
+        # device tracker
+
+        self.register_buffer('_dummy', torch.Tensor([True]), persistent = False)
+
+    @property
+    def device(self):
+        return self._dummy.device
+
     def get_unet(self, unet_number):
         assert 0 < unet_number <= len(self.unets)
         index = unet_number - 1
@@ -1879,7 +2027,7 @@ class Decoder(BaseGaussianDiffusion):
         for unet, device in zip(self.unets, devices):
             unet.to(device)
 
-    def p_mean_variance(self, unet, x, t, image_embed, text_encodings = None, text_mask = None, lowres_cond_img = None, clip_denoised = True, predict_x_start = False, learned_variance = False, cond_scale = 1., model_output = None):
+    def p_mean_variance(self, unet, x, t, image_embed, noise_scheduler, text_encodings = None, text_mask = None, lowres_cond_img = None, clip_denoised = True, predict_x_start = False, learned_variance = False, cond_scale = 1., model_output = None):
         assert not (cond_scale != 1. and not self.can_classifier_guidance), 'the decoder was not trained with conditional dropout, and thus one cannot use classifier free guidance (cond_scale anything other than 1)'
 
         pred = default(model_output, lambda: unet.forward_with_cond_scale(x, t, image_embed = image_embed, text_encodings = text_encodings, text_mask = text_mask, cond_scale = cond_scale, lowres_cond_img = lowres_cond_img))
@@ -1890,7 +2038,7 @@ class Decoder(BaseGaussianDiffusion):
         if predict_x_start:
             x_recon = pred
         else:
-            x_recon = self.predict_start_from_noise(x, t = t, noise = pred)
+            x_recon = noise_scheduler.predict_start_from_noise(x, t = t, noise = pred)
 
         if clip_denoised:
             # s is the threshold amount
@@ -1909,33 +2057,36 @@ class Decoder(BaseGaussianDiffusion):
             # clip by threshold, depending on whether static or dynamic
             x_recon = x_recon.clamp(-s, s) / s
 
-        model_mean, posterior_variance, posterior_log_variance = self.q_posterior(x_start=x_recon, x_t=x, t=t)
+        model_mean, posterior_variance, posterior_log_variance = noise_scheduler.q_posterior(x_start=x_recon, x_t=x, t=t)
 
         if learned_variance:
             # if learned variance, posterio variance and posterior log variance are predicted by the network
             # by an interpolation of the max and min log beta values
             # eq 15 - https://arxiv.org/abs/2102.09672
-            min_log = extract(self.posterior_log_variance_clipped, t, x.shape)
-            max_log = extract(torch.log(self.betas), t, x.shape)
+            min_log = extract(noise_scheduler.posterior_log_variance_clipped, t, x.shape)
+            max_log = extract(torch.log(noise_scheduler.betas), t, x.shape)
             var_interp_frac = unnormalize_zero_to_one(var_interp_frac_unnormalized)
 
+            if self.learned_variance_constrain_frac:
+                var_interp_frac = var_interp_frac.sigmoid()
+
             posterior_log_variance = var_interp_frac * max_log + (1 - var_interp_frac) * min_log
             posterior_variance = posterior_log_variance.exp()
 
         return model_mean, posterior_variance, posterior_log_variance
 
     @torch.no_grad()
-    def p_sample(self, unet, x, t, image_embed, text_encodings = None, text_mask = None, cond_scale = 1., lowres_cond_img = None, predict_x_start = False, learned_variance = False, clip_denoised = True, repeat_noise = False):
+    def p_sample(self, unet, x, t, image_embed, noise_scheduler, text_encodings = None, text_mask = None, cond_scale = 1., lowres_cond_img = None, predict_x_start = False, learned_variance = False, clip_denoised = True):
         b, *_, device = *x.shape, x.device
-        model_mean, _, model_log_variance = self.p_mean_variance(unet, x = x, t = t, image_embed = image_embed, text_encodings = text_encodings, text_mask = text_mask, cond_scale = cond_scale, lowres_cond_img = lowres_cond_img, clip_denoised = clip_denoised, predict_x_start = predict_x_start, learned_variance = learned_variance)
-        noise = noise_like(x.shape, device, repeat_noise)
+        model_mean, _, model_log_variance = self.p_mean_variance(unet, x = x, t = t, image_embed = image_embed, text_encodings = text_encodings, text_mask = text_mask, cond_scale = cond_scale, lowres_cond_img = lowres_cond_img, clip_denoised = clip_denoised, predict_x_start = predict_x_start, noise_scheduler = noise_scheduler, learned_variance = learned_variance)
+        noise = torch.randn_like(x)
         # no noise when t == 0
         nonzero_mask = (1 - (t == 0).float()).reshape(b, *((1,) * (len(x.shape) - 1)))
         return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise
 
     @torch.no_grad()
-    def p_sample_loop(self, unet, shape, image_embed, predict_x_start = False, learned_variance = False, clip_denoised = True, lowres_cond_img = None, text_encodings = None, text_mask = None, cond_scale = 1, is_latent_diffusion = False):
-        device = self.betas.device
+    def p_sample_loop(self, unet, shape, image_embed, noise_scheduler, predict_x_start = False, learned_variance = False, clip_denoised = True, lowres_cond_img = None, text_encodings = None, text_mask = None, cond_scale = 1, is_latent_diffusion = False):
+        device = self.device
 
         b = shape[0]
         img = torch.randn(shape, device = device)
@@ -1943,7 +2094,7 @@ class Decoder(BaseGaussianDiffusion):
         if not is_latent_diffusion:
             lowres_cond_img = maybe(self.normalize_img)(lowres_cond_img)
 
-        for i in tqdm(reversed(range(0, self.num_timesteps)), desc = 'sampling loop time step', total = self.num_timesteps):
+        for i in tqdm(reversed(range(0, noise_scheduler.num_timesteps)), desc = 'sampling loop time step', total = noise_scheduler.num_timesteps):
             img = self.p_sample(
                 unet,
                 img,
@@ -1954,6 +2105,7 @@ class Decoder(BaseGaussianDiffusion):
                 cond_scale = cond_scale,
                 lowres_cond_img = lowres_cond_img,
                 predict_x_start = predict_x_start,
+                noise_scheduler = noise_scheduler,
                 learned_variance = learned_variance,
                 clip_denoised = clip_denoised
             )
@@ -1961,7 +2113,7 @@ class Decoder(BaseGaussianDiffusion):
         unnormalize_img = self.unnormalize_img(img)
         return unnormalize_img
 
-    def p_losses(self, unet, x_start, times, *, image_embed, lowres_cond_img = None, text_encodings = None, text_mask = None, predict_x_start = False, noise = None, learned_variance = False, clip_denoised = False, is_latent_diffusion = False):
+    def p_losses(self, unet, x_start, times, *, image_embed, noise_scheduler, lowres_cond_img = None, text_encodings = None, text_mask = None, predict_x_start = False, noise = None, learned_variance = False, clip_denoised = False, is_latent_diffusion = False):
         noise = default(noise, lambda: torch.randn_like(x_start))
 
         # normalize to [-1, 1]
@@ -1972,7 +2124,7 @@ class Decoder(BaseGaussianDiffusion):
 
         # get x_t
 
-        x_noisy = self.q_sample(x_start = x_start, t = times, noise = noise)
+        x_noisy = noise_scheduler.q_sample(x_start = x_start, t = times, noise = noise)
 
         model_output = unet(
             x_noisy,
@@ -1992,7 +2144,12 @@ class Decoder(BaseGaussianDiffusion):
 
         target = noise if not predict_x_start else x_start
 
-        loss = self.loss_fn(pred, target)
+        loss = noise_scheduler.loss_fn(pred, target, reduction = 'none')
+        loss = reduce(loss, 'b ... -> b (...)', 'mean')
+
+        loss = noise_scheduler.p2_reweigh_loss(loss, times)
+
+        loss = loss.mean()
 
         if not learned_variance:
             # return simple loss if not using learned variance
@@ -2005,8 +2162,8 @@ class Decoder(BaseGaussianDiffusion):
 
         # if learning the variance, also include the extra weight kl loss
 
-        true_mean, _, true_log_variance_clipped = self.q_posterior(x_start = x_start, x_t = x_noisy, t = times)
-        model_mean, _, model_log_variance = self.p_mean_variance(unet, x = x_noisy, t = times, image_embed = image_embed, clip_denoised = clip_denoised, learned_variance = True, model_output = model_output)
+        true_mean, _, true_log_variance_clipped = noise_scheduler.q_posterior(x_start = x_start, x_t = x_noisy, t = times)
+        model_mean, _, model_log_variance = self.p_mean_variance(unet, x = x_noisy, t = times, image_embed = image_embed, noise_scheduler = noise_scheduler, clip_denoised = clip_denoised, learned_variance = True, model_output = model_output)
 
         # kl loss with detached model predicted mean, for stability reasons as in paper
 
@@ -2038,7 +2195,8 @@ class Decoder(BaseGaussianDiffusion):
         text_encodings = None,
         batch_size = 1,
         cond_scale = 1.,
-        stop_at_unet_number = None
+        stop_at_unet_number = None,
+        distributed = False,
     ):
         assert self.unconditional or exists(image_embed), 'image embed must be present on sampling from decoder unless if trained unconditionally'
 
@@ -2055,9 +2213,9 @@ class Decoder(BaseGaussianDiffusion):
         img = None
         is_cuda = next(self.parameters()).is_cuda
 
-        for unet_number, unet, vae, channel, image_size, predict_x_start, learned_variance in tqdm(zip(range(1, len(self.unets) + 1), self.unets, self.vaes, self.sample_channels, self.image_sizes, self.predict_x_start, self.learned_variance)):
+        for unet_number, unet, vae, channel, image_size, predict_x_start, learned_variance, noise_scheduler in tqdm(zip(range(1, len(self.unets) + 1), self.unets, self.vaes, self.sample_channels, self.image_sizes, self.predict_x_start, self.learned_variance, self.noise_schedulers)):
 
-            context = self.one_unet_in_gpu(unet = unet) if is_cuda else null_context()
+            context = self.one_unet_in_gpu(unet = unet) if is_cuda and not distributed else null_context()
 
             with context:
                 lowres_cond_img = None
@@ -2083,7 +2241,8 @@ class Decoder(BaseGaussianDiffusion):
                     learned_variance = learned_variance,
                     clip_denoised = not is_latent_diffusion,
                     lowres_cond_img = lowres_cond_img,
-                    is_latent_diffusion = is_latent_diffusion
+                    is_latent_diffusion = is_latent_diffusion,
+                    noise_scheduler = noise_scheduler
                 )
 
                 img = vae.decode(img)
@@ -2100,7 +2259,8 @@ class Decoder(BaseGaussianDiffusion):
         image_embed = None,
         text_encodings = None,
         text_mask = None,
-        unet_number = None
+        unet_number = None,
+        return_lowres_cond_image = False # whether to return the low resolution conditioning images, for debugging upsampler purposes
     ):
         assert not (len(self.unets) > 1 and not exists(unet_number)), f'you must specify which unet you want trained, from a range of 1 to {len(self.unets)}, if you are training cascading DDPM (multiple unets)'
         unet_number = default(unet_number, 1)
@@ -2109,6 +2269,7 @@ class Decoder(BaseGaussianDiffusion):
         unet = self.get_unet(unet_number)
 
         vae                 = self.vaes[unet_index]
+        noise_scheduler     = self.noise_schedulers[unet_index]
         target_image_size   = self.image_sizes[unet_index]
         predict_x_start     = self.predict_x_start[unet_index]
         random_crop_size    = self.random_crop_sizes[unet_index]
@@ -2118,7 +2279,7 @@ class Decoder(BaseGaussianDiffusion):
         check_shape(image, 'b c h w', c = self.channels)
         assert h >= target_image_size and w >= target_image_size
 
-        times = torch.randint(0, self.num_timesteps, (b,), device = device, dtype = torch.long)
+        times = torch.randint(0, noise_scheduler.num_timesteps, (b,), device = device, dtype = torch.long)
 
         if not exists(image_embed) and not self.unconditional:
             assert exists(self.clip), 'if you want to derive CLIP image embeddings automatically, you must supply `clip` to the decoder on init'
@@ -2149,7 +2310,12 @@ class Decoder(BaseGaussianDiffusion):
             image = vae.encode(image)
             lowres_cond_img = maybe(vae.encode)(lowres_cond_img)
 
-        return self.p_losses(unet, image, times, image_embed = image_embed, text_encodings = text_encodings, text_mask = text_mask, lowres_cond_img = lowres_cond_img, predict_x_start = predict_x_start, learned_variance = learned_variance, is_latent_diffusion = is_latent_diffusion)
+        losses = self.p_losses(unet, image, times, image_embed = image_embed, text_encodings = text_encodings, text_mask = text_mask, lowres_cond_img = lowres_cond_img, predict_x_start = predict_x_start, learned_variance = learned_variance, is_latent_diffusion = is_latent_diffusion, noise_scheduler = noise_scheduler)
+
+        if not return_lowres_cond_image:
+            return losses
+
+        return losses, lowres_cond_img
 
 # main class
 
@@ -2197,6 +2363,6 @@ class DALLE2(nn.Module):
             images = list(map(self.to_pil, images.unbind(dim = 0)))
 
         if one_text:
-            return images[0]
+            return first(images)
 
         return images

dalle2_pytorch/dataloaders/README.md

@@ -15,7 +15,7 @@ from dalle2_pytorch.dataloaders import ImageEmbeddingDataset, create_image_embed
 
 # Create a dataloader directly.
 dataloader = create_image_embedding_dataloader(
-    tar_url="/path/or/url/to/webdataset/{0000..9999}.tar", # Uses braket expanding notation. This specifies to read all tars from 0000.tar to 9999.tar
+    tar_url="/path/or/url/to/webdataset/{0000..9999}.tar", # Uses bracket expanding notation. This specifies to read all tars from 0000.tar to 9999.tar
     embeddings_url="path/or/url/to/embeddings/folder",     # Included if .npy files are not in webdataset. Left out or set to None otherwise
     num_workers=4,
     batch_size=32,

dalle2_pytorch/dataloaders/decoder_loader.py

@@ -21,7 +21,7 @@ def get_example_file(fs, path, file_format):
     """
     return fs.glob(os.path.join(path, f"*.{file_format}"))[0]
 
-def embedding_inserter(samples, embeddings_url, index_width, handler=wds.handlers.reraise_exception):
+def embedding_inserter(samples, embeddings_url, index_width, sample_key='npy', handler=wds.handlers.reraise_exception):
     """Given a datum of {"__key__": str, "__url__": str, ...} adds the cooresponding embedding and yields"""
     previous_tar_url = None
     current_embeddings = None
@@ -56,7 +56,7 @@ def embedding_inserter(samples, embeddings_url, index_width, handler=wds.handler
             # We need to check if this sample is nonzero. If it is, this embedding is not valid and we should continue to the next loop
             if torch.count_nonzero(embedding) == 0:
                 raise RuntimeError(f"Webdataset had a sample, but no embedding was found. ImgShard: {key[:-index_width]} - Index: {key[-index_width:]}")
-            sample["npy"] = embedding
+            sample[sample_key] = embedding
             yield sample
         except Exception as exn:  # From wds implementation
             if handler(exn):
@@ -84,18 +84,20 @@ def unassociated_shard_skipper(tarfiles, embeddings_url, handler=wds.handlers.re
                 continue
             else:
                 break
-    
 skip_unassociated_shards = wds.filters.pipelinefilter(unassociated_shard_skipper)
 
-def verify_keys(samples, handler=wds.handlers.reraise_exception):
+def join_embeddings(samples, handler=wds.handlers.reraise_exception):
     """
-    Requires that both the image and embedding are present in the sample
-    This is important to do as a user may forget they do not have embeddings in their webdataset and neglect to add them using the embedding_folder_url parameter.
+    Takes the img_emb and text_emb keys and turns them into one key "emb": { "text": text_emb, "img": img_emb }
+    either or both of text_emb and img_emb may not be in the sample so we only add the ones that exist
     """
     for sample in samples:
         try:
-            assert "jpg" in sample, f"Sample {sample['__key__']} missing image"
-            assert "npy" in sample, f"Sample {sample['__key__']} missing embedding. Did you set embedding_folder_url?"
+            sample['emb'] = {}
+            if 'text_emb' in sample:
+                sample['emb']['text'] = sample['text_emb']
+            if 'img_emb' in sample:
+                sample['emb']['img'] = sample['img_emb']
             yield sample
         except Exception as exn:  # From wds implementation
             if handler(exn):
@@ -103,6 +105,23 @@ def verify_keys(samples, handler=wds.handlers.reraise_exception):
             else:
                 break
 
+def verify_keys(samples, required_keys, handler=wds.handlers.reraise_exception):
+    """
+    Requires that both the image and embedding are present in the sample
+    This is important to do as a user may forget they do not have embeddings in their webdataset and neglect to add them using the embedding_folder_url parameter.
+    """
+    for sample in samples:
+        try:
+            for key in required_keys:
+                assert key in sample, f"Sample {sample['__key__']} missing {key}. Has keys {sample.keys()}"
+            yield sample
+        except Exception as exn:  # From wds implementation
+            if handler(exn):
+                continue
+            else:
+                break
+key_verifier = wds.filters.pipelinefilter(verify_keys)
+
 class ImageEmbeddingDataset(wds.DataPipeline, wds.compat.FluidInterface):
     """
     A fluid interface wrapper for DataPipline that returns image embedding pairs
@@ -112,7 +131,8 @@ class ImageEmbeddingDataset(wds.DataPipeline, wds.compat.FluidInterface):
     def __init__(
             self,
             urls,
-            embedding_folder_url=None,
+            img_embedding_folder_url=None,
+            text_embedding_folder_url=None,
             index_width=None,
             img_preproc=None,
             extra_keys=[],
@@ -136,7 +156,12 @@ class ImageEmbeddingDataset(wds.DataPipeline, wds.compat.FluidInterface):
 
