allow for config driven creation of clip-less diffusion prior

block in a section that links to available pre-trained models for those who are interested

README.md

@@ -24,6 +24,11 @@ There was enough interest for a <a href="https://github.com/lucidrains/dalle2-ja
 
 *ongoing at 21k steps*
 
+## 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 🚧
+- DALL-E 2 🚧
+
 ## Install
 
 ```bash
@@ -1078,6 +1083,8 @@ This library would not have gotten to this working state without the help of
 - [x] use an experimental tracker agnostic setup, as done <a href="https://github.com/lucidrains/tf-bind-transformer#simple-trainer-class-for-fine-tuning">here</a>
 - [x] use pydantic for config drive training
 - [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
 - [ ] 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
@@ -1087,11 +1094,9 @@ This library would not have gotten to this working state without the help of
 - [ ] test out grid attention in cascading ddpm locally, decide whether to keep or remove
 - [ ] 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
-- [ ] 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
 - [ ] 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
-- [ ] for all model classes with hyperparameters that changes the network architecture, make it requirement that they must expose a config property, and write a simple function that asserts that it restores the object correctly
 - [ ] read the paper, figure it out, and build it https://github.com/lucidrains/DALLE2-pytorch/issues/89
 
 ## Citations

configs/README.md

@@ -6,9 +6,10 @@ For more complex configuration, we provide the option of using a configuration f
 
 The decoder trainer has 7 main configuration options. A full example of their use can be found in the [example decoder configuration](train_decoder_config.example.json).
 
-**<ins>Unets</ins>:**
+**<ins>Unet</ins>:**
+
+This is a single unet config, which belongs as an array nested under the decoder config as a list of `unets`
 
-Each member of this array defines a single unet that will be added to the decoder.
 | Option | Required | Default | Description |
 | ------ | -------- | ------- | ----------- |
 | `dim`  | Yes      | N/A     | The starting channels of the unet. |
@@ -22,6 +23,7 @@ Any parameter from the `Unet` constructor can also be given here.
 Defines the configuration options for the decoder model. The unets defined above will automatically be inserted.
 | Option | Required | Default | Description |
 | ------ | -------- | ------- | ----------- |
+| `unets` | Yes | N/A | A list of unets, using the configuration above |
 | `image_sizes` | Yes | N/A | The resolution of the image after each upsampling step. The length of this array should be the number of unets defined. |
 | `image_size` | Yes | N/A | Not used. Can be any number. |
 | `timesteps` | No | `1000` | The number of diffusion timesteps used for generation. |

configs/train_decoder_config.example.json

@@ -1,16 +1,16 @@
 {
-    "unets": [
-        {
-            "dim": 128,
-            "image_embed_dim": 768,
-            "cond_dim": 64,
-            "channels": 3,
-            "dim_mults": [1, 2, 4, 8],
-            "attn_dim_head": 32,
-            "attn_heads": 16
-        }
-    ],
     "decoder": {
+        "unets": [
+            {
+                "dim": 128,
+                "image_embed_dim": 768,
+                "cond_dim": 64,
+                "channels": 3,
+                "dim_mults": [1, 2, 4, 8],
+                "attn_dim_head": 32,
+                "attn_heads": 16
+            }
+        ],
         "image_sizes": [64],
         "channels": 3,
         "timesteps": 1000,

dalle2_pytorch/dalle2_pytorch.py

@@ -1712,7 +1712,7 @@ class Decoder(BaseGaussianDiffusion):
         self.unconditional = unconditional
         assert not (condition_on_text_encodings and unconditional), 'unconditional decoder image generation cannot be set to True if conditioning on text is present'
 
-        assert self.unconditional or (exists(clip) ^ exists(image_size)), 'either CLIP is supplied, or you must give the image_size and channels (usually 3 for RGB)'
+        assert self.unconditional or (exists(clip) ^ (exists(image_size) or exists(image_sizes))), 'either CLIP is supplied, or you must give the image_size and channels (usually 3 for RGB)'
 
         self.clip = None
         if exists(clip):
@@ -1728,7 +1728,7 @@ class Decoder(BaseGaussianDiffusion):
             self.clip_image_size = clip.image_size