         """
         super().__init__()
-        keys = ["jpg", "npy"] + extra_keys
+        keys = ["jpg", "emb"] + extra_keys
+        # if img_embedding_folder_url is not None:
+        #     keys.append("img_emb")
+        # if text_embedding_folder_url is not None:
+        #     keys.append("text_emb")
+        # keys.extend(extra_keys)
         self.key_map = {key: i for i, key in enumerate(keys)}
         self.resampling = resample
         self.img_preproc = img_preproc
@@ -145,7 +170,7 @@ class ImageEmbeddingDataset(wds.DataPipeline, wds.compat.FluidInterface):
             # Then this has an s3 link for the webdataset and we need extra packages
             if shutil.which("s3cmd") is None:
                 raise RuntimeError("s3cmd is required for s3 webdataset")
-        if "s3:" in embedding_folder_url:
+        if (img_embedding_folder_url is not None and "s3:" in img_embedding_folder_url) or (text_embedding_folder_url is not None and "s3:" in text_embedding_folder_url):
             # Then the embeddings are being loaded from s3 and fsspec requires s3fs
             try:
                 import s3fs
@@ -160,20 +185,24 @@ class ImageEmbeddingDataset(wds.DataPipeline, wds.compat.FluidInterface):
             if shuffle_shards:
                 self.append(wds.filters.shuffle(1000))
         
-        if embedding_folder_url is not None:
+        if img_embedding_folder_url is not None:
             # There may be webdataset shards that do not have a embedding shard associated with it. If we do not skip these, they would cause issues.
-            self.append(skip_unassociated_shards(embeddings_url=embedding_folder_url, handler=handler))
-
-        self.append(wds.split_by_node)
-        self.append(wds.split_by_worker)
+            self.append(skip_unassociated_shards(embeddings_url=img_embedding_folder_url, handler=handler))
+        if text_embedding_folder_url is not None:
+            self.append(skip_unassociated_shards(embeddings_url=text_embedding_folder_url, handler=handler))
 
         self.append(wds.tarfile_to_samples(handler=handler))
         self.append(wds.decode("pilrgb", handler=handler))
-        if embedding_folder_url is not None:
-            # Then we are loading embeddings for a remote source
+        if img_embedding_folder_url is not None:
+            # Then we are loading image embeddings for a remote source
             assert index_width is not None, "Reading embeddings separately requires index width length to be given"
-            self.append(insert_embedding(embeddings_url=embedding_folder_url, index_width=index_width, handler=handler))
-        self.append(verify_keys)
+            self.append(insert_embedding(embeddings_url=img_embedding_folder_url, index_width=index_width, sample_key='img_emb', handler=handler))
+        if text_embedding_folder_url is not None:
+            # Then we are loading image embeddings for a remote source
+            assert index_width is not None, "Reading embeddings separately requires index width length to be given"
+            self.append(insert_embedding(embeddings_url=text_embedding_folder_url, index_width=index_width, sample_key='text_emb', handler=handler))
+        self.append(join_embeddings)
+        self.append(key_verifier(required_keys=keys, handler=handler))
         # Apply preprocessing
         self.append(wds.map(self.preproc))
         self.append(wds.to_tuple(*keys))
@@ -188,7 +217,8 @@ def create_image_embedding_dataloader(
     tar_url,
     num_workers,
     batch_size,
-    embeddings_url=None,
+    img_embeddings_url=None,
+    text_embeddings_url=None,
     index_width=None,
     shuffle_num = None,
     shuffle_shards = True,
@@ -214,7 +244,8 @@ def create_image_embedding_dataloader(
     """
     ds = ImageEmbeddingDataset(
         tar_url,
-        embeddings_url,
+        img_embedding_folder_url=img_embeddings_url,
+        text_embedding_folder_url=text_embeddings_url,
         index_width=index_width,
         shuffle_shards=shuffle_shards,
         resample=resample_shards,
@@ -231,4 +262,4 @@ def create_image_embedding_dataloader(
         prefetch_factor=2,  # This might be good to have high so the next npy file is prefetched
         pin_memory=True,
         shuffle=False
-    )
+    )

dalle2_pytorch/optimizer.py

@@ -1,15 +1,17 @@
 from torch.optim import AdamW, Adam
 
 def separate_weight_decayable_params(params):
-    no_wd_params = set([param for param in params if param.ndim < 2])
-    wd_params = set(params) - no_wd_params
+    wd_params, no_wd_params = [], []
+    for param in params:
+        param_list = no_wd_params if param.ndim < 2 else wd_params
+        param_list.append(param)
     return wd_params, no_wd_params
 
 def get_optimizer(
     params,
     lr = 1e-4,
     wd = 1e-2,
-    betas = (0.9, 0.999),
+    betas = (0.9, 0.99),
     eps = 1e-8,
     filter_by_requires_grad = False,
     group_wd_params = True,
@@ -25,8 +27,8 @@ def get_optimizer(
         wd_params, no_wd_params = separate_weight_decayable_params(params)
 
         params = [
-            {'params': list(wd_params)},
-            {'params': list(no_wd_params), 'weight_decay': 0},
+            {'params': wd_params},
+            {'params': no_wd_params, 'weight_decay': 0},
         ]
 
     return AdamW(params, lr = lr, weight_decay = wd, betas = betas, eps = eps)

dalle2_pytorch/tokenizer.py

@@ -2,7 +2,6 @@
 # to give users a quick easy start to training DALL-E without doing BPE
 
 import torch
-import youtokentome as yttm
 
 import html
 import os
@@ -11,6 +10,8 @@ import regex as re
 from functools import lru_cache
 from pathlib import Path
 
+from dalle2_pytorch.utils import import_or_print_error
+
 # OpenAI simple tokenizer
 
 @lru_cache()
@@ -156,7 +157,9 @@ class YttmTokenizer:
         bpe_path = Path(bpe_path)
         assert bpe_path.exists(), f'BPE json path {str(bpe_path)} does not exist'
 
-        tokenizer = yttm.BPE(model = str(bpe_path))
+        self.yttm = import_or_print_error('youtokentome', 'you need to install youtokentome by `pip install youtokentome`')
+
+        tokenizer = self.yttm.BPE(model = str(bpe_path))
         self.tokenizer = tokenizer
         self.vocab_size = tokenizer.vocab_size()
 
@@ -167,7 +170,7 @@ class YttmTokenizer:
         return self.tokenizer.decode(tokens, ignore_ids = pad_tokens.union({0}))
 
     def encode(self, texts):
-        encoded = self.tokenizer.encode(texts, output_type = yttm.OutputType.ID)
+        encoded = self.tokenizer.encode(texts, output_type = self.yttm.OutputType.ID)
         return list(map(torch.tensor, encoded))
 
     def tokenize(self, texts, context_length = 256, truncate_text = False):

dalle2_pytorch/trackers.py

@@ -1,10 +1,15 @@
+import urllib.request
 import os
 from pathlib import Path
-import importlib
+import shutil
 from itertools import zip_longest
+from typing import Optional, List, Union
+from pydantic import BaseModel
 
 import torch
-from torch import nn
+
+from dalle2_pytorch.utils import import_or_print_error
+from dalle2_pytorch.trainer import DecoderTrainer, DiffusionPriorTrainer
 
 # constants
 
@@ -15,101 +20,494 @@ DEFAULT_DATA_PATH = './.tracker-data'
 def exists(val):
     return val is not None
 
-def import_or_print_error(pkg_name, err_str = None):
-    try:
-        return importlib.import_module(pkg_name)
-    except ModuleNotFoundError as e:
-        if exists(err_str):
-            print(err_str)
-        exit()
+# load file functions
 
-# load state dict functions
-
-def load_wandb_state_dict(run_path, file_path, **kwargs):
+def load_wandb_file(run_path, file_path, **kwargs):
     wandb = import_or_print_error('wandb', '`pip install wandb` to use the wandb recall function')
     file_reference = wandb.restore(file_path, run_path=run_path)
-    return torch.load(file_reference.name)
+    return file_reference.name
 
-def load_local_state_dict(file_path, **kwargs):
-    return torch.load(file_path)
+def load_local_file(file_path, **kwargs):
+    return file_path
 
-# base class
-
-class BaseTracker(nn.Module):
-    def __init__(self, data_path = DEFAULT_DATA_PATH):
-        super().__init__()
+class BaseLogger:
+    """
+    An abstract class representing an object that can log data.
+    Parameters:
+        data_path (str): A file path for storing temporary data.
+        verbose (bool): Whether of not to always print logs to the console.
+    """
+    def __init__(self, data_path: str, verbose: bool = False, **kwargs):
         self.data_path = Path(data_path)
-        self.data_path.mkdir(parents = True, exist_ok = True)
+        self.verbose = verbose
 
-    def init(self, config, **kwargs):
-        raise NotImplementedError
-
-    def log(self, log, **kwargs):
-        raise NotImplementedError
-
-    def log_images(self, images, **kwargs):
-        raise NotImplementedError
-
-    def save_state_dict(self, state_dict, relative_path, **kwargs):
-        raise NotImplementedError
-
-    def recall_state_dict(self, recall_source, *args, **kwargs):
+    def init(self, full_config: BaseModel, extra_config: dict, **kwargs) -> None:
         """
-        Loads a state dict from any source.
-        Since a user may wish to load a model from a different source than their own tracker (i.e. tracking using wandb but recalling from disk),
-            this should not be linked to any individual tracker.
+        Initializes the logger.
+        Errors if the logger is invalid.
         """
-        # TODO: Pull this into a dict or something similar so that we can add more sources without having a massive switch statement
-        if recall_source == 'wandb':
-            return load_wandb_state_dict(*args, **kwargs)
-        elif recall_source == 'local':
-            return load_local_state_dict(*args, **kwargs)
-        else:
-            raise ValueError('`recall_source` must be one of `wandb` or `local`')
+        raise NotImplementedError
 
+    def log(self, log, **kwargs) -> None:
+        raise NotImplementedError
 
-# basic stdout class
+    def log_images(self, images, captions=[], image_section="images", **kwargs) -> None:
+        raise NotImplementedError
 
-class ConsoleTracker(BaseTracker):
-    def init(self, **config):
-        print(config)
+    def log_file(self, file_path, **kwargs) -> None:
+        raise NotImplementedError
 
-    def log(self, log, **kwargs):
+    def log_error(self, error_string, **kwargs) -> None:
+        raise NotImplementedError
+
+class ConsoleLogger(BaseLogger):
+    def init(self, full_config: BaseModel, extra_config: dict, **kwargs) -> None:
+        print("Logging to console")
+
+    def log(self, log, **kwargs) -> None:
         print(log)
 
-    def log_images(self, images, **kwargs): # noop for logging images
+    def log_images(self, images, captions=[], image_section="images", **kwargs) -> None:
         pass
-    
-    def save_state_dict(self, state_dict, relative_path, **kwargs):
-        torch.save(state_dict, str(self.data_path / relative_path))
 
-# basic wandb class
+    def log_file(self, file_path, **kwargs) -> None:
+        pass
 
-class WandbTracker(BaseTracker):
-    def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-        self.wandb = import_or_print_error('wandb', '`pip install wandb` to use the wandb experiment tracker')
+    def log_error(self, error_string, **kwargs) -> None:
+        print(error_string)
+
+class WandbLogger(BaseLogger):
+    """
+    Logs to a wandb run.
+    Parameters:
+        data_path (str): A file path for storing temporary data.
+        wandb_entity (str): The wandb entity to log to.
+        wandb_project (str): The wandb project to log to.
+        wandb_run_id (str): The wandb run id to resume.
+        wandb_run_name (str): The wandb run name to use.
+        wandb_resume (bool): Whether to resume a wandb run.
+    """
+    def __init__(self,
+        data_path: str,
+        wandb_entity: str,
+        wandb_project: str,
+        wandb_run_id: Optional[str] = None,
+        wandb_run_name: Optional[str] = None,
+        wandb_resume: bool = False,
+        **kwargs
+    ):
+        super().__init__(data_path, **kwargs)
+        self.entity = wandb_entity
+        self.project = wandb_project
+        self.run_id = wandb_run_id
+        self.run_name = wandb_run_name
+        self.resume = wandb_resume
+
+    def init(self, full_config: BaseModel, extra_config: dict, **kwargs) -> None:
+        assert self.entity is not None, "wandb_entity must be specified for wandb logger"
+        assert self.project is not None, "wandb_project must be specified for wandb logger"
+        self.wandb = import_or_print_error('wandb', '`pip install wandb` to use the wandb logger')
         os.environ["WANDB_SILENT"] = "true"
+        # Initializes the wandb run
+        init_object = {
+            "entity": self.entity,
+            "project": self.project,
+            "config": {**full_config.dict(), **extra_config}
+        }
+        if self.run_name is not None:
+            init_object['name'] = self.run_name
+        if self.resume:
+            assert self.run_id is not None, '`wandb_run_id` must be provided if `wandb_resume` is True'
+            if self.run_name is not None:
+                print("You are renaming a run. I hope that is what you intended.")
+            init_object['resume'] = 'must'
+            init_object['id'] = self.run_id
 
-    def init(self, **config):
-        self.wandb.init(**config)
+        self.wandb.init(**init_object)
+        print(f"Logging to wandb run {self.wandb.run.path}-{self.wandb.run.name}")
 
-    def log(self, log, verbose=False, **kwargs):
-        if verbose:
+    def log(self, log, **kwargs) -> None:
+        if self.verbose:
             print(log)
         self.wandb.log(log, **kwargs)
 
-    def log_images(self, images, captions=[], image_section="images", **kwargs):
+    def log_images(self, images, captions=[], image_section="images", **kwargs) -> None:
         """
         Takes a tensor of images and a list of captions and logs them to wandb.
         """
         wandb_images = [self.wandb.Image(image, caption=caption) for image, caption in zip_longest(images, captions)]
-        self.log({ image_section: wandb_images }, **kwargs)
+        self.wandb.log({ image_section: wandb_images }, **kwargs)
+
+    def log_file(self, file_path, base_path: Optional[str] = None, **kwargs) -> None:
+        if base_path is None:
+            # Then we take the basepath as the parent of the file_path
+            base_path = Path(file_path).parent
+        self.wandb.save(str(file_path), base_path = str(base_path))
+
+    def log_error(self, error_string, step=None, **kwargs) -> None:
+        if self.verbose:
+            print(error_string)
+        self.wandb.log({"error": error_string, **kwargs}, step=step)
+
+logger_type_map = {
+    'console': ConsoleLogger,
+    'wandb': WandbLogger,
+}
+def create_logger(logger_type: str, data_path: str, **kwargs) -> BaseLogger:
+    if logger_type == 'custom':
+        raise NotImplementedError('Custom loggers are not supported yet. Please use a different logger type.')
+    try:
+        logger_class = logger_type_map[logger_type]
+    except KeyError:
+        raise ValueError(f'Unknown logger type: {logger_type}. Must be one of {list(logger_type_map.keys())}')
+    return logger_class(data_path, **kwargs)
+
+class BaseLoader:
+    """
+    An abstract class representing an object that can load a model checkpoint.
+    Parameters:
+        data_path (str): A file path for storing temporary data.
+    """
+    def __init__(self, data_path: str, **kwargs):
+        self.data_path = Path(data_path)
+
+    def init(self, logger: BaseLogger, **kwargs) -> None:
+        raise NotImplementedError
+
+    def recall() -> dict:
+        raise NotImplementedError
+
+class UrlLoader(BaseLoader):
+    """
+    A loader that downloads the file from a url and loads it
+    Parameters:
+        data_path (str): A file path for storing temporary data.
+        url (str): The url to download the file from.
+    """
+    def __init__(self, data_path: str, url: str, **kwargs):
+        super().__init__(data_path, **kwargs)
+        self.url = url
+
+    def init(self, logger: BaseLogger, **kwargs) -> None:
+        # Makes sure the file exists to be downloaded
+        pass  # TODO: Actually implement that
+
+    def recall(self) -> dict:
+        # Download the file
+        save_path = self.data_path / 'loaded_checkpoint.pth'
+        urllib.request.urlretrieve(self.url, str(save_path))
+        # Load the file
+        return torch.load(str(save_path), map_location='cpu')
+        
+
+class LocalLoader(BaseLoader):
+    """
+    A loader that loads a file from a local path
+    Parameters:
+        data_path (str): A file path for storing temporary data.
+        file_path (str): The path to the file to load.
+    """
+    def __init__(self, data_path: str, file_path: str, **kwargs):
+        super().__init__(data_path, **kwargs)
+        self.file_path = Path(file_path)
+
+    def init(self, logger: BaseLogger, **kwargs) -> None:
+        # Makes sure the file exists to be loaded
+        if not self.file_path.exists():
+            raise FileNotFoundError(f'Model not found at {self.file_path}')
+
+    def recall(self) -> dict:
+        # Load the file
+        return torch.load(str(self.file_path), map_location='cpu')
+
+class WandbLoader(BaseLoader):
+    """
+    A loader that loads a model from an existing wandb run
+    """
+    def __init__(self, data_path: str, wandb_file_path: str, wandb_run_path: Optional[str] = None, **kwargs):
+        super().__init__(data_path, **kwargs)
+        self.run_path = wandb_run_path
+        self.file_path = wandb_file_path
+
+    def init(self, logger: BaseLogger, **kwargs) -> None:
+        self.wandb = import_or_print_error('wandb', '`pip install wandb` to use the wandb recall function')
+        # Make sure the file can be downloaded
+        if self.wandb.run is not None and self.run_path is None:
+            self.run_path = self.wandb.run.path
+            assert self.run_path is not None, 'wandb run was not found to load from. If not using the wandb logger must specify the `wandb_run_path`.'
+        assert self.run_path is not None, '`wandb_run_path` must be provided for the wandb loader'
+        assert self.file_path is not None, '`wandb_file_path` must be provided for the wandb loader'
+        
+        os.environ["WANDB_SILENT"] = "true"
+        pass  # TODO: Actually implement that
+
+    def recall(self) -> dict:
+        file_reference = self.wandb.restore(self.file_path, run_path=self.run_path)
+        return torch.load(file_reference.name, map_location='cpu')
+
+loader_type_map = {
+    'url': UrlLoader,
+    'local': LocalLoader,
+    'wandb': WandbLoader,
+}
+def create_loader(loader_type: str, data_path: str, **kwargs) -> BaseLoader:
+    if loader_type == 'custom':
+        raise NotImplementedError('Custom loaders are not supported yet. Please use a different loader type.')
+    try:
+        loader_class = loader_type_map[loader_type]
+    except KeyError:
+        raise ValueError(f'Unknown loader type: {loader_type}. Must be one of {list(loader_type_map.keys())}')
+    return loader_class(data_path, **kwargs)
+
+class BaseSaver:
+    def __init__(self,
+        data_path: str,
+        save_latest_to: Optional[Union[str, bool]] = 'latest.pth',
+        save_best_to: Optional[Union[str, bool]] = 'best.pth',
+        save_meta_to: str = './',
+        save_type: str = 'checkpoint',
+        **kwargs
+    ):
+        self.data_path = Path(data_path)
+        self.save_latest_to = save_latest_to
+        self.saving_latest = save_latest_to is not None and save_latest_to is not False
+        self.save_best_to = save_best_to
+        self.saving_best = save_best_to is not None and save_best_to is not False
+        self.save_meta_to = save_meta_to
+        self.save_type = save_type
+        assert save_type in ['checkpoint', 'model'], '`save_type` must be one of `checkpoint` or `model`'
+        assert self.save_meta_to is not None, '`save_meta_to` must be provided'
+        assert self.saving_latest or self.saving_best, '`save_latest_to` or `save_best_to` must be provided'
+
+    def init(self, logger: BaseLogger, **kwargs) -> None:
+        raise NotImplementedError
+
+    def save_file(self, local_path: Path, save_path: str, is_best=False, is_latest=False, **kwargs) -> None:
+        """
+        Save a general file under save_meta_to
+        """
+        raise NotImplementedError
+
+class LocalSaver(BaseSaver):
+    def __init__(self,
+        data_path: str,
+        **kwargs
+    ):
+        super().__init__(data_path, **kwargs)
+
+    def init(self, logger: BaseLogger, **kwargs) -> None:
+        # Makes sure the directory exists to be saved to
+        print(f"Saving {self.save_type} locally")
+        if not self.data_path.exists():
+            self.data_path.mkdir(parents=True)
+
+    def save_file(self, local_path: str, save_path: str, **kwargs) -> None:
+        # Copy the file to save_path
+        save_path_file_name = Path(save_path).name
+        print(f"Saving {save_path_file_name} {self.save_type} to local path {save_path}")
+        shutil.copy(local_path, save_path)
+
+class WandbSaver(BaseSaver):
+    def __init__(self, data_path: str, wandb_run_path: Optional[str] = None, **kwargs):
+        super().__init__(data_path, **kwargs)
+        self.run_path = wandb_run_path
+
+    def init(self, logger: BaseLogger, **kwargs) -> None:
+        self.wandb = import_or_print_error('wandb', '`pip install wandb` to use the wandb logger')
+        os.environ["WANDB_SILENT"] = "true"
+        # Makes sure that the user can upload tot his run
+        if self.run_path is not None:
+            entity, project, run_id = self.run_path.split("/")
+            self.run = self.wandb.init(entity=entity, project=project, id=run_id)
+        else:
+            assert self.wandb.run is not None, 'You must be using the wandb logger if you are saving to wandb and have not set `wandb_run_path`'
+            self.run = self.wandb.run
+        # TODO: Now actually check if upload is possible
+        print(f"Saving to wandb run {self.run.path}-{self.run.name}")
+
+    def save_file(self, local_path: Path, save_path: str, **kwargs) -> None:
+        # In order to log something in the correct place in wandb, we need to have the same file structure here
+        save_path_file_name = Path(save_path).name
+        print(f"Saving {save_path_file_name} {self.save_type} to wandb run {self.run.path}-{self.run.name}")
+        save_path = Path(self.data_path) / save_path
+        save_path.parent.mkdir(parents=True, exist_ok=True)
+        shutil.copy(local_path, save_path)
+        self.run.save(str(save_path), base_path = str(self.data_path), policy='now')
+
+class HuggingfaceSaver(BaseSaver):
+    def __init__(self, data_path: str, huggingface_repo: str, token_path: Optional[str] = None, **kwargs):
+        super().__init__(data_path, **kwargs)
+        self.huggingface_repo = huggingface_repo
+        self.token_path = token_path
+
+    def init(self, logger: BaseLogger, **kwargs):
+        # Makes sure this user can upload to the repo
+        self.hub = import_or_print_error('huggingface_hub', '`pip install huggingface_hub` to use the huggingface saver')
+        try:
+            identity = self.hub.whoami()  # Errors if not logged in
+            # Then we are logged in
+        except:
+            # We are not logged in. Use the token_path to set the token.
+            if not os.path.exists(self.token_path):
+                raise Exception("Not logged in to huggingface and no token_path specified. Please login with `huggingface-cli login` or if that does not work set the token_path.")
+            with open(self.token_path, "r") as f:
+                token = f.read().strip()
+            self.hub.HfApi.set_access_token(token)
+            identity = self.hub.whoami()
+        print(f"Saving to huggingface repo {self.huggingface_repo}")
+
+    def save_file(self, local_path: Path, save_path: str, **kwargs) -> None:
+        # Saving to huggingface is easy, we just need to upload the file with the correct name
+        save_path_file_name = Path(save_path).name
+        print(f"Saving {save_path_file_name} {self.save_type} to huggingface repo {self.huggingface_repo}")
+        self.hub.upload_file(
+            path_or_fileobj=str(local_path),
+            path_in_repo=str(save_path),
+            repo_id=self.huggingface_repo
+        )
+        
+saver_type_map = {
+    'local': LocalSaver,
+    'wandb': WandbSaver,
+    'huggingface': HuggingfaceSaver
+}
+def create_saver(saver_type: str, data_path: str, **kwargs) -> BaseSaver:
+    if saver_type == 'custom':
+        raise NotImplementedError('Custom savers are not supported yet. Please use a different saver type.')
+    try:
+        saver_class = saver_type_map[saver_type]
+    except KeyError:
+        raise ValueError(f'Unknown saver type: {saver_type}. Must be one of {list(saver_type_map.keys())}')
+    return saver_class(data_path, **kwargs)
+
+
+class Tracker:
+    def __init__(self, data_path: Optional[str] = DEFAULT_DATA_PATH, overwrite_data_path: bool = False, dummy_mode: bool = False):
+        self.data_path = Path(data_path)
+        if not dummy_mode:
+            if overwrite_data_path:
+                if self.data_path.exists():
+                    shutil.rmtree(self.data_path)
+                self.data_path.mkdir(parents=True)
+            else:
+                assert not self.data_path.exists(), f'Data path {self.data_path} already exists. Set overwrite_data_path to True to overwrite.'
+                if not self.data_path.exists():
+                    self.data_path.mkdir(parents=True)
+        self.logger: BaseLogger = None
+        self.loader: Optional[BaseLoader] = None
+        self.savers: List[BaseSaver]= []
+        self.dummy_mode = dummy_mode
+
+    def init(self, full_config: BaseModel, extra_config: dict):
+        assert self.logger is not None, '`logger` must be set before `init` is called'
+        if self.dummy_mode:
+            # The only thing we need is a loader
+            if self.loader is not None:
+                self.loader.init(self.logger)
+            return
+        assert len(self.savers) > 0, '`savers` must be set before `init` is called'
+        self.logger.init(full_config, extra_config)
+        if self.loader is not None:
+            self.loader.init(self.logger)
+        for saver in self.savers:
+            saver.init(self.logger)
+
+    def add_logger(self, logger: BaseLogger):
+        self.logger = logger
+
+    def add_loader(self, loader: BaseLoader):
+        self.loader = loader
+
+    def add_saver(self, saver: BaseSaver):
+        self.savers.append(saver)
+
+    def log(self, *args, **kwargs):
+        if self.dummy_mode:
+            return
+        self.logger.log(*args, **kwargs)
     
-    def save_state_dict(self, state_dict, relative_path, **kwargs):
+    def log_images(self, *args, **kwargs):
+        if self.dummy_mode:
+            return
+        self.logger.log_images(*args, **kwargs)
+
+    def log_file(self, *args, **kwargs):
+        if self.dummy_mode:
+            return
+        self.logger.log_file(*args, **kwargs)
+
+    def save_config(self, current_config_path: str, config_name = 'config.json'):
+        if self.dummy_mode:
+            return
+        # Save the config under config_name in the root folder of data_path
+        shutil.copy(current_config_path, self.data_path / config_name)
+        for saver in self.savers:
+            remote_path = Path(saver.save_meta_to) / config_name
+            saver.save_file(current_config_path, str(remote_path))
+
+    def _save_state_dict(self, trainer: Union[DiffusionPriorTrainer, DecoderTrainer], save_type: str, file_path: str, **kwargs) -> Path:
         """
-        Saves a state_dict to disk and uploads it 
+        Gets the state dict to be saved and writes it to file_path.
+        If save_type is 'checkpoint', we save the entire trainer state dict.
+        If save_type is 'model', we save only the model state dict.
         """
-        full_path = str(self.data_path / relative_path)
-        torch.save(state_dict, full_path)
-        self.wandb.save(full_path, base_path = str(self.data_path))  # Upload and keep relative to data_path
+        assert save_type in ['checkpoint', 'model']
+        if save_type == 'checkpoint':
+            trainer.save(file_path, overwrite=True, **kwargs)
+        elif save_type == 'model':
+            if isinstance(trainer, DiffusionPriorTrainer):
+                prior = trainer.ema_diffusion_prior.ema_model if trainer.use_ema else trainer.diffusion_prior
+                state_dict = trainer.unwrap_model(prior).state_dict()
+                torch.save(state_dict, file_path)
+            elif isinstance(trainer, DecoderTrainer):
+                decoder = trainer.accelerator.unwrap_model(trainer.decoder)
+                if trainer.use_ema:
+                    trainable_unets = decoder.unets
+                    decoder.unets = trainer.unets  # Swap EMA unets in
+                    state_dict = decoder.state_dict()
+                    decoder.unets = trainable_unets  # Swap back
+                else:
+                    state_dict = decoder.state_dict()
+                torch.save(state_dict, file_path)
+            else:
+                raise NotImplementedError('Saving this type of model with EMA mode enabled is not yet implemented. Actually, how did you get here?')
+        return Path(file_path)
+
+    def save(self, trainer, is_best: bool, is_latest: bool, **kwargs):
+        if self.dummy_mode:
+            return
+        if not is_best and not is_latest:
+            # Nothing to do
+            return
+        # Save the checkpoint and model to data_path
+        checkpoint_path = self.data_path / 'checkpoint.pth'
+        self._save_state_dict(trainer, 'checkpoint', checkpoint_path, **kwargs)
+        model_path = self.data_path / 'model.pth'
+        self._save_state_dict(trainer, 'model', model_path, **kwargs)
+        print("Saved cached models")
+        # Call the save methods on the savers
+        for saver in self.savers:
+            local_path = checkpoint_path if saver.save_type == 'checkpoint' else model_path
+            if saver.saving_latest and is_latest:
+                latest_checkpoint_path = saver.save_latest_to.format(**kwargs)
+                try:
+                    saver.save_file(local_path, latest_checkpoint_path, is_latest=True, **kwargs)
+                except Exception as e:
+                    self.logger.log_error(f'Error saving checkpoint: {e}', **kwargs)
+                    print(f'Error saving checkpoint: {e}')
+            if saver.saving_best and is_best:
+                best_checkpoint_path = saver.save_best_to.format(**kwargs)
+                try:
+                    saver.save_file(local_path, best_checkpoint_path, is_best=True, **kwargs)
+                except Exception as e:
+                    self.logger.log_error(f'Error saving checkpoint: {e}', **kwargs)
+                    print(f'Error saving checkpoint: {e}')
+    
+    def recall(self):
+        if self.loader is not None:
+            return self.loader.recall()
+        else:
+            raise ValueError('No loader specified')
+
+
+    

dalle2_pytorch/train_configs.py

@@ -13,8 +13,9 @@ from dalle2_pytorch.dalle2_pytorch import (
     Decoder,
     DiffusionPrior,
     DiffusionPriorNetwork,
-    XClipAdapter,
+    XClipAdapter
 )
+from dalle2_pytorch.trackers import Tracker, create_loader, create_logger, create_saver
 
 # helper functions
 
@@ -44,13 +45,66 @@ class TrainSplitConfig(BaseModel):
             raise ValueError(f'{fields.keys()} must sum to 1.0. Found: {actual_sum}')
         return fields
 
+class TrackerLogConfig(BaseModel):
+    log_type: str = 'console'
+    verbose: bool = False
+
+    class Config:
+        # Each individual log type has it's own arguments that will be passed through the config
+        extra = "allow"
+
+    def create(self, data_path: str):
+        kwargs = self.dict()
+        return create_logger(self.log_type, data_path, **kwargs)
+
+class TrackerLoadConfig(BaseModel):
+    load_from: Optional[str] = None
+
+    class Config:
+        extra = "allow"
+
+    def create(self, data_path: str):
+        kwargs = self.dict()
+        if self.load_from is None:
+            return None
+        return create_loader(self.load_from, data_path, **kwargs)
+
+class TrackerSaveConfig(BaseModel):
+    save_to: str = 'local'
+    save_all: bool = False
+    save_latest: bool = True
+    save_best: bool = True
+
+    class Config:
+        extra = "allow"
+
+    def create(self, data_path: str):
+        kwargs = self.dict()
+        return create_saver(self.save_to, data_path, **kwargs)
+
 class TrackerConfig(BaseModel):
-    tracker_type: str = 'console'           # Decoder currently supports console and wandb
-    data_path: str = './models'             # The path where files will be saved locally
-    init_config: Dict[str, Any] = None
-    wandb_entity: str = ''                  # Only needs to be set if tracker_type is wandb
-    wandb_project: str = ''
-    verbose: bool = False                   # Whether to print console logging for non-console trackers
+    data_path: str = '.tracker_data'
+    overwrite_data_path: bool = False
+    log: TrackerLogConfig
+    load: Optional[TrackerLoadConfig]
+    save: Union[List[TrackerSaveConfig], TrackerSaveConfig]
+
+    def create(self, full_config: BaseModel, extra_config: dict, dummy_mode: bool = False) -> Tracker:
+        tracker = Tracker(self.data_path, dummy_mode=dummy_mode, overwrite_data_path=self.overwrite_data_path)
+        # Add the logger
+        tracker.add_logger(self.log.create(self.data_path))
+        # Add the loader
+        if self.load is not None:
+            tracker.add_loader(self.load.create(self.data_path))
+        # Add the saver or savers
+        if isinstance(self.save, list):
+            for save_config in self.save:
+                tracker.add_saver(save_config.create(self.data_path))
+        else:
+            tracker.add_saver(self.save.create(self.data_path))
+        # Initialize all the components and verify that all data is valid
+        tracker.init(full_config, extra_config)
+        return tracker
 
 # diffusion prior pydantic classes
 
@@ -158,8 +212,11 @@ class UnetConfig(BaseModel):
     dim: int
     dim_mults: ListOrTuple(int)
     image_embed_dim: int = None
+    text_embed_dim: int = None
+    cond_on_text_encodings: bool = None
     cond_dim: int = None
     channels: int = 3
+    self_attn: ListOrTuple(int)
     attn_dim_head: int = 32
     attn_heads: int = 16
 
@@ -170,19 +227,27 @@ class DecoderConfig(BaseModel):
     unets: ListOrTuple(UnetConfig)
     image_size: int = None
     image_sizes: ListOrTuple(int) = None
+    clip: Optional[AdapterConfig]   # The clip model to use if embeddings are not provided
     channels: int = 3
     timesteps: int = 1000
     loss_type: str = 'l2'
-    beta_schedule: str = 'cosine'
+    beta_schedule: ListOrTuple(str) = 'cosine'
     learned_variance: bool = True
     image_cond_drop_prob: float = 0.1
     text_cond_drop_prob: float = 0.5
 
     def create(self):
         decoder_kwargs = self.dict()
+
         unet_configs = decoder_kwargs.pop('unets')
         unets = [Unet(**config) for config in unet_configs]
-        return Decoder(unets, **decoder_kwargs)
+
+        has_clip = exists(decoder_kwargs.pop('clip'))
+        clip = None
+        if has_clip:
+            clip = self.clip.create()
+
+        return Decoder(unets, clip=clip, **decoder_kwargs)
 
     @validator('image_sizes')
     def check_image_sizes(cls, image_sizes, values):
@@ -194,8 +259,9 @@ class DecoderConfig(BaseModel):
         extra = "allow"
 
 class DecoderDataConfig(BaseModel):
-    webdataset_base_url: str     # path to a webdataset with jpg images
-    embeddings_url: str          # path to .npy files with embeddings
+    webdataset_base_url: str               # path to a webdataset with jpg images
+    img_embeddings_url: Optional[str]      # path to .npy files with embeddings
+    text_embeddings_url: Optional[str]     # path to .npy files with embeddings
     num_workers: int = 4
     batch_size: int = 64
     start_shard: int = 0
@@ -227,6 +293,7 @@ class DecoderTrainConfig(BaseModel):
     epochs: int = 20
     lr: SingularOrIterable(float) = 1e-4
     wd: SingularOrIterable(float) = 0.01
+    find_unused_parameters: bool = True
     max_grad_norm: SingularOrIterable(float) = 0.5
     save_every_n_samples: int = 100000
     n_sample_images: int = 6                       # The number of example images to produce when sampling the train and test dataset
@@ -236,9 +303,6 @@ class DecoderTrainConfig(BaseModel):
     use_ema: bool = True
     ema_beta: float = 0.999
     amp: bool = False
-    save_all: bool = False                         # Whether to preserve all checkpoints
-    save_latest: bool = True                       # Whether to always save the latest checkpoint
-    save_best: bool = True                         # Whether to save the best checkpoint
     unet_training_mask: ListOrTuple(bool) = None   # If None, use all unets
 
 class DecoderEvaluateConfig(BaseModel):
@@ -260,10 +324,39 @@ class TrainDecoderConfig(BaseModel):
     train: DecoderTrainConfig
     evaluate: DecoderEvaluateConfig
     tracker: TrackerConfig
-    load: DecoderLoadConfig
+    seed: int = 0
 