             self.channels = clip.image_channels
         else:
-            self.clip_image_size = image_size
+            self.clip_image_size = default(image_size, lambda: image_sizes[-1])
             self.channels = channels
 
         self.condition_on_text_encodings = condition_on_text_encodings

dalle2_pytorch/train_configs.py

@@ -3,15 +3,61 @@ from torchvision import transforms as T
 from pydantic import BaseModel, validator, root_validator
 from typing import List, Iterable, Optional, Union, Tuple, Dict, Any
 
+from dalle2_pytorch.dalle2_pytorch import Unet, Decoder, DiffusionPrior, DiffusionPriorNetwork
+
+# helper functions
+
 def exists(val):
     return val is not None
 
 def default(val, d):
     return val if exists(val) else d
 
+def ListOrTuple(inner_type):
+    return Union[List[inner_type], Tuple[inner_type]]
+
+# pydantic classes
+
+class DiffusionPriorNetworkConfig(BaseModel):
+    dim: int
+    depth: int
+    num_timesteps: int = None
+    num_time_embeds: int = 1
+    num_image_embeds: int = 1
+    num_text_embeds: int = 1
+    dim_head: int = 64
+    heads: int = 8
+    ff_mult: int = 4
+    norm_out: bool = True
+    attn_dropout: float = 0.
+    ff_dropout: float = 0.
+    final_proj: bool = True
+    normformer: bool = False
+    rotary_emb: bool = True
+
+class DiffusionPriorConfig(BaseModel):
+    # only clip-less diffusion prior config for now
+    net: DiffusionPriorNetworkConfig
+    image_embed_dim: int
+    image_size: int
+    image_channels: int = 3
+    timesteps: int = 1000
+    cond_drop_prob: float = 0.
+    loss_type: str = 'l2'
+    predict_x_start: bool = True
+    beta_schedule: str = 'cosine'
+
+    def create(self):
+        kwargs = self.dict()
+        diffusion_prior_network = DiffusionPriorNetwork(**kwargs.pop('net'))
+        return DiffusionPrior(net = diffusion_prior_network, **kwargs)
+
+    class Config:
+        extra = "allow"
+
 class UnetConfig(BaseModel):
     dim: int
-    dim_mults: List[int]
+    dim_mults: ListOrTuple(int)
     image_embed_dim: int = None
     cond_dim: int = None
     channels: int = 3
@@ -22,13 +68,22 @@ class UnetConfig(BaseModel):
         extra = "allow"
 
 class DecoderConfig(BaseModel):
+    unets: Union[List[UnetConfig], Tuple[UnetConfig]]
     image_size: int = None
-    image_sizes: Union[List[int], Tuple[int]] = None
+    image_sizes: ListOrTuple(int) = None
     channels: int = 3
     timesteps: int = 1000
     loss_type: str = 'l2'
     beta_schedule: 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)
 
     @validator('image_sizes')
     def check_image_sizes(cls, image_sizes, values):
@@ -64,23 +119,39 @@ class DecoderDataConfig(BaseModel):
     resample_train: bool = False
     preprocessing: Dict[str, Any] = {'ToTensor': True}
 
+    @property
+    def img_preproc(self):
+        def _get_transformation(transformation_name, **kwargs):
+            if transformation_name == "RandomResizedCrop":
+                return T.RandomResizedCrop(**kwargs)
+            elif transformation_name == "RandomHorizontalFlip":
+                return T.RandomHorizontalFlip()
+            elif transformation_name == "ToTensor":
+                return T.ToTensor()
+
+        transforms = []
+        for transform_name, transform_kwargs_or_bool in self.preprocessing.items():
+            transform_kwargs = {} if not isinstance(transform_kwargs_or_bool, dict) else transform_kwargs_or_bool
+            transforms.append(_get_transformation(transform_name, **transform_kwargs))
+        return T.Compose(transforms)
+
 class DecoderTrainConfig(BaseModel):
     epochs: int = 20
     lr: float = 1e-4
     wd: float = 0.01
     max_grad_norm: 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
+    n_sample_images: int = 6                       # The number of example images to produce when sampling the train and test dataset
     device: str = 'cuda:0'
-    epoch_samples: int = None               # Limits the number of samples per epoch. None means no limit. Required if resample_train is true as otherwise the number of samples per epoch is infinite.
-    validation_samples: int = None          # Same as above but for validation.
+    epoch_samples: int = None                      # Limits the number of samples per epoch. None means no limit. Required if resample_train is true as otherwise the number of samples per epoch is infinite.
+    validation_samples: int = None                 # Same as above but for validation.
     use_ema: bool = True