     @classmethod
     def from_json_path(cls, json_path):
         with open(json_path) as f:
             config = json.load(f)
         return cls(**config)
+    
+    @root_validator
+    def check_has_embeddings(cls, values):
+        # Makes sure that enough information is provided to get the embeddings specified for training
+        data_config, decoder_config = values.get('data'), values.get('decoder')
+
+        if not exists(data_config) or not exists(decoder_config):
+            # Then something else errored and we should just pass through
+            return values
+
+        using_text_embeddings = any([unet.cond_on_text_encodings for unet in decoder_config.unets])
+        using_clip = exists(decoder_config.clip)
+        img_emb_url = data_config.img_embeddings_url
+        text_emb_url = data_config.text_embeddings_url
+
+        if using_text_embeddings:
+            # Then we need some way to get the embeddings
+            assert using_clip or exists(text_emb_url), 'If text conditioning, either clip or text_embeddings_url must be provided'
+
+        if using_clip:
+            if using_text_embeddings:
+                assert not exists(text_emb_url) or not exists(img_emb_url), 'Loaded clip, but also provided text_embeddings_url and img_embeddings_url. This is redundant. Remove the clip model or the text embeddings'
+            else:
+                assert not exists(img_emb_url), 'Loaded clip, but also provided img_embeddings_url. This is redundant. Remove the clip model or the embeddings'
+
+        if text_emb_url:
+            assert using_text_embeddings, "Text embeddings are being loaded, but text embeddings are not being conditioned on. This will slow down the dataloader for no reason."
+
+        return values

dalle2_pytorch/trainer.py

@@ -11,6 +11,12 @@ from torch.cuda.amp import autocast, GradScaler
 
 from dalle2_pytorch.dalle2_pytorch import Decoder, DiffusionPrior
 from dalle2_pytorch.optimizer import get_optimizer
+from dalle2_pytorch.version import __version__
+from packaging import version
+
+from ema_pytorch import EMA
+
+from accelerate import Accelerator
 
 import numpy as np
 
@@ -20,7 +26,9 @@ def exists(val):
     return val is not None
 
 def default(val, d):
-    return val if exists(val) else d
+    if exists(val):
+        return val
+    return d() if callable(d) else d
 
 def cast_tuple(val, length = 1):
     return val if isinstance(val, tuple) else ((val,) * length)
@@ -56,10 +64,6 @@ def num_to_groups(num, divisor):
         arr.append(remainder)
     return arr
 
-def get_pkg_version():
-    from pkg_resources import get_distribution
-    return get_distribution('dalle2_pytorch').version
-
 # decorators
 
 def cast_torch_tensor(fn):
@@ -133,105 +137,6 @@ def split_args_and_kwargs(*args, split_size = None, **kwargs):
         chunk_size_frac = chunk_size / batch_size
         yield chunk_size_frac, (chunked_args, chunked_kwargs)
 
-# saving and loading functions
-
-# for diffusion prior
-
-def load_diffusion_model(dprior_path, device):
-    dprior_path = Path(dprior_path)
-    assert dprior_path.exists(), 'Dprior model file does not exist'
-    loaded_obj = torch.load(str(dprior_path), map_location='cpu')
-
-    # Get hyperparameters of loaded model
-    dpn_config = loaded_obj['hparams']['diffusion_prior_network']
-    dp_config = loaded_obj['hparams']['diffusion_prior']
-    image_embed_dim = loaded_obj['image_embed_dim']['image_embed_dim']
-
-    # Create DiffusionPriorNetwork and DiffusionPrior with loaded hyperparameters
-
-    # DiffusionPriorNetwork
-    prior_network = DiffusionPriorNetwork( dim = image_embed_dim, **dpn_config).to(device)
-
-    # DiffusionPrior with text embeddings and image embeddings pre-computed
-    diffusion_prior = DiffusionPrior(net = prior_network, **dp_config, image_embed_dim = image_embed_dim).to(device)
-
-    # Load state dict from saved model
-    diffusion_prior.load_state_dict(loaded_obj['model'])
-
-    return diffusion_prior, loaded_obj
-
-def save_diffusion_model(save_path, model, optimizer, scaler, config, image_embed_dim):
-    # Saving State Dict
-    print_ribbon('Saving checkpoint')
-
-    state_dict = dict(model=model.state_dict(),
-                      optimizer=optimizer.state_dict(),
-                      scaler=scaler.state_dict(),
-                      hparams = config,
-                      image_embed_dim = {"image_embed_dim":image_embed_dim})
-    torch.save(state_dict, save_path+'/'+str(time.time())+'_saved_model.pth')
-
-# exponential moving average wrapper
-
-class EMA(nn.Module):
-    def __init__(
-        self,
-        model,
-        beta = 0.9999,
-        update_after_step = 1000,
-        update_every = 10,
-    ):
-        super().__init__()
-        self.beta = beta
-        self.online_model = model
-        self.ema_model = copy.deepcopy(model)
-
-        self.update_every = update_every
-        self.update_after_step = update_after_step  // update_every # only start EMA after this step number, starting at 0
-
-        self.register_buffer('initted', torch.Tensor([False]))
-        self.register_buffer('step', torch.tensor([0]))
-
-    def restore_ema_model_device(self):
-        device = self.initted.device
-        self.ema_model.to(device)
-
-    def copy_params_from_model_to_ema(self):
-        self.ema_model.state_dict(self.online_model.state_dict())
-
-    def update(self):
-        self.step += 1
-
-        if (self.step % self.update_every) != 0:
-            return
-
-        if self.step <= self.update_after_step:
-            self.copy_params_from_model_to_ema()
-            return
-
-        if not self.initted:
-            self.copy_params_from_model_to_ema()
-            self.initted.data.copy_(torch.Tensor([True]))
-
-        self.update_moving_average(self.ema_model, self.online_model)
-
-    def update_moving_average(self, ma_model, current_model):
-        def calculate_ema(beta, old, new):
-            if not exists(old):
-                return new
-            return old * beta + (1 - beta) * new
-
-        for current_params, ma_params in zip(current_model.parameters(), ma_model.parameters()):
-            old_weight, up_weight = ma_params.data, current_params.data
-            ma_params.data = calculate_ema(self.beta, old_weight, up_weight)
-
-        for current_buffer, ma_buffer in zip(current_model.buffers(), ma_model.buffers()):
-            new_buffer_value = calculate_ema(self.beta, ma_buffer, current_buffer)
-            ma_buffer.copy_(new_buffer_value)
-
-    def __call__(self, *args, **kwargs):
-        return self.ema_model(*args, **kwargs)
-
 # diffusion prior trainer
 
 def prior_sample_in_chunks(fn):
@@ -255,88 +160,189 @@ class DiffusionPriorTrainer(nn.Module):
         max_grad_norm = None,
         amp = False,
         group_wd_params = True,
+        device = None,
+        accelerator = None,
         **kwargs
     ):
         super().__init__()
         assert isinstance(diffusion_prior, DiffusionPrior)
+        assert not exists(accelerator) or isinstance(accelerator, Accelerator)
+        assert exists(accelerator) or exists(device), "You must supply some method of obtaining a device."
         ema_kwargs, kwargs = groupby_prefix_and_trim('ema_', kwargs)
 
+        # assign some helpful member vars
+        self.accelerator = accelerator
+        self.device = accelerator.device if exists(accelerator) else device
+        self.text_conditioned = diffusion_prior.condition_on_text_encodings
+
+        # save model
+
         self.diffusion_prior = diffusion_prior
 
-        # exponential moving average
-
-        self.use_ema = use_ema
-        if self.use_ema:
-            self.ema_diffusion_prior = EMA(diffusion_prior, **ema_kwargs)
-
         # optimizer and mixed precision stuff
 
         self.amp = amp
 
         self.scaler = GradScaler(enabled = amp)
 
+        self.optim_kwargs = dict(lr=lr, wd=wd, eps=eps, group_wd_params=group_wd_params)
+
         self.optimizer = get_optimizer(
-            diffusion_prior.parameters(),
-            lr = lr,
-            wd = wd,
-            eps = eps,
-            group_wd_params = group_wd_params,
+            self.diffusion_prior.parameters(),
+            **self.optim_kwargs,
             **kwargs
         )
 
+        # distribute the model if using HFA
+        if exists(self.accelerator):
+            self.diffusion_prior, self.optimizer = self.accelerator.prepare(self.diffusion_prior, self.optimizer)
+
+        # exponential moving average stuff
+
+        self.use_ema = use_ema
+
+        if self.use_ema:
+            self.ema_diffusion_prior = EMA(self.unwrap_model(self.diffusion_prior), **ema_kwargs)
+
         # gradient clipping if needed
 
         self.max_grad_norm = max_grad_norm
 
+        # track steps internally
+
         self.register_buffer('step', torch.tensor([0]))
 
+    # accelerator wrappers
+
+    def print(self, msg):
+        if exists(self.accelerator):
+            self.accelerator.print(msg)
+        else:
+            print(msg)
+
+    def unwrap_model(self, model):
+        if exists(self.accelerator):
+            return self.accelerator.unwrap_model(model)
+        else:
+            return model
+
+    def wait_for_everyone(self):
+        if exists(self.accelerator):
+            self.accelerator.wait_for_everyone()
+
+    def is_main_process(self):
+        if exists(self.accelerator):
+            return self.accelerator.is_main_process
+        else:
+            return True
+
+    def clip_grad_norm_(self, *args):
+        if exists(self.accelerator):
+            return self.accelerator.clip_grad_norm_(*args)
+        else:
+            return torch.nn.utils.clip_grad_norm_(*args)
+
+    def backprop(self, x):
+        if exists(self.accelerator):
+            self.accelerator.backward(x)
+        else:
+            try:
+                x.backward()
+            except Exception as e:
+                self.print(f"Caught error in backprop call: {e}")
+
+    # utility
+
     def save(self, path, overwrite = True, **kwargs):
-        path = Path(path)
-        assert not (path.exists() and not overwrite)
-        path.parent.mkdir(parents = True, exist_ok = True)
+        # ensure we sync gradients before continuing
+        self.wait_for_everyone()
 
-        save_obj = dict(
-            scaler = self.scaler.state_dict(),
-            optimizer = self.optimizer.state_dict(),
-            model = self.diffusion_prior.state_dict(),
-            version = get_pkg_version(),
-            step = self.step.item(),
-            **kwargs
-        )
+        # only save on the main process
+        if self.is_main_process():
+            self.print(f"Saving checkpoint at step: {self.step.item()}")
+            path = Path(path)
+            assert not (path.exists() and not overwrite)
+            path.parent.mkdir(parents = True, exist_ok = True)
 
-        if self.use_ema:
-            save_obj = {**save_obj, 'ema': self.ema_diffusion_prior.state_dict()}
+            save_obj = dict(
+                scaler = self.scaler.state_dict(),
+                optimizer = self.optimizer.state_dict(),
+                model = self.unwrap_model(self.diffusion_prior).state_dict(), # unwrap the model from distribution if applicable
+                version = version.parse(__version__),
+                step = self.step.item(),
+                **kwargs
+            )
 
-        torch.save(save_obj, str(path))
+            if self.use_ema:
+                save_obj = {
+                    **save_obj,
+                    'ema': self.ema_diffusion_prior.state_dict(),
+                    'ema_model': self.ema_diffusion_prior.ema_model.state_dict() # save the ema model specifically for easy ema-only reload
+                }
 
-    def load(self, path, only_model = False, strict = True):
+            torch.save(save_obj, str(path))
+
+    def load(self, path, overwrite_lr = True, strict = True):
+        """
+        Load a checkpoint of a diffusion prior trainer.
+
+        Will load the entire trainer, including the optimizer and EMA.
+
+        Params:
+            - path (str): a path to the DiffusionPriorTrainer checkpoint file
+            - overwrite_lr (bool): wether or not to overwrite the stored LR with the LR specified in the new trainer
+            - strict (bool): kwarg for `torch.nn.Module.load_state_dict`, will force an exact checkpoint match
+
+        Returns:
+            loaded_obj (dict): The loaded checkpoint dictionary
+        """
+
+        # all processes need to load checkpoint. no restriction here
         path = Path(path)
         assert path.exists()
 
-        loaded_obj = torch.load(str(path))
+        loaded_obj = torch.load(str(path), map_location=self.device)
 
-        if get_pkg_version() != loaded_obj['version']:
-            print(f'loading saved diffusion prior at version {loaded_obj["version"]} but current package version is at {get_pkg_version()}')
+        if version.parse(__version__) != loaded_obj['version']:
+            print(f'loading saved diffusion prior at version {loaded_obj["version"]} but current package version is at {__version__}')
 
-        self.diffusion_prior.load_state_dict(loaded_obj['model'], strict = strict)
+        # unwrap the model when loading from checkpoint
+        self.unwrap_model(self.diffusion_prior).load_state_dict(loaded_obj['model'], strict = strict)
         self.step.copy_(torch.ones_like(self.step) * loaded_obj['step'])
 
-        if only_model:
-            return loaded_obj
-
         self.scaler.load_state_dict(loaded_obj['scaler'])
         self.optimizer.load_state_dict(loaded_obj['optimizer'])
 
+        if overwrite_lr:
+            new_lr = self.optim_kwargs["lr"]
+
+            self.print(f"Overriding LR to be {new_lr}")
+
+            for group in self.optimizer.param_groups:
+                group["lr"] = new_lr
+
         if self.use_ema:
             assert 'ema' in loaded_obj
             self.ema_diffusion_prior.load_state_dict(loaded_obj['ema'], strict = strict)
+            # below not be necessary, but I had a suspicion that this wasn't being loaded correctly
+            self.ema_diffusion_prior.ema_model.load_state_dict(loaded_obj["ema_model"])
+
+        # sync and inform
+        self.wait_for_everyone()
+        self.print(f"Loaded model")
 
         return loaded_obj
 
+    # model functionality
+
     def update(self):
+        # only continue with updates until all ranks finish
+        self.wait_for_everyone()
+
         if exists(self.max_grad_norm):
             self.scaler.unscale_(self.optimizer)
-            nn.utils.clip_grad_norm_(self.diffusion_prior.parameters(), self.max_grad_norm)
+            # utilize HFA clipping where applicable
+            self.clip_grad_norm_(self.diffusion_prior.parameters(), self.max_grad_norm)
 
         self.scaler.step(self.optimizer)
         self.scaler.update()
@@ -351,17 +357,26 @@ class DiffusionPriorTrainer(nn.Module):
     @cast_torch_tensor
     @prior_sample_in_chunks
     def p_sample_loop(self, *args, **kwargs):
-        return self.ema_diffusion_prior.ema_model.p_sample_loop(*args, **kwargs)
+        model = self.ema_diffusion_prior.ema_model if self.use_ema else self.diffusion_prior
+        return model.p_sample_loop(*args, **kwargs)
 
     @torch.no_grad()
     @cast_torch_tensor
     @prior_sample_in_chunks
     def sample(self, *args, **kwargs):
-        return self.ema_diffusion_prior.ema_model.sample(*args, **kwargs)
+        model = self.ema_diffusion_prior.ema_model if self.use_ema else self.diffusion_prior
+        return model.sample(*args, **kwargs)
 
     @torch.no_grad()
     def sample_batch_size(self, *args, **kwargs):
-        return self.ema_diffusion_prior.ema_model.sample_batch_size(*args, **kwargs)
+        model = self.ema_diffusion_prior.ema_model if self.use_ema else self.diffusion_prior
+        return model.sample_batch_size(*args, **kwargs)
+
+    @torch.no_grad()
+    @cast_torch_tensor
+    @prior_sample_in_chunks
+    def embed_text(self, *args, **kwargs):
+        return self.unwrap_model(self.diffusion_prior).clip.embed_text(*args, **kwargs)
 
     @cast_torch_tensor
     def forward(
@@ -379,8 +394,10 @@ class DiffusionPriorTrainer(nn.Module):
 
             total_loss += loss.item()
 
+            # backprop with accelerate if applicable
+
             if self.training:
-                self.scaler.scale(loss).backward()
+                self.backprop(self.scaler.scale(loss))
 
         return total_loss
 
@@ -406,6 +423,7 @@ class DecoderTrainer(nn.Module):
     def __init__(
         self,
         decoder,
+        accelerator = None,
         use_ema = True,
         lr = 1e-4,
         wd = 1e-2,
@@ -419,8 +437,9 @@ class DecoderTrainer(nn.Module):
         assert isinstance(decoder, Decoder)
         ema_kwargs, kwargs = groupby_prefix_and_trim('ema_', kwargs)
 
-        self.decoder = decoder
-        self.num_unets = len(self.decoder.unets)
+        self.accelerator = default(accelerator, Accelerator)
+
+        self.num_unets = len(decoder.unets)
 
         self.use_ema = use_ema
         self.ema_unets = nn.ModuleList([])
@@ -432,7 +451,11 @@ class DecoderTrainer(nn.Module):
 
         lr, wd, eps = map(partial(cast_tuple, length = self.num_unets), (lr, wd, eps))
 
-        for ind, (unet, unet_lr, unet_wd, unet_eps) in enumerate(zip(self.decoder.unets, lr, wd, eps)):
+        assert all([unet_lr < 1e-3 for unet_lr in lr]), 'your learning rate is too high, recommend sticking with 1e-4, at most 5e-4'
+
+        optimizers = []
+
+        for unet, unet_lr, unet_wd, unet_eps in zip(decoder.unets, lr, wd, eps):
             optimizer = get_optimizer(
                 unet.parameters(),
                 lr = unet_lr,
@@ -442,101 +465,92 @@ class DecoderTrainer(nn.Module):
                 **kwargs
             )
 
-            setattr(self, f'optim{ind}', optimizer) # cannot use pytorch ModuleList for some reason with optimizers
+            optimizers.append(optimizer)
 
             if self.use_ema:
                 self.ema_unets.append(EMA(unet, **ema_kwargs))
 
-            scaler = GradScaler(enabled = amp)
-            setattr(self, f'scaler{ind}', scaler)
-
         # gradient clipping if needed
 
         self.max_grad_norm = max_grad_norm
 
         self.register_buffer('step', torch.tensor([0.]))
 
+        decoder, *optimizers = list(self.accelerator.prepare(decoder, *optimizers))
+
+        self.decoder = decoder
+
+        for opt_ind, optimizer in zip(range(len(optimizers)), optimizers):
+            setattr(self, f'optim{opt_ind}', optimizer)
+
     def save(self, path, overwrite = True, **kwargs):
         path = Path(path)
         assert not (path.exists() and not overwrite)
         path.parent.mkdir(parents = True, exist_ok = True)
 
         save_obj = dict(
-            model = self.decoder.state_dict(),
-            version = get_pkg_version(),
+            model = self.accelerator.unwrap_model(self.decoder).state_dict(),
+            version = __version__,
             step = self.step.item(),
             **kwargs
         )
 
         for ind in range(0, self.num_unets):
-            scaler_key = f'scaler{ind}'
-            optimizer_key = f'scaler{ind}'
-            scaler = getattr(self, scaler_key)
+            optimizer_key = f'optim{ind}'
             optimizer = getattr(self, optimizer_key)
-            save_obj = {**save_obj, scaler_key: scaler.state_dict(), optimizer_key: optimizer.state_dict()}
+            save_obj = {**save_obj, optimizer_key: self.accelerator.unwrap_model(optimizer).state_dict()}
 
         if self.use_ema:
             save_obj = {**save_obj, 'ema': self.ema_unets.state_dict()}
 
-        torch.save(save_obj, str(path))
+        self.accelerator.save(save_obj, str(path))
 
-    def load(self, path, only_model = False, strict = True):
-        path = Path(path)
-        assert path.exists()
+    def load_state_dict(self, loaded_obj, only_model = False, strict = True):
+        if version.parse(__version__) != version.parse(loaded_obj['version']):
+            self.accelerator.print(f'loading saved decoder at version {loaded_obj["version"]}, but current package version is {__version__}')
 
-        loaded_obj = torch.load(str(path))
-
-        if get_pkg_version() != loaded_obj['version']:
-            print(f'loading saved decoder at version {loaded_obj["version"]}, but current package version is {get_pkg_version()}')
-
-        self.decoder.load_state_dict(loaded_obj['model'], strict = strict)
+        self.accelerator.unwrap_model(self.decoder).load_state_dict(loaded_obj['model'], strict = strict)
         self.step.copy_(torch.ones_like(self.step) * loaded_obj['step'])
 
         if only_model:
             return loaded_obj
 
         for ind in range(0, self.num_unets):
-            scaler_key = f'scaler{ind}'
-            optimizer_key = f'scaler{ind}'
-            scaler = getattr(self, scaler_key)
+            optimizer_key = f'optim{ind}'
             optimizer = getattr(self, optimizer_key)
 
-            scaler.load_state_dict(loaded_obj[scaler_key])
-            optimizer.load_state_dict(loaded_obj[optimizer_key])
+            self.accelerator.unwrap_model(optimizer).load_state_dict(loaded_obj[optimizer_key])
 
         if self.use_ema:
             assert 'ema' in loaded_obj
             self.ema_unets.load_state_dict(loaded_obj['ema'], strict = strict)
 
+    def load(self, path, only_model = False, strict = True):
+        path = Path(path)
+        assert path.exists()
+
+        loaded_obj = torch.load(str(path), map_location = 'cpu')
+
+        self.load_state_dict(loaded_obj, only_model = only_model, strict = strict)
+
         return loaded_obj
 
     @property
     def unets(self):
         return nn.ModuleList([ema.ema_model for ema in self.ema_unets])
 
-    def scale(self, loss, *, unet_number):
-        assert 1 <= unet_number <= self.num_unets
-        index = unet_number - 1
-        scaler = getattr(self, f'scaler{index}')
-        return scaler.scale(loss)
-
     def update(self, unet_number = None):
         if self.num_unets == 1:
             unet_number = default(unet_number, 1)
 
         assert exists(unet_number) and 1 <= unet_number <= self.num_unets
         index = unet_number - 1
-        unet = self.decoder.unets[index]
 
         optimizer = getattr(self, f'optim{index}')
-        scaler = getattr(self, f'scaler{index}')
 
         if exists(self.max_grad_norm):
-            scaler.unscale_(optimizer)
-            nn.utils.clip_grad_norm_(unet.parameters(), self.max_grad_norm)
-
-        scaler.step(optimizer)
-        scaler.update()
+            self.accelerator.clip_grad_norm_(self.decoder.parameters(), self.max_grad_norm)  # Automatically unscales gradients
+        optimizer.step()
         optimizer.zero_grad()
 
         if self.use_ema:
@@ -549,15 +563,17 @@ class DecoderTrainer(nn.Module):
     @cast_torch_tensor
     @decoder_sample_in_chunks
     def sample(self, *args, **kwargs):
+        distributed = self.accelerator.num_processes > 1
+        base_decoder = self.accelerator.unwrap_model(self.decoder)
         if kwargs.pop('use_non_ema', False) or not self.use_ema:
-            return self.decoder.sample(*args, **kwargs)
+            return base_decoder.sample(*args, **kwargs, distributed = distributed)
 
-        trainable_unets = self.decoder.unets
-        self.decoder.unets = self.unets                  # swap in exponential moving averaged unets for sampling
+        trainable_unets = self.accelerator.unwrap_model(self.decoder).unets
+        base_decoder.unets = self.unets                  # swap in exponential moving averaged unets for sampling
 
-        output = self.decoder.sample(*args, **kwargs)
+        output = base_decoder.sample(*args, **kwargs, distributed = distributed)
 
-        self.decoder.unets = trainable_unets             # restore original training unets
+        base_decoder.unets = trainable_unets             # restore original training unets
 
         # cast the ema_model unets back to original device
         for ema in self.ema_unets:
@@ -565,6 +581,18 @@ class DecoderTrainer(nn.Module):
 
         return output
 
+    @torch.no_grad()
+    @cast_torch_tensor
+    @prior_sample_in_chunks
+    def embed_text(self, *args, **kwargs):
+        return self.accelerator.unwrap_model(self.decoder).clip.embed_text(*args, **kwargs)
+
+    @torch.no_grad()
+    @cast_torch_tensor
+    @prior_sample_in_chunks
+    def embed_image(self, *args, **kwargs):
+        return self.accelerator.unwrap_model(self.decoder).clip.embed_image(*args, **kwargs)
+
     @cast_torch_tensor
     def forward(
         self,
@@ -579,13 +607,14 @@ class DecoderTrainer(nn.Module):
         total_loss = 0.
 
         for chunk_size_frac, (chunked_args, chunked_kwargs) in split_args_and_kwargs(*args, split_size = max_batch_size, **kwargs):
-            with autocast(enabled = self.amp):
+            # with autocast(enabled = self.amp):
+            with self.accelerator.autocast():
                 loss = self.decoder(*chunked_args, unet_number = unet_number, **chunked_kwargs)
                 loss = loss * chunk_size_frac
 
             total_loss += loss.item()
 
             if self.training:
-                self.scale(loss, unet_number = unet_number).backward()
+                self.accelerator.backward(loss)
 
         return total_loss

dalle2_pytorch/utils.py

@@ -1,4 +1,10 @@
 import time
+import importlib
+
+# helper functions
+
+def exists(val):
+    return val is not None
 
 # time helpers
 
@@ -17,3 +23,13 @@ class Timer:
 def print_ribbon(s, symbol = '=', repeat = 40):
     flank = symbol * repeat
     return f'{flank} {s} {flank}'
+
+# import helpers
+
+def import_or_print_error(pkg_name, err_str = None):
+    try:
+        return importlib.import_module(pkg_name)
+    except ModuleNotFoundError as e:
+        if exists(err_str):
+            print(err_str)
+        exit()

dalle2_pytorch/version.py

@@ -0,0 +1 @@
+__version__ = '0.16.1'

dalle2_pytorch/vqgan_vae.py

@@ -68,8 +68,8 @@ def group_dict_by_key(cond, d):
         return_val[ind][key] = d[key]
     return (*return_val,)
 
-def string_begins_with(prefix, str):
-    return str.startswith(prefix)
+def string_begins_with(prefix, string_input):
+    return string_input.startswith(prefix)
 
 def group_by_key_prefix(prefix, d):
     return group_dict_by_key(partial(string_begins_with, prefix), d)

dalle2_pytorch/vqgan_vae_trainer.py

@@ -16,10 +16,11 @@ from torchvision.utils import make_grid, save_image
 
 from einops import rearrange
 
-from dalle2_pytorch.train import EMA
 from dalle2_pytorch.vqgan_vae import VQGanVAE
 from dalle2_pytorch.optimizer import get_optimizer
 
+from ema_pytorch import EMA
+
 # helpers
 
 def exists(val):
@@ -97,7 +98,7 @@ class VQGanVAETrainer(nn.Module):
         valid_frac = 0.05,
         random_split_seed = 42,
         ema_beta = 0.995,
-        ema_update_after_step = 2000,
+        ema_update_after_step = 500,
         ema_update_every = 10,
         apply_grad_penalty_every = 4,
         amp = False

setup.py

@@ -1,4 +1,5 @@
 from setuptools import setup, find_packages
+exec(open('dalle2_pytorch/version.py').read())
 
 setup(
   name = 'dalle2-pytorch',
@@ -10,7 +11,7 @@ setup(
       'dream = dalle2_pytorch.cli:dream'
     ],
   },
-  version = '0.5.7',
+  version = __version__,
   license='MIT',
   description = 'DALL-E 2',
   author = 'Phil Wang',
@@ -23,14 +24,17 @@ setup(
     'text to image'
   ],
   install_requires=[
+    'accelerate',
     'click',
     'clip-anytorch',
     'coca-pytorch>=0.0.5',
+    'ema-pytorch>=0.0.7',
     'einops>=0.4',
     'einops-exts>=0.0.3',
     'embedding-reader',
     'kornia>=0.5.4',
     'numpy',
+    'packaging',
     'pillow',
     'pydantic',
     'resize-right>=0.0.2',
@@ -40,7 +44,6 @@ setup(
     'tqdm',
     'vector-quantize-pytorch',
     'x-clip>=0.4.4',
-    'youtokentome',
     'webdataset>=0.2.5',
     'fsspec>=2022.1.0',
     'torchmetrics[image]>=0.8.0'

train_decoder.py

@@ -1,9 +1,13 @@
-from dalle2_pytorch import Unet, Decoder
+from pathlib import Path
+from typing import List
+
 from dalle2_pytorch.trainer import DecoderTrainer
 from dalle2_pytorch.dataloaders import create_image_embedding_dataloader
-from dalle2_pytorch.trackers import WandbTracker, ConsoleTracker
-from dalle2_pytorch.train_configs import TrainDecoderConfig
+from dalle2_pytorch.trackers import Tracker
+from dalle2_pytorch.train_configs import DecoderConfig, TrainDecoderConfig
 from dalle2_pytorch.utils import Timer, print_ribbon
+from dalle2_pytorch.dalle2_pytorch import Decoder, resize_image_to
+from clip import tokenize
 
 import torchvision
 import torch
@@ -11,6 +15,8 @@ from torchmetrics.image.fid import FrechetInceptionDistance
 from torchmetrics.image.inception import InceptionScore
 from torchmetrics.image.kid import KernelInceptionDistance
 from torchmetrics.image.lpip import LearnedPerceptualImagePatchSimilarity
+from accelerate import Accelerator, DistributedDataParallelKwargs
+from accelerate.utils import dataclasses as accelerate_dataclasses
 import webdataset as wds
 import click
 
@@ -29,7 +35,8 @@ def exists(val):
 def create_dataloaders(
     available_shards,
     webdataset_base_url,
-    embeddings_url,
+    img_embeddings_url=None,
+    text_embeddings_url=None,
     shard_width=6,
     num_workers=4,
     batch_size=32,
@@ -41,6 +48,7 @@ def create_dataloaders(
     train_prop = 0.75,
     val_prop = 0.15,
     test_prop = 0.10,
+    seed = 0,
     **kwargs
 ):
     """
@@ -51,21 +59,22 @@ def create_dataloaders(
     num_test = round(test_prop*len(available_shards))
     num_val = len(available_shards) - num_train - num_test
     assert num_train + num_test + num_val == len(available_shards), f"{num_train} + {num_test} + {num_val} = {num_train + num_test + num_val} != {len(available_shards)}"
-    train_split, test_split, val_split = torch.utils.data.random_split(available_shards, [num_train, num_test, num_val], generator=torch.Generator().manual_seed(0))
+    train_split, test_split, val_split = torch.utils.data.random_split(available_shards, [num_train, num_test, num_val], generator=torch.Generator().manual_seed(seed))
 
     # The shard number in the webdataset file names has a fixed width. We zero pad the shard numbers so they correspond to a filename.
     train_urls = [webdataset_base_url.format(str(shard).zfill(shard_width)) for shard in train_split]
     test_urls = [webdataset_base_url.format(str(shard).zfill(shard_width)) for shard in test_split]
     val_urls = [webdataset_base_url.format(str(shard).zfill(shard_width)) for shard in val_split]
     
-    create_dataloader = lambda tar_urls, shuffle=False, resample=False, with_text=False, for_sampling=False: create_image_embedding_dataloader(
+    create_dataloader = lambda tar_urls, shuffle=False, resample=False, for_sampling=False: create_image_embedding_dataloader(
         tar_url=tar_urls,
         num_workers=num_workers,
         batch_size=batch_size if not for_sampling else n_sample_images,
-        embeddings_url=embeddings_url,
+        img_embeddings_url=img_embeddings_url,
+        text_embeddings_url=text_embeddings_url,
         index_width=index_width,
         shuffle_num = None,
-        extra_keys= ["txt"] if with_text else [],
+        extra_keys= ["txt"],
         shuffle_shards = shuffle,
         resample_shards = resample, 
         img_preproc=img_preproc,
@@ -74,8 +83,8 @@ def create_dataloaders(
 
     train_dataloader = create_dataloader(train_urls, shuffle=shuffle_train, resample=resample_train)
     train_sampling_dataloader = create_dataloader(train_urls, shuffle=False, for_sampling=True)
-    val_dataloader = create_dataloader(val_urls, shuffle=False, with_text=True)
-    test_dataloader = create_dataloader(test_urls, shuffle=False, with_text=True)
+    val_dataloader = create_dataloader(val_urls, shuffle=False)
+    test_dataloader = create_dataloader(test_urls, shuffle=False)
     test_sampling_dataloader = create_dataloader(test_urls, shuffle=False, for_sampling=True)
     return {
         "train": train_dataloader,
@@ -99,74 +108,111 @@ def get_example_data(dataloader, device, n=5):
     Samples the dataloader and returns a zipped list of examples
     """
     images = []
-    embeddings = []
+    img_embeddings = []
+    text_embeddings = []
     captions = []
-    dataset_keys = get_dataset_keys(dataloader)
-    has_caption = "txt" in dataset_keys
-    for data in dataloader:
-        if has_caption:
-            img, emb, txt = data
+    for img, emb, txt in dataloader:
+        img_emb, text_emb = emb.get('img'), emb.get('text')
+        if img_emb is not None:
+            img_emb = img_emb.to(device=device, dtype=torch.float)
+            img_embeddings.extend(list(img_emb))
         else:
-            img, emb = data
-            txt = [""] * emb.shape[0]
+            # Then we add None img.shape[0] times
+            img_embeddings.extend([None]*img.shape[0])
+        if text_emb is not None:
+            text_emb = text_emb.to(device=device, dtype=torch.float)
+            text_embeddings.extend(list(text_emb))
+        else:
+            # Then we add None img.shape[0] times
+            text_embeddings.extend([None]*img.shape[0])
         img = img.to(device=device, dtype=torch.float)
-        emb = emb.to(device=device, dtype=torch.float)
         images.extend(list(img))
-        embeddings.extend(list(emb))
         captions.extend(list(txt))
         if len(images) >= n:
             break
-    print("Generated {} examples".format(len(images)))
-    return list(zip(images[:n], embeddings[:n], captions[:n]))
+    return list(zip(images[:n], img_embeddings[:n], text_embeddings[:n], captions[:n]))
 
-def generate_samples(trainer, example_data, text_prepend=""):
+def generate_samples(trainer, example_data, condition_on_text_encodings=False, text_prepend=""):
     """
     Takes example data and generates images from the embeddings
     Returns three lists: real images, generated images, and captions
     """
-    real_images, embeddings, txts = zip(*example_data)
-    embeddings_tensor = torch.stack(embeddings)
-    samples = trainer.sample(embeddings_tensor)
+    real_images, img_embeddings, text_embeddings, txts = zip(*example_data)
+    sample_params = {}
+    if img_embeddings[0] is None:
+        # Generate image embeddings from clip
+        imgs_tensor = torch.stack(real_images)
+        img_embeddings, *_ = trainer.embed_image(imgs_tensor)
+        sample_params["image_embed"] = img_embeddings
+    else:
+        # Then we are using precomputed image embeddings
+        img_embeddings = torch.stack(img_embeddings)
+        sample_params["image_embed"] = img_embeddings
+    if condition_on_text_encodings:
+        if text_embeddings[0] is None:
+            # Generate text embeddings from text
+            tokenized_texts = tokenize(txts, truncate=True)
+            sample_params["text"] = tokenized_texts
+        else:
+            # Then we are using precomputed text embeddings
+            text_embeddings = torch.stack(text_embeddings)
+            sample_params["text_encodings"] = text_embeddings
+    samples = trainer.sample(**sample_params)
     generated_images = list(samples)
     captions = [text_prepend + txt for txt in txts]
     return real_images, generated_images, captions
 