     ema_beta: float = 0.99
     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: List[bool] = None   # If None, use all unets
+    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):
     n_evaluation_samples: int = 1000
@@ -104,7 +175,6 @@ class DecoderLoadConfig(BaseModel):
     resume: bool = False                    # If using wandb, whether to resume the run
 
 class TrainDecoderConfig(BaseModel):
-    unets: List[UnetConfig]
     decoder: DecoderConfig
     data: DecoderDataConfig
     train: DecoderTrainConfig
@@ -117,19 +187,3 @@ class TrainDecoderConfig(BaseModel):
         with open(json_path) as f:
             config = json.load(f)
         return cls(**config)
-
-    @property
-    def img_preproc(self):
-        def _get_transformation(transformation_name, **kwargs):
-            if transformation_name == "RandomResizedCrop":
-                return T.RandomResizedCrop(**kwargs)
-            elif transformation_name == "RandomHorizontalFlip":
-                return T.RandomHorizontalFlip()
-            elif transformation_name == "ToTensor":
-                return T.ToTensor()
-        
-        transforms = []
-        for transform_name, transform_kwargs_or_bool in self.data.preprocessing.items():
-            transform_kwargs = {} if not isinstance(transform_kwargs_or_bool, dict) else transform_kwargs_or_bool
-            transforms.append(_get_transformation(transform_name, **transform_kwargs))
-        return T.Compose(transforms)

dalle2_pytorch/trainer.py

@@ -133,12 +133,6 @@ 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)
 
-# print helpers
-
-def print_ribbon(s, symbol = '=', repeat = 40):
-    flank = symbol * repeat
-    return f'{flank} {s} {flank}'
-
 # saving and loading functions
 
 # for diffusion prior

dalle2_pytorch/utils.py

@@ -1,5 +1,7 @@
 import time
 
+# time helpers
+
 class Timer:
     def __init__(self):
         self.reset()
@@ -9,3 +11,9 @@ class Timer:
 
     def elapsed(self):
         return time.time() - self.last_time
+
+# print helpers
+
+def print_ribbon(s, symbol = '=', repeat = 40):
+    flank = symbol * repeat
+    return f'{flank} {s} {flank}'

setup.py

@@ -10,7 +10,7 @@ setup(
       'dream = dalle2_pytorch.cli:dream'
     ],
   },
-  version = '0.4.5',
+  version = '0.4.9',
   license='MIT',
   description = 'DALL-E 2',
   author = 'Phil Wang',

train_decoder.py

@@ -1,9 +1,9 @@
 from dalle2_pytorch import Unet, Decoder
-from dalle2_pytorch.trainer import DecoderTrainer, print_ribbon
+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.utils import Timer
+from dalle2_pytorch.utils import Timer, print_ribbon
 
 import torchvision
 import torch
@@ -85,20 +85,6 @@ def create_dataloaders(
         "test_sampling": test_sampling_dataloader
     }
 
-
-def create_decoder(device, decoder_config, unets_config):
-    """Creates a sample decoder"""
-
-    unets = [Unet(**config.dict()) for config in unets_config]
-
-    decoder = Decoder(
-        unet=unets,
-        **decoder_config.dict()
-    )
-
-    decoder.to(device=device)
-    return decoder
-
 def get_dataset_keys(dataloader):
     """
     It is sometimes neccesary to get the keys the dataloader is returning. Since the dataset is burried in the dataloader, we need to do a process to recover it.
@@ -420,7 +406,7 @@ def initialize_training(config):
 
     dataloaders = create_dataloaders (
         available_shards=all_shards,
-        img_preproc = config.img_preproc,
+        img_preproc = config.data.img_preproc,
         train_prop = config.data.splits.train,
         val_prop = config.data.splits.val,
         test_prop = config.data.splits.test,
@@ -428,7 +414,7 @@ def initialize_training(config):
         **config.data.dict()
     )
 
-    decoder = create_decoder(device, config.decoder, config.unets)
+    decoder = config.decoder.create().to(device = device)
     num_parameters = sum(p.numel() for p in decoder.parameters())
     print(print_ribbon("Loaded Config", repeat=40))
     print(f"Number of parameters: {num_parameters}")

train_diffusion_prior.py

@@ -9,10 +9,10 @@ from torch import nn
 
 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, print_ribbon
+from dalle2_pytorch.trainer import DiffusionPriorTrainer, load_diffusion_model, save_diffusion_model
 
 from dalle2_pytorch.trackers import ConsoleTracker, WandbTracker
-from dalle2_pytorch.utils import Timer
+from dalle2_pytorch.utils import Timer, print_ribbon
 
 from embedding_reader import EmbeddingReader