-def generate_grid_samples(trainer, examples, text_prepend=""):
+def generate_grid_samples(trainer, examples, condition_on_text_encodings=False, text_prepend=""):
     """
     Generates samples and uses torchvision to put them in a side by side grid for easy viewing
     """
-    real_images, generated_images, captions = generate_samples(trainer, examples, text_prepend)
+    real_images, generated_images, captions = generate_samples(trainer, examples, condition_on_text_encodings, text_prepend)
+
+    real_image_size = real_images[0].shape[-1]
+    generated_image_size = generated_images[0].shape[-1]
+
+    # training images may be larger than the generated one
+    if real_image_size > generated_image_size:
+        real_images = [resize_image_to(image, generated_image_size) for image in real_images]
+
     grid_images = [torchvision.utils.make_grid([original_image, generated_image]) for original_image, generated_image in zip(real_images, generated_images)]
     return grid_images, captions
                     
-def evaluate_trainer(trainer, dataloader, device, n_evaluation_samples=1000, FID=None, IS=None, KID=None, LPIPS=None):
+def evaluate_trainer(trainer, dataloader, device, condition_on_text_encodings=False, n_evaluation_samples=1000, FID=None, IS=None, KID=None, LPIPS=None):
     """
     Computes evaluation metrics for the decoder
     """
     metrics = {}
     # Prepare the data
     examples = get_example_data(dataloader, device, n_evaluation_samples)
-    real_images, generated_images, captions = generate_samples(trainer, examples)
+    if len(examples) == 0:
+        print("No data to evaluate. Check that your dataloader has shards.")
+        return metrics
+    real_images, generated_images, captions = generate_samples(trainer, examples, condition_on_text_encodings)
     real_images = torch.stack(real_images).to(device=device, dtype=torch.float)
     generated_images = torch.stack(generated_images).to(device=device, dtype=torch.float)
     # Convert from [0, 1] to [0, 255] and from torch.float to torch.uint8
     int_real_images = real_images.mul(255).add(0.5).clamp(0, 255).type(torch.uint8)
     int_generated_images = generated_images.mul(255).add(0.5).clamp(0, 255).type(torch.uint8)
+
+    def null_sync(t, *args, **kwargs):
+        return [t]
+
     if exists(FID):
-        fid = FrechetInceptionDistance(**FID)
+        fid = FrechetInceptionDistance(**FID, dist_sync_fn=null_sync)
         fid.to(device=device)
         fid.update(int_real_images, real=True)
         fid.update(int_generated_images, real=False)
         metrics["FID"] = fid.compute().item()
     if exists(IS):
-        inception = InceptionScore(**IS)
+        inception = InceptionScore(**IS, dist_sync_fn=null_sync)
         inception.to(device=device)
         inception.update(int_real_images)
         is_mean, is_std = inception.compute()
         metrics["IS_mean"] = is_mean.item()
         metrics["IS_std"] = is_std.item()
     if exists(KID):
-        kernel_inception = KernelInceptionDistance(**KID)
+        kernel_inception = KernelInceptionDistance(**KID, dist_sync_fn=null_sync)
         kernel_inception.to(device=device)
         kernel_inception.update(int_real_images, real=True)
         kernel_inception.update(int_generated_images, real=False)
@@ -177,68 +223,82 @@ def evaluate_trainer(trainer, dataloader, device, n_evaluation_samples=1000, FID
         # Convert from [0, 1] to [-1, 1]
         renorm_real_images = real_images.mul(2).sub(1)
         renorm_generated_images = generated_images.mul(2).sub(1)
-        lpips = LearnedPerceptualImagePatchSimilarity(**LPIPS)
+        lpips = LearnedPerceptualImagePatchSimilarity(**LPIPS, dist_sync_fn=null_sync)
         lpips.to(device=device)
         lpips.update(renorm_real_images, renorm_generated_images)
         metrics["LPIPS"] = lpips.compute().item()
+
+    if trainer.accelerator.num_processes > 1:
+        # Then we should sync the metrics
+        metrics_order = sorted(metrics.keys())
+        metrics_tensor = torch.zeros(1, len(metrics), device=device, dtype=torch.float)
+        for i, metric_name in enumerate(metrics_order):
+            metrics_tensor[0, i] = metrics[metric_name]
+        metrics_tensor = trainer.accelerator.gather(metrics_tensor)
+        metrics_tensor = metrics_tensor.mean(dim=0)
+        for i, metric_name in enumerate(metrics_order):
+            metrics[metric_name] = metrics_tensor[i].item()
     return metrics
 
-def save_trainer(tracker, trainer, epoch, step, validation_losses, relative_paths):
+def save_trainer(tracker: Tracker, trainer: DecoderTrainer, epoch: int, sample: int, next_task: str, validation_losses: List[float], samples_seen: int, is_latest=True, is_best=False):
     """
     Logs the model with an appropriate method depending on the tracker
     """
-    if isinstance(relative_paths, str):
-        relative_paths = [relative_paths]
-    trainer_state_dict = {}
-    trainer_state_dict["trainer"] = trainer.state_dict()
-    trainer_state_dict['epoch'] = epoch
-    trainer_state_dict['step'] = step
-    trainer_state_dict['validation_losses'] = validation_losses
-    for relative_path in relative_paths:
-        tracker.save_state_dict(trainer_state_dict, relative_path)
+    tracker.save(trainer, is_best=is_best, is_latest=is_latest, epoch=epoch, sample=sample, next_task=next_task, validation_losses=validation_losses, samples_seen=samples_seen)
     
-def recall_trainer(tracker, trainer, recall_source=None, **load_config):
+def recall_trainer(tracker: Tracker, trainer: DecoderTrainer):
     """
     Loads the model with an appropriate method depending on the tracker
     """
-    print(print_ribbon(f"Loading model from {recall_source}"))
-    state_dict = tracker.recall_state_dict(recall_source, **load_config)
-    trainer.load_state_dict(state_dict["trainer"])
-    print("Model loaded")
-    return state_dict["epoch"], state_dict["step"], state_dict["validation_losses"]
+    trainer.accelerator.print(print_ribbon(f"Loading model from {type(tracker.loader).__name__}"))
+    state_dict = tracker.recall()
+    trainer.load_state_dict(state_dict, only_model=False, strict=True)
+    return state_dict.get("epoch", 0), state_dict.get("validation_losses", []), state_dict.get("next_task", "train"), state_dict.get("sample", 0), state_dict.get("samples_seen", 0)
 
 def train(
     dataloaders,
-    decoder,
-    tracker,
+    decoder: Decoder,
+    accelerator: Accelerator,
+    tracker: Tracker,
     inference_device,
-    load_config=None,
     evaluate_config=None,
     epoch_samples = None,  # If the training dataset is resampling, we have to manually stop an epoch
     validation_samples = None,
     epochs = 20,
     n_sample_images = 5,
     save_every_n_samples = 100000,
-    save_all=False,
-    save_latest=True,
-    save_best=True,
     unet_training_mask=None,
+    condition_on_text_encodings=False,
     **kwargs
 ):
     """
     Trains a decoder on a dataset.
     """
-    trainer = DecoderTrainer(  # TODO: Change the get_optimizer function so that it can take arbitrary named args so we can just put **kwargs as an argument here
-        decoder,
+    is_master = accelerator.process_index == 0
+
+    trainer = DecoderTrainer(
+        decoder=decoder,
+        accelerator=accelerator,
         **kwargs
     )
+
     # Set up starting model and parameters based on a recalled state dict
-    start_step = 0
     start_epoch = 0
     validation_losses = []
+    next_task = 'train'
+    sample = 0
+    samples_seen = 0
+    val_sample = 0
+    step = lambda: int(trainer.step.item())
 
-    if exists(load_config) and exists(load_config.source):
-        start_epoch, start_step, validation_losses = recall_trainer(tracker, trainer, recall_source=load_config.source, **load_config)
+    if tracker.loader is not None:
+        start_epoch, validation_losses, next_task, recalled_sample, samples_seen = recall_trainer(tracker, trainer)
+        if next_task == 'train':
+            sample = recalled_sample
+        if next_task == 'val':
+            val_sample = recalled_sample
+        accelerator.print(f"Loaded model from {type(tracker.loader).__name__} on epoch {start_epoch} having seen {samples_seen} samples with minimum validation loss {min(validation_losses) if len(validation_losses) > 0 else 'N/A'}")
+        accelerator.print(f"Starting training from task {next_task} at sample {sample} and validation sample {val_sample}")
     trainer.to(device=inference_device)
 
     if not exists(unet_training_mask):
@@ -246,197 +306,291 @@ def train(
         unet_training_mask = [True] * trainer.num_unets
     assert len(unet_training_mask) == trainer.num_unets, f"The unet training mask should be the same length as the number of unets in the decoder. Got {len(unet_training_mask)} and {trainer.num_unets}"
 
-    print(print_ribbon("Generating Example Data", repeat=40))
-    print("This can take a while to load the shard lists...")
-    train_example_data = get_example_data(dataloaders["train_sampling"], inference_device, n_sample_images)
-    test_example_data = get_example_data(dataloaders["test_sampling"], inference_device, n_sample_images)
+    accelerator.print(print_ribbon("Generating Example Data", repeat=40))
+    accelerator.print("This can take a while to load the shard lists...")
+    if is_master:
+        train_example_data = get_example_data(dataloaders["train_sampling"], inference_device, n_sample_images)
+        accelerator.print("Generated training examples")
+        test_example_data = get_example_data(dataloaders["test_sampling"], inference_device, n_sample_images)
+        accelerator.print("Generated testing examples")
     
     send_to_device = lambda arr: [x.to(device=inference_device, dtype=torch.float) for x in arr]
-    step = start_step
 
+    sample_length_tensor = torch.zeros(1, dtype=torch.int, device=inference_device)
+    unet_losses_tensor = torch.zeros(TRAIN_CALC_LOSS_EVERY_ITERS, trainer.num_unets, dtype=torch.float, device=inference_device)
     for epoch in range(start_epoch, epochs):
-        print(print_ribbon(f"Starting epoch {epoch}", repeat=40))
+        accelerator.print(print_ribbon(f"Starting epoch {epoch}", repeat=40))
 
         timer = Timer()
+        last_sample = sample
+        last_snapshot = sample
 
-        sample = 0
-        last_sample = 0
-        last_snapshot = 0
+        if next_task == 'train':
+            for i, (img, emb, txt) in enumerate(dataloaders["train"]):
+                # We want to count the total number of samples across all processes
+                sample_length_tensor[0] = len(img)
+                all_samples = accelerator.gather(sample_length_tensor)  # TODO: accelerator.reduce is broken when this was written. If it is fixed replace this.
+                total_samples = all_samples.sum().item()
+                sample += total_samples
+                samples_seen += total_samples
+                img_emb = emb.get('img')
+                has_img_embedding = img_emb is not None
+                if has_img_embedding:
+                    img_emb, = send_to_device((img_emb,))
+                text_emb = emb.get('text')
+                has_text_embedding = text_emb is not None
+                if has_text_embedding:
+                    text_emb, = send_to_device((text_emb,))
+                img, = send_to_device((img,))
 
-        losses = []
+                trainer.train()
+                for unet in range(1, trainer.num_unets+1):
+                    # Check if this is a unet we are training
+                    if not unet_training_mask[unet-1]: # Unet index is the unet number - 1
+                        continue
 
-        for i, (img, emb) in enumerate(dataloaders["train"]):
-            step += 1
-            sample += img.shape[0]
-            img, emb = send_to_device((img, emb))
-            
-            trainer.train()
-            for unet in range(1, trainer.num_unets+1):
-                # Check if this is a unet we are training
-                if not unet_training_mask[unet-1]: # Unet index is the unet number - 1
-                    continue
-
-                loss = trainer.forward(img, image_embed=emb, unet_number=unet)
-                trainer.update(unet_number=unet)
-                losses.append(loss)
-
-            samples_per_sec = (sample - last_sample) / timer.elapsed()
-
-            timer.reset()
-            last_sample = sample
-
-            if i % TRAIN_CALC_LOSS_EVERY_ITERS == 0:
-                average_loss = sum(losses) / len(losses)
-                log_data = {
-                    "Training loss": average_loss,
-                    "Epoch": epoch,
-                    "Sample": sample,
-                    "Step": i,
-                    "Samples per second": samples_per_sec
-                }
-                tracker.log(log_data, step=step, verbose=True)
-                losses = []
-
-            if last_snapshot + save_every_n_samples < sample:  # This will miss by some amount every time, but it's not a big deal... I hope
-                last_snapshot = sample
-                # We need to know where the model should be saved
-                save_paths = []
-                if save_latest:
-                    save_paths.append("latest.pth")
-                if save_all:
-                    save_paths.append(f"checkpoints/epoch_{epoch}_step_{step}.pth")
-
-                save_trainer(tracker, trainer, epoch, step, validation_losses, save_paths)
-
-                if exists(n_sample_images) and n_sample_images > 0:
-                    trainer.eval()
-                    train_images, train_captions = generate_grid_samples(trainer, train_example_data, "Train: ")
-                    tracker.log_images(train_images, captions=train_captions, image_section="Train Samples", step=step)
-
-            if exists(epoch_samples) and sample >= epoch_samples:
-                break
-
-        trainer.eval()
-        print(print_ribbon(f"Starting Validation {epoch}", repeat=40))
-        with torch.no_grad():
-            sample = 0
-            average_loss = 0
-            timer = Timer()
-            for i, (img, emb, txt) in enumerate(dataloaders["val"]):
-                sample += img.shape[0]
-                img, emb = send_to_device((img, emb))
+                    forward_params = {}
+                    if has_img_embedding:
+                        forward_params['image_embed'] = img_emb
+                    else:
+                        # Forward pass automatically generates embedding
+                        pass
+                    if condition_on_text_encodings:
+                        if has_text_embedding:
+                            forward_params['text_encodings'] = text_emb
+                        else:
+                            # Then we need to pass the text instead
+                            tokenized_texts = tokenize(txt, truncate=True)
+                            forward_params['text'] = tokenized_texts
+                    loss = trainer.forward(img, **forward_params, unet_number=unet)
+                    trainer.update(unet_number=unet)
+                    unet_losses_tensor[i % TRAIN_CALC_LOSS_EVERY_ITERS, unet-1] = loss
                 
+                samples_per_sec = (sample - last_sample) / timer.elapsed()
+                timer.reset()
+                last_sample = sample
+
+                if i % TRAIN_CALC_LOSS_EVERY_ITERS == 0:
+                    # We want to average losses across all processes
+                    unet_all_losses = accelerator.gather(unet_losses_tensor)
+                    mask = unet_all_losses != 0
+                    unet_average_loss = (unet_all_losses * mask).sum(dim=0) / mask.sum(dim=0)
+                    loss_map = { f"Unet {index} Training Loss": loss.item() for index, loss in enumerate(unet_average_loss) if loss != 0 }
+
+                    # gather decay rate on each UNet
+                    ema_decay_list = {f"Unet {index} EMA Decay": ema_unet.get_current_decay() for index, ema_unet in enumerate(trainer.ema_unets)}
+
+                    log_data = {
+                        "Epoch": epoch,
+                        "Sample": sample,
+                        "Step": i,
+                        "Samples per second": samples_per_sec,
+                        "Samples Seen": samples_seen,
+                        **ema_decay_list,
+                        **loss_map
+                    }
+
+                    if is_master:
+                        tracker.log(log_data, step=step())
+
+                if is_master and last_snapshot + save_every_n_samples < sample:  # This will miss by some amount every time, but it's not a big deal... I hope
+                    # It is difficult to gather this kind of info on the accelerator, so we have to do it on the master
+                    print("Saving snapshot")
+                    last_snapshot = sample
+                    # We need to know where the model should be saved
+                    save_trainer(tracker, trainer, epoch, sample, next_task, validation_losses, samples_seen)
+                    if exists(n_sample_images) and n_sample_images > 0:
+                        trainer.eval()
+                        train_images, train_captions = generate_grid_samples(trainer, train_example_data, condition_on_text_encodings, "Train: ")
+                        tracker.log_images(train_images, captions=train_captions, image_section="Train Samples", step=step())
+                
+                if epoch_samples is not None and sample >= epoch_samples:
+                    break
+            next_task = 'val'
+            sample = 0
+
+        all_average_val_losses = None
+        if next_task == 'val':
+            trainer.eval()
+            accelerator.print(print_ribbon(f"Starting Validation {epoch}", repeat=40))
+            last_val_sample = val_sample
+            val_sample_length_tensor = torch.zeros(1, dtype=torch.int, device=inference_device)
+            average_val_loss_tensor = torch.zeros(1, trainer.num_unets, dtype=torch.float, device=inference_device)
+            timer = Timer()
+            accelerator.wait_for_everyone()
+            i = 0
+            for i, (img, emb, txt) in enumerate(dataloaders["val"]):
+                val_sample_length_tensor[0] = len(img)
+                all_samples = accelerator.gather(val_sample_length_tensor)
+                total_samples = all_samples.sum().item()
+                val_sample += total_samples
+                img_emb = emb.get('img')
+                has_img_embedding = img_emb is not None
+                if has_img_embedding:
+                    img_emb, = send_to_device((img_emb,))
+                text_emb = emb.get('text')
+                has_text_embedding = text_emb is not None
+                if has_text_embedding:
+                    text_emb, = send_to_device((text_emb,))
+                img, = send_to_device((img,))
+
                 for unet in range(1, len(decoder.unets)+1):
-                    loss = trainer.forward(img.float(), image_embed=emb.float(), unet_number=unet)
-                    average_loss += loss
+                    if not unet_training_mask[unet-1]: # Unet index is the unet number - 1
+                        # No need to evaluate an unchanging unet
+                        continue
+                        
+                    forward_params = {}
+                    if has_img_embedding:
+                        forward_params['image_embed'] = img_emb.float()
+                    else:
+                        # Forward pass automatically generates embedding
+                        pass
+                    if condition_on_text_encodings:
+                        if has_text_embedding:
+                            forward_params['text_encodings'] = text_emb.float()
+                        else:
+                            # Then we need to pass the text instead
+                            tokenized_texts = tokenize(txt, truncate=True)
+                            forward_params['text'] = tokenized_texts
+                    loss = trainer.forward(img.float(), **forward_params, unet_number=unet)
+                    average_val_loss_tensor[0, unet-1] += loss
 
                 if i % VALID_CALC_LOSS_EVERY_ITERS == 0:
-                    print(f"Epoch {epoch}/{epochs} - {sample / timer.elapsed():.2f} samples/sec")
-                    print(f"Loss: {average_loss / (i+1)}")
-                    print("")
-
-                if exists(validation_samples) and sample >= validation_samples:
+                    samples_per_sec = (val_sample - last_val_sample) / timer.elapsed()
+                    timer.reset()
+                    last_val_sample = val_sample
+                    accelerator.print(f"Epoch {epoch}/{epochs} Val Step {i} -  Sample {val_sample} - {samples_per_sec:.2f} samples/sec")
+                    accelerator.print(f"Loss: {(average_val_loss_tensor / (i+1))}")
+                    accelerator.print("")
+                
+                if validation_samples is not None and val_sample >= validation_samples:
                     break
+            print(f"Rank {accelerator.state.process_index} finished validation after {i} steps")
+            accelerator.wait_for_everyone()
+            average_val_loss_tensor /= i+1
+            # Gather all the average loss tensors
+            all_average_val_losses = accelerator.gather(average_val_loss_tensor)
+            if is_master:
+                unet_average_val_loss = all_average_val_losses.mean(dim=0)
+                val_loss_map = { f"Unet {index} Validation Loss": loss.item() for index, loss in enumerate(unet_average_val_loss) if loss != 0 }
+                tracker.log(val_loss_map, step=step())
+            next_task = 'eval'
 
-            average_loss /= i+1
-            log_data = {
-                "Validation loss": average_loss
-            }
-            tracker.log(log_data, step=step, verbose=True)
+        if next_task == 'eval':
+            if exists(evaluate_config):
+                accelerator.print(print_ribbon(f"Starting Evaluation {epoch}", repeat=40))
+                evaluation = evaluate_trainer(trainer, dataloaders["val"], inference_device, **evaluate_config.dict(), condition_on_text_encodings=condition_on_text_encodings)
+                if is_master:
+                    tracker.log(evaluation, step=step())
+            next_task = 'sample'
+            val_sample = 0
 
-        # Compute evaluation metrics
-        if exists(evaluate_config):
-            print(print_ribbon(f"Starting Evaluation {epoch}", repeat=40))
-            evaluation = evaluate_trainer(trainer, dataloaders["val"], inference_device, **evaluate_config.dict())
-            tracker.log(evaluation, step=step, verbose=True)
+        if next_task == 'sample':
+            if is_master:
+                # Generate examples and save the model if we are the master
+                # Generate sample images
+                print(print_ribbon(f"Sampling Set {epoch}", repeat=40))
+                test_images, test_captions = generate_grid_samples(trainer, test_example_data, condition_on_text_encodings, "Test: ")
+                train_images, train_captions = generate_grid_samples(trainer, train_example_data, condition_on_text_encodings, "Train: ")
+                tracker.log_images(test_images, captions=test_captions, image_section="Test Samples", step=step())
+                tracker.log_images(train_images, captions=train_captions, image_section="Train Samples", step=step())
 
-        # Generate sample images
-        print(print_ribbon(f"Sampling Set {epoch}", repeat=40))
-        test_images, test_captions = generate_grid_samples(trainer, test_example_data, "Test: ")
-        train_images, train_captions = generate_grid_samples(trainer, train_example_data, "Train: ")
-        tracker.log_images(test_images, captions=test_captions, image_section="Test Samples", step=step)
-        tracker.log_images(train_images, captions=train_captions, image_section="Train Samples", step=step)
+                print(print_ribbon(f"Starting Saving {epoch}", repeat=40))
+                is_best = False
+                if all_average_val_losses is not None:
+                    average_loss = all_average_val_losses.mean(dim=0).item()
+                    if len(validation_losses) == 0 or average_loss < min(validation_losses):
+                        is_best = True
+                    validation_losses.append(average_loss)
+                save_trainer(tracker, trainer, epoch, sample, next_task, validation_losses, samples_seen, is_best=is_best)
+            next_task = 'train'
 
-        print(print_ribbon(f"Starting Saving {epoch}", repeat=40))
-        # Get the same paths
-        save_paths = []
-        if save_latest:
-            save_paths.append("latest.pth")
-        if save_best and (len(validation_losses) == 0 or average_loss < min(validation_losses)):
-            save_paths.append("best.pth")
-        validation_losses.append(average_loss)
-        save_trainer(tracker, trainer, epoch, step, validation_losses, save_paths)
-
-def create_tracker(config, tracker_type=None, data_path=None, **kwargs):
-    """
-    Creates a tracker of the specified type and initializes special features based on the full config
-    """
+def create_tracker(accelerator: Accelerator, config: TrainDecoderConfig, config_path: str, dummy: bool = False) -> Tracker:
     tracker_config = config.tracker
-    init_config = {}
-
-    if exists(tracker_config.init_config):
-        init_config["config"] = tracker_config.init_config
-
-    if tracker_type == "console":
-        tracker = ConsoleTracker(**init_config)
-    elif tracker_type == "wandb":
-        # We need to initialize the resume state here
-        load_config = config.load
-        if load_config.source == "wandb" and load_config.resume:
-            # Then we are resuming the run load_config["run_path"]
-            run_id = load_config.run_path.split("/")[-1]
-            init_config["id"] = run_id
-            init_config["resume"] = "must"
-
-        init_config["entity"] = tracker_config.wandb_entity
-        init_config["project"] = tracker_config.wandb_project
-        tracker = WandbTracker(data_path)
-        tracker.init(**init_config)
-    else:
-        raise ValueError(f"Tracker type {tracker_type} not supported by decoder trainer")
+    accelerator_config = {
+        "Distributed": accelerator.distributed_type != accelerate_dataclasses.DistributedType.NO,
+        "DistributedType": accelerator.distributed_type,
+        "NumProcesses": accelerator.num_processes,
+        "MixedPrecision": accelerator.mixed_precision
+    }
+    tracker: Tracker = tracker_config.create(config, accelerator_config, dummy_mode=dummy)
+    tracker.save_config(config_path, config_name='decoder_config.json')
     return tracker
     
-def initialize_training(config):
-    # Create the save path
-    if "cuda" in config.train.device:
-        assert torch.cuda.is_available(), "CUDA is not available"
-    device = torch.device(config.train.device)
-    torch.cuda.set_device(device)
-    all_shards = list(range(config.data.start_shard, config.data.end_shard + 1))
+def initialize_training(config: TrainDecoderConfig, config_path):
+    # Make sure if we are not loading, distributed models are initialized to the same values
+    torch.manual_seed(config.seed)
 
+    # Set up accelerator for configurable distributed training
+    ddp_kwargs = DistributedDataParallelKwargs(find_unused_parameters=config.train.find_unused_parameters)
+    accelerator = Accelerator(kwargs_handlers=[ddp_kwargs])
+    
+    # Set up data
+    all_shards = list(range(config.data.start_shard, config.data.end_shard + 1))
+    world_size = accelerator.num_processes
+    rank = accelerator.process_index
+    shards_per_process = len(all_shards) // world_size
+    assert shards_per_process > 0, "Not enough shards to split evenly"
+    my_shards = all_shards[rank * shards_per_process: (rank + 1) * shards_per_process]
     dataloaders = create_dataloaders (
-        available_shards=all_shards,
+        available_shards=my_shards,
         img_preproc = config.data.img_preproc,
         train_prop = config.data.splits.train,
         val_prop = config.data.splits.val,
         test_prop = config.data.splits.test,
         n_sample_images=config.train.n_sample_images,
-        **config.data.dict()
+        **config.data.dict(),
+        rank = rank,
+        seed = config.seed,
     )
 
-    decoder = config.decoder.create().to(device = device)
+    # Create the decoder model and print basic info
+    decoder = config.decoder.create()
     num_parameters = sum(p.numel() for p in decoder.parameters())
-    print(print_ribbon("Loaded Config", repeat=40))
-    print(f"Number of parameters: {num_parameters}")
 
-    tracker = create_tracker(config, **config.tracker.dict())
+    # Create and initialize the tracker if we are the master
+    tracker = create_tracker(accelerator, config, config_path, dummy = rank!=0)
 
-    train(dataloaders, decoder, 
+    has_img_embeddings = config.data.img_embeddings_url is not None
+    has_text_embeddings = config.data.text_embeddings_url is not None
+    conditioning_on_text = any([unet.cond_on_text_encodings for unet in config.decoder.unets])
+
+    has_clip_model = config.decoder.clip is not None
+    data_source_string = ""
+
+    if has_img_embeddings:
+        data_source_string += "precomputed image embeddings"
+    elif has_clip_model:
+        data_source_string += "clip image embeddings generation"
+    else:
+        raise ValueError("No image embeddings source specified")
+    if conditioning_on_text:
+        if has_text_embeddings:
+            data_source_string += " and precomputed text embeddings"
+        elif has_clip_model:
+            data_source_string += " and clip text encoding generation"
+        else:
+            raise ValueError("No text embeddings source specified")
+
+    accelerator.print(print_ribbon("Loaded Config", repeat=40))
+    accelerator.print(f"Running training with {accelerator.num_processes} processes and {accelerator.distributed_type} distributed training")
+    accelerator.print(f"Training using {data_source_string}. {'conditioned on text' if conditioning_on_text else 'not conditioned on text'}")
+    accelerator.print(f"Number of parameters: {num_parameters}")
+    train(dataloaders, decoder, accelerator,
         tracker=tracker,
-        inference_device=device,
-        load_config=config.load,
+        inference_device=accelerator.device,
         evaluate_config=config.evaluate,
+        condition_on_text_encodings=conditioning_on_text,
         **config.train.dict(),
     )
-
+    
 # Create a simple click command line interface to load the config and start the training
 @click.command()
 @click.option("--config_file", default="./train_decoder_config.json", help="Path to config file")
 def main(config_file):
-    print("Recalling config from {}".format(config_file))
-    config = TrainDecoderConfig.from_json_path(config_file)
-    initialize_training(config)
-
+    config_file_path = Path(config_file)
+    config = TrainDecoderConfig.from_json_path(str(config_file_path))
+    initialize_training(config, config_path=config_file_path)
 
 if __name__ == "__main__":
     main()

train_diffusion_prior.py

@@ -1,75 +1,135 @@
-from pathlib import Path
+# TODO: add start, num_data_points, eval_every and group to config
+# TODO: switch back to repo's wandb
+
+START = 0
+NUM_DATA_POINTS = 250e6
+EVAL_EVERY = 1000
+GROUP = "distributed"
+
+import os
 import click
-import math
-import numpy as np
+import wandb
 
 import torch
-import clip
 from torch import nn
+from torch.utils.data import DataLoader
 
-from dalle2_pytorch.dataloaders import make_splits
-from dalle2_pytorch import DiffusionPrior, DiffusionPriorNetwork, OpenAIClipAdapter
-from dalle2_pytorch.trainer import DiffusionPriorTrainer, load_diffusion_model, save_diffusion_model
+import numpy as np
 
-from dalle2_pytorch.trackers import ConsoleTracker, WandbTracker
-from dalle2_pytorch.utils import Timer, print_ribbon
+from accelerate import Accelerator
 
-from embedding_reader import EmbeddingReader
+from dalle2_pytorch.dataloaders import get_reader, make_splits
+from dalle2_pytorch.utils import Timer
+from dalle2_pytorch.train_configs import (
+    DiffusionPriorTrainConfig,
+    TrainDiffusionPriorConfig,
+)
+from dalle2_pytorch.trackers import BaseTracker, WandbTracker
+from dalle2_pytorch import DiffusionPriorTrainer
 
-from tqdm import tqdm
 
-# constants
+# helpers
 
-REPORT_METRICS_EVERY = 250 # for cosine similarity and other metric reporting during training
 
-tracker = WandbTracker()
+cos = nn.CosineSimilarity(dim=1, eps=1e-6)
 
-# helpers functions
 
 def exists(val):
-    val is not None
+    return val is not None
 
-# functions
 
-def eval_model(model, dataloader, text_conditioned, loss_type, phase="Validation"):
-    model.eval()
+def make_model(
+    prior_config, train_config, device: str = None, accelerator: Accelerator = None
+):
+    # create model from config
+    diffusion_prior = prior_config.create()
+
+    # instantiate the trainer
+    trainer = DiffusionPriorTrainer(
+        diffusion_prior=diffusion_prior,
+        lr=train_config.lr,
+        wd=train_config.wd,
+        max_grad_norm=train_config.max_grad_norm,
+        amp=train_config.amp,
+        use_ema=train_config.use_ema,
+        device=device,
+        accelerator=accelerator,
+    )
+
+    return trainer
+
+
+# eval functions
+
+
+def eval_model(
+    trainer: DiffusionPriorTrainer,
+    dataloader: DataLoader,
+    text_conditioned: bool,
+    loss_type: str,
+    tracker_context: str,
+    tracker: BaseTracker = None,
+    use_ema: bool = True,
+):
+    trainer.eval()
+    if trainer.is_main_process():
+        click.secho(f"Measuring performance on {tracker_context}", fg="green", blink=True)
 
     with torch.no_grad():
-        total_loss = 0.
-        total_samples = 0.
+        total_loss = 0.0
+        total_samples = 0.0
 
-        for image_embeddings, text_data in tqdm(dataloader):
+        for image_embeddings, text_data in dataloader:
+            image_embeddings = image_embeddings.to(trainer.device)
+            text_data = text_data.to(trainer.device)
 
             batches = image_embeddings.shape[0]
 
             input_args = dict(image_embed=image_embeddings)
+
             if text_conditioned:
-                input_args = dict(**input_args, text = text_data)
+                input_args = dict(**input_args, text=text_data)
             else:
                 input_args = dict(**input_args, text_embed=text_data)
 
-            loss = model(**input_args)
+            if use_ema:
+                loss = trainer.ema_diffusion_prior(**input_args)
+            else:
+                loss = trainer(**input_args)
 
             total_loss += loss * batches
             total_samples += batches
 
-        avg_loss = (total_loss / total_samples)
+        avg_loss = total_loss / total_samples
 
-        tracker.log({f'{phase} {loss_type}': avg_loss})
+        stats = {f"{tracker_context}-{loss_type}": avg_loss}
+        trainer.print(stats)
 
-def report_cosine_sims(diffusion_prior, dataloader, text_conditioned):
-    diffusion_prior.eval()
+        if exists(tracker):
+            tracker.log(stats, step=trainer.step.item() + 1)
 
-    cos = nn.CosineSimilarity(dim=1, eps=1e-6)
 
-    for test_image_embeddings, text_data in tqdm(dataloader):
+def report_cosine_sims(
+    trainer: DiffusionPriorTrainer,
+    dataloader: DataLoader,
+    text_conditioned: bool,
+    tracker: BaseTracker,
+    tracker_context: str = "validation",
+):
+    trainer.eval()
+    if trainer.is_main_process():
+        click.secho("Measuring Cosine-Similarity", fg="green", blink=True)
+
+    for test_image_embeddings, text_data in dataloader:
+        test_image_embeddings = test_image_embeddings.to(trainer.device)
+        text_data = text_data.to(trainer.device)
 
         # we are text conditioned, we produce an embedding from the tokenized text
         if text_conditioned:
-            text_embedding, text_encodings, text_mask = diffusion_prior.clip.embed_text(
-                text_data)
-            text_cond = dict(text_embed=text_embedding,
-                             text_encodings=text_encodings, mask=text_mask)
+            text_embedding, text_encodings, text_mask = trainer.embed_text(text_data)
+            text_cond = dict(
+                text_embed=text_embedding, text_encodings=text_encodings, mask=text_mask
+            )
         else:
             text_embedding = text_data
             text_cond = dict(text_embed=text_embedding)
@@ -80,8 +140,9 @@ def report_cosine_sims(diffusion_prior, dataloader, text_conditioned):
         # roll the text to simulate "unrelated" captions
         rolled_idx = torch.roll(torch.arange(text_embedding.shape[0]), 1)
         text_embed_shuffled = text_embed_shuffled[rolled_idx]
-        text_embed_shuffled = text_embed_shuffled / \
-            text_embed_shuffled.norm(dim=1, keepdim=True)
+        text_embed_shuffled = text_embed_shuffled / text_embed_shuffled.norm(
+            dim=1, keepdim=True
+        )
 
         if text_conditioned:
             text_encodings_shuffled = text_encodings[rolled_idx]
@@ -90,276 +151,276 @@ def report_cosine_sims(diffusion_prior, dataloader, text_conditioned):
             text_encodings_shuffled = None
             text_mask_shuffled = None
 
-        text_cond_shuffled = dict(text_embed=text_embed_shuffled,
-                                  text_encodings=text_encodings_shuffled, mask=text_mask_shuffled)
+        text_cond_shuffled = dict(
+            text_embed=text_embed_shuffled,
+            text_encodings=text_encodings_shuffled,
+            mask=text_mask_shuffled,
+        )
 
         # prepare the text embedding
         text_embed = text_embedding / text_embedding.norm(dim=1, keepdim=True)
 
         # prepare image embeddings
-        test_image_embeddings = test_image_embeddings / \
-            test_image_embeddings.norm(dim=1, keepdim=True)
+        test_image_embeddings = test_image_embeddings / test_image_embeddings.norm(
+            dim=1, keepdim=True
+        )
 
         # predict on the unshuffled text embeddings
-        predicted_image_embeddings = diffusion_prior.p_sample_loop(
-            test_image_embeddings.shape, text_cond)
-        predicted_image_embeddings = predicted_image_embeddings / \
-            predicted_image_embeddings.norm(dim=1, keepdim=True)
+        predicted_image_embeddings = trainer.p_sample_loop(
+            test_image_embeddings.shape, text_cond
+        )
+
+        predicted_image_embeddings = (
+            predicted_image_embeddings
+            / predicted_image_embeddings.norm(dim=1, keepdim=True)
+        )
 
         # predict on the shuffled embeddings
-        predicted_unrelated_embeddings = diffusion_prior.p_sample_loop(
-            test_image_embeddings.shape, text_cond_shuffled)
-        predicted_unrelated_embeddings = predicted_unrelated_embeddings / \
-            predicted_unrelated_embeddings.norm(dim=1, keepdim=True)
+        predicted_unrelated_embeddings = trainer.p_sample_loop(
+            test_image_embeddings.shape, text_cond_shuffled
+        )
+
+        predicted_unrelated_embeddings = (
+            predicted_unrelated_embeddings
+            / predicted_unrelated_embeddings.norm(dim=1, keepdim=True)
+        )
 
         # calculate similarities
-        original_similarity = cos(
-           text_embed, test_image_embeddings).cpu().numpy()
-        predicted_similarity = cos(
-           text_embed, predicted_image_embeddings).cpu().numpy()
-        unrelated_similarity = cos(
-           text_embed, predicted_unrelated_embeddings).cpu().numpy()
-        predicted_img_similarity = cos(
-           test_image_embeddings, predicted_image_embeddings).cpu().numpy()
-        tracker.log({"CosineSimilarity(text_embed,image_embed)": np.mean(original_similarity),
-            "CosineSimilarity(text_embed,predicted_image_embed)":np.mean(predicted_similarity),
-            "CosineSimilarity(orig_image_embed,predicted_image_embed)":np.mean(predicted_img_similarity),
-            "CosineSimilarity(text_embed,predicted_unrelated_embed)": np.mean(unrelated_similarity),
-            "Cosine similarity difference":np.mean(predicted_similarity - original_similarity)})
+        original_similarity = cos(text_embed, test_image_embeddings).cpu().numpy()
+        predicted_similarity = cos(text_embed, predicted_image_embeddings).cpu().numpy()
+        unrelated_similarity = (
+            cos(text_embed, predicted_unrelated_embeddings).cpu().numpy()
+        )
+        predicted_img_similarity = (
+            cos(test_image_embeddings, predicted_image_embeddings).cpu().numpy()
+        )
+
+        stats = {
+            f"{tracker_context}/baseline similarity": np.mean(original_similarity),
+            f"{tracker_context}/similarity with text": np.mean(predicted_similarity),
+            f"{tracker_context}/similarity with original image": np.mean(
+                predicted_img_similarity
+            ),
+            f"{tracker_context}/similarity with unrelated caption": np.mean(unrelated_similarity),
+            f"{tracker_context}/difference from baseline similarity": np.mean(
+                predicted_similarity - original_similarity
+            ),
+        }
+
+        for k, v in stats.items():
+            trainer.print(f"{tracker_context}/{k}: {v}")
+
+        if exists(tracker):
+            tracker.log(stats, step=trainer.step.item() + 1)
+
+
+# training script
+
+
+def train(
+    trainer: DiffusionPriorTrainer,
+    train_loader: DataLoader,
+    eval_loader: DataLoader,
+    test_loader: DataLoader,
+    config: DiffusionPriorTrainConfig,
+):
+    # distributed tracking with wandb
+    if trainer.accelerator.num_processes > 1:
+        os.environ["WANDB_START_METHOD"] = "thread"
+
+    tracker = wandb.init(
+        name=f"RANK:{trainer.device}",
+        entity=config.tracker.wandb_entity,
+        project=config.tracker.wandb_project,
+        config=config.dict(),
+        group=GROUP,
+    )
+
+    # sync after tracker init
+    trainer.wait_for_everyone()
+
+    # init a timer
+    timer = Timer()
+
+    # do training
+    for img, txt in train_loader:
+        trainer.train()
+        current_step = trainer.step.item() + 1
+
+        # place data on device
+        img = img.to(trainer.device)
+        txt = txt.to(trainer.device)
+
+        # pass to model
+        loss = trainer(text=txt, image_embed=img)
+
+        # display & log loss (will only print from main process)
+        trainer.print(f"Step {current_step}: Loss {loss}")
+
+        # perform backprop & apply EMA updates
+        trainer.update()
+
+        # track samples/sec/rank
+        samples_per_sec = img.shape[0] / timer.elapsed()
+
+        # samples seen
+        samples_seen = (
+            config.data.batch_size * trainer.accelerator.num_processes * current_step
+        )
+
+        # ema decay
+        ema_decay = trainer.ema_diffusion_prior.get_current_decay()
+
+        # Log on all processes for debugging
+        tracker.log(
+            {
+                "tracking/samples-sec": samples_per_sec,
+                "tracking/samples-seen": samples_seen,
+                "tracking/ema-decay": ema_decay,
+                "metrics/training-loss": loss,
+            },
+            step=current_step,
+        )
+
+        # Metric Tracking & Checkpointing (outside of timer's scope)
+        if current_step % EVAL_EVERY == 0:
+            eval_model(
+                trainer=trainer,
+                dataloader=eval_loader,
+                text_conditioned=config.prior.condition_on_text_encodings,
+                loss_type=config.prior.loss_type,
+                tracker_context="metrics/online-model-validation",
+                tracker=tracker,
+                use_ema=False,
+            )
+
+            eval_model(
+                trainer=trainer,
+                dataloader=eval_loader,
+                text_conditioned=config.prior.condition_on_text_encodings,
+                loss_type=config.prior.loss_type,
+                tracker_context="metrics/ema-model-validation",
+                tracker=tracker,
+                use_ema=True,
+            )
+
+            report_cosine_sims(
+                trainer=trainer,
+                dataloader=eval_loader,
+                text_conditioned=config.prior.condition_on_text_encodings,
+                tracker=tracker,
+                tracker_context="metrics",
+            )
+
+        if current_step % config.train.save_every == 0:
+            trainer.save(f"{config.tracker.data_path}/chkpt_step_{current_step}.pth")
+
+        # reset timer for next round
+        timer.reset()
+
+    # evaluate on test data
+
+    eval_model(
+        trainer=trainer,
+        dataloader=test_loader,
+        text_conditioned=config.prior.condition_on_text_encodings,
+        loss_type=config.prior.loss_type,
+        tracker_context="test",
+        tracker=tracker,
+    )
+
+    report_cosine_sims(
+        trainer,
+        test_loader,
+        config.prior.condition_on_text_encodings,
+        tracker,
+        tracker_context="test",
+    )
+
+
+def initialize_training(config, accelerator=None):
+    """
+    Parse the configuration file, and prepare everything necessary for training
+    """
+
+    # get a device
+
+    if accelerator:
+        device = accelerator.device
+        click.secho(f"Accelerating on: {device}", fg="yellow")
+    else:
+        if torch.cuda.is_available():
+            click.secho("GPU detected, defaulting to cuda:0", fg="yellow")
+            device = "cuda:0"
+        else:
+            click.secho("No GPU detected...using cpu", fg="yellow")
+            device = "cpu"
+
+    # make the trainer (will automatically distribute if possible & configured)
+
+    trainer = make_model(config.prior, config.train, device, accelerator).to(device)
+
+    # reload from chcekpoint
+
+    if config.load.resume == True:
+        click.secho(f"Loading checkpoint: {config.load.source}", fg="cyan")
+        trainer.load(config.load.source)
+
+    # fetch and prepare data
+
+    if trainer.is_main_process():
+        click.secho("Grabbing data from source", fg="blue", blink=True)
+
+    img_reader = get_reader(
+        text_conditioned=trainer.text_conditioned,
+        img_url=config.data.image_url,
+        meta_url=config.data.meta_url,
+    )
+
+    train_loader, eval_loader, test_loader = make_splits(
+        text_conditioned=trainer.text_conditioned,
+        batch_size=config.data.batch_size,
+        num_data_points=NUM_DATA_POINTS,
+        train_split=config.data.splits.train,
+        eval_split=config.data.splits.val,
+        image_reader=img_reader,
+        rank=accelerator.state.process_index if exists(accelerator) else 0,
+        world_size=accelerator.state.num_processes if exists(accelerator) else 1,
+        start=START,
+    )
+
+    # wait for everyone to load data before continuing
+    trainer.wait_for_everyone()
+
+    # start training
+    train(
+        trainer=trainer,
+        train_loader=train_loader,
+        eval_loader=eval_loader,
+        test_loader=test_loader,
+        config=config,
+    )
 
 
 @click.command()
-@click.option("--wandb-entity", default="laion")
-@click.option("--wandb-project", default="diffusion-prior")
-@click.option("--wandb-dataset", default="LAION-5B")
-@click.option("--wandb-arch", default="DiffusionPrior")
-@click.option("--image-embed-url", default="https://mystic.the-eye.eu/public/AI/cah/laion5b/embeddings/laion2B-en/img_emb/")
-@click.option("--text-embed-url", default="https://mystic.the-eye.eu/public/AI/cah/laion5b/embeddings/laion2B-en/text_emb/")
-@click.option("--meta-url", default="https://mystic.the-eye.eu/public/AI/cah/laion5b/embeddings/laion2B-en/laion2B-en-metadata/")
-@click.option("--learning-rate", default=1.1e-4)
-@click.option("--weight-decay", default=6.02e-2)
-@click.option("--dropout", default=5e-2)
-@click.option("--max-grad-norm", default=0.5)
-@click.option("--num-data-points", default=250e6)
-@click.option("--batch-size", default=320)
-@click.option("--num-epochs", default=5)
-@click.option("--image-embed-dim", default=768)
-@click.option("--train-percent", default=0.9)
-@click.option("--val-percent", default=1e-7)
-@click.option("--test-percent", default=0.0999999)
-@click.option("--dpn-depth", default=12)
-@click.option("--dpn-dim-head", default=64)
-@click.option("--dpn-heads", default=12)
-@click.option("--dp-condition-on-text-encodings", default=True)
-@click.option("--dp-timesteps", default=1000)
-@click.option("--dp-normformer", default=True)
-@click.option("--dp-cond-drop-prob", default=0.1)
-@click.option("--dp-loss-type", default="l2")
-@click.option("--clip", default="ViT-L/14")
-@click.option("--amp", default=False)
-@click.option("--save-interval", default=120)
-@click.option("--save-path", default="./diffusion_prior_checkpoints")
-@click.option("--pretrained-model-path", default=None)
-@click.option("--gpu-device", default=0)
-def train(
-    wandb_entity,
-    wandb_project,
-    wandb_dataset,
-    wandb_arch,
-    image_embed_url,
-    text_embed_url,
-    meta_url,
-    learning_rate,
-    weight_decay,
-    dropout,
-    max_grad_norm,
-    num_data_points,
-    batch_size,
-    num_epochs,
-    image_embed_dim,
-    train_percent,
-    val_percent,
-    test_percent,
-    dpn_depth,
-    dpn_dim_head,
-    dpn_heads,
-    dp_condition_on_text_encodings,
-    dp_timesteps,
-    dp_normformer,
-    dp_cond_drop_prob,
-    dp_loss_type,
-    clip,
-    amp,
-    save_interval,
-    save_path,
-    pretrained_model_path,
-    gpu_device
-):
-    config = {
-        "learning_rate": learning_rate,
-        "architecture": wandb_arch,
-        "dataset": wandb_dataset,
-        "weight_decay": weight_decay,
-        "max_gradient_clipping_norm": max_grad_norm,
-        "batch_size": batch_size,
-        "epochs": num_epochs,
-        "diffusion_prior_network": {
-            "depth": dpn_depth,
-            "dim_head": dpn_dim_head,
-            "heads": dpn_heads,
-            "normformer": dp_normformer
-        },
-        "diffusion_prior": {
-            "condition_on_text_encodings": dp_condition_on_text_encodings,
-            "timesteps": dp_timesteps,
-            "cond_drop_prob": dp_cond_drop_prob,
-            "loss_type": dp_loss_type,
-            "clip": clip
-        }
-    }
-
-    # Check if DPRIOR_PATH exists(saved model path)
-
-    DPRIOR_PATH = pretrained_model_path
-    RESUME = exists(DPRIOR_PATH)
-
-    if not RESUME:
-        tracker.init(
-            entity = wandb_entity,
-            project = wandb_project,
-            config = config
-        )
-
-    # Obtain the utilized device.
-
-    has_cuda = torch.cuda.is_available()
-    if has_cuda:
-        device = torch.device(f"cuda:{gpu_device}")
-        torch.cuda.set_device(device)
-
-    # Training loop
-    # diffusion prior network
-
-    prior_network = DiffusionPriorNetwork( 
-        dim = image_embed_dim,
-        depth = dpn_depth,
-        dim_head = dpn_dim_head,
-        heads = dpn_heads,
-        attn_dropout = dropout,
-        ff_dropout = dropout,
-        normformer = dp_normformer
-    )
-    
-    # Load clip model if text-conditioning
-    if dp_condition_on_text_encodings:
-        clip_adapter = OpenAIClipAdapter(clip)
+@click.option("--hfa", default=True)
+@click.option("--config_path", default="configs/prior.json")
+def main(hfa, config_path):
+    # start HFA if requested
+    if hfa:
+        accelerator = Accelerator()
     else:
-        clip_adapter = None
-        
-    # diffusion prior with text embeddings and image embeddings pre-computed
+        accelerator = None
 
-    diffusion_prior = DiffusionPrior( 
-        net = prior_network,
-        clip = clip_adapter,
-        image_embed_dim = image_embed_dim,
-        timesteps = dp_timesteps,
-        cond_drop_prob = dp_cond_drop_prob,
-        loss_type = dp_loss_type,
-        condition_on_text_encodings = dp_condition_on_text_encodings
-    )
+    # load the configuration file on main process
+    if not exists(accelerator) or accelerator.is_main_process:
+        click.secho(f"Loading configuration from {config_path}", fg="green")
 
-    # Load pre-trained model from DPRIOR_PATH
+    config = TrainDiffusionPriorConfig.from_json_path(config_path)
 
-    if RESUME:
-        diffusion_prior, loaded_obj = load_diffusion_model(DPRIOR_PATH, device)
-        tracker.init(entity = wandb_entity, project = wandb_project, config = config)
-
-    # diffusion prior trainer
-
-    trainer = DiffusionPriorTrainer(
-        diffusion_prior = diffusion_prior,
-        lr = learning_rate,
-        wd = weight_decay,
-        max_grad_norm = max_grad_norm,
-        amp = amp,
-    ).to(device)
-
-    # load optimizer and scaler
-
-    if RESUME:
-        trainer.optimizer.load_state_dict(loaded_obj['optimizer'])
-        trainer.scaler.load_state_dict(loaded_obj['scaler'])
-
-    # Create save_path if it doesn't exist
-
-    Path(save_path).mkdir(exist_ok = True, parents = True)
-
-    # Utilize wrapper to abstract away loader logic
-    print_ribbon("Downloading Embeddings")
-    loader_args = dict(text_conditioned=dp_condition_on_text_encodings, batch_size=batch_size, num_data_points=num_data_points,
-                       train_split=train_percent, eval_split=val_percent, device=device, img_url=image_embed_url)
-
-    if dp_condition_on_text_encodings:
-        loader_args = dict(**loader_args, meta_url=meta_url)
-    else:
-        loader_args = dict(**loader_args, txt_url=text_embed_url)
-
-    train_loader, eval_loader, test_loader = make_splits(**loader_args)
-
-    ### Training code ###
-
-    step = 1 
-    timer = Timer()
-    epochs = num_epochs
-
-    for _ in range(epochs):
-
-        for image, text in tqdm(train_loader):
-            
-            diffusion_prior.train()
-            
-            input_args = dict(image_embed=image)
-            if dp_condition_on_text_encodings:
-                input_args = dict(**input_args, text = text)
-            else:
-                input_args = dict(**input_args, text_embed=text)
-
-            loss = trainer(**input_args)
-
-            # Samples per second
-
-            samples_per_sec = batch_size * step / timer.elapsed()
-
-            # Save checkpoint every save_interval minutes
-            if(int(timer.elapsed()) >= 60 * save_interval):
-                timer.reset()
-
-                save_diffusion_model(
-                    save_path,
-                    diffusion_prior,
-                    trainer.optimizer,
-                    trainer.scaler,
-                    config,
-                    image_embed_dim)
-
-            # Log to wandb
-            tracker.log({"Training loss": loss,
-                        "Steps": step,
-                        "Samples per second": samples_per_sec})
-            # Log cosineSim(text_embed,predicted_image_embed) - cosineSim(text_embed,image_embed)
-            # Use NUM_TEST_EMBEDDINGS samples from the test set each time
-            # Get embeddings from the most recently saved model
-            if(step % REPORT_METRICS_EVERY) == 0:
-                report_cosine_sims(diffusion_prior, eval_loader, dp_condition_on_text_encodings)
-                ### Evaluate model(validation run) ###
-                eval_model(diffusion_prior, eval_loader, dp_condition_on_text_encodings, dp_loss_type, phase="Validation")
-
-            step += 1
-            trainer.update()
-
-    ### Test run ###
-    eval_model(diffusion_prior, test_loader, dp_condition_on_text_encodings, dp_loss_type, phase="Test")
+    # send config to get processed
+    initialize_training(config, accelerator)
 
 
 if __name__ == "__main__":
-    train()
+    main()