move neural network creations off the configuration file into the pydantic classes

README.md

@@ -1077,6 +1077,8 @@ This library would not have gotten to this working state without the help of
 - [x] cross embed layers for downsampling, as an option
 - [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
 - [ ] 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
@@ -1086,12 +1088,9 @@ 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
-- [ ] 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)
 - [ ] 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

@@ -0,0 +1,99 @@
+{
+    "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,
+        "loss_type": "l2",
+        "beta_schedule": "cosine",
+        "learned_variance": true
+    },
+    "data": {
+        "webdataset_base_url": "pipe:s3cmd get s3://bucket/path/{}.tar -",
+        "embeddings_url": "s3://bucket/embeddings/path/",
+        "num_workers": 4,
+        "batch_size": 64,
+        "start_shard": 0,
+        "end_shard": 9999999,
+        "shard_width": 6,
+        "index_width": 4,
+        "splits": {
+            "train": 0.75,
+            "val": 0.15,
+            "test": 0.1
+        },
+        "shuffle_train": true,
+        "resample_train": false,
+        "preprocessing": {
+            "RandomResizedCrop": {
+                "size": [128, 128],
+                "scale": [0.75, 1.0],
+                "ratio": [1.0, 1.0]
+            },
+            "ToTensor": true
+        }
+    },
+    "train": {
+        "epochs": 20,
+        "lr": 1e-4,
+        "wd": 0.01,
+        "max_grad_norm": 0.5,
+        "save_every_n_samples": 100000,
+        "n_sample_images": 6,
+        "device": "cuda:0",
+        "epoch_samples": null,
+        "validation_samples": null,
+        "use_ema": true,
+        "ema_beta": 0.99,
+        "amp": false,
+        "save_all": false,
+        "save_latest": true,
+        "save_best": true,
+        "unet_training_mask": [true]
+    },
+    "evaluate": {
+        "n_evaluation_samples": 1000,
+        "FID": {
+            "feature": 64
+        },
+        "IS": {
+            "feature": 64,
+            "splits": 10
+        },
+        "KID": {
+            "feature": 64,
+            "subset_size": 10
+        },
+        "LPIPS": {
+            "net_type": "vgg",
+            "reduction": "mean"
+        }
+    },
+    "tracker": {
+        "tracker_type": "console",
+        "data_path": "./models",
+
+        "wandb_entity": "",
+        "wandb_project": "",
+
+        "verbose": false
+    },
+    "load": {
+        "source": null,
+
+        "run_path": "",
+        "file_path": "",
+
+        "resume": false
+    }
+}

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

@@ -1,16 +1,26 @@
+import json
 from torchvision import transforms as T
-from pydantic import BaseModel, validator
+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
+
+# 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 UnetConfig(BaseModel):
     dim: int
-    dim_mults: List[int]
+    dim_mults: ListOrTuple(int)
     image_embed_dim: int = None
     cond_dim: int = None
     channels: int = 3
@@ -21,14 +31,21 @@ 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
 
+    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):
         if exists(values.get('image_size')) ^ exists(image_sizes):
@@ -38,6 +55,17 @@ class DecoderConfig(BaseModel):
     class Config:
         extra = "allow"
 
+class TrainSplitConfig(BaseModel):
+    train: float = 0.75
+    val: float = 0.15
+    test: float = 0.1
+
+    @root_validator
+    def validate_all(cls, fields):
+        if sum([*fields.values()]) != 1.:
+            raise ValueError(f'{fields.keys()} must sum to 1.0')
+        return fields
+
 class DecoderDataConfig(BaseModel):
     webdataset_base_url: str     # path to a webdataset with jpg images
     embeddings_url: str          # path to .npy files with embeddings
@@ -47,32 +75,44 @@ class DecoderDataConfig(BaseModel):
     end_shard: int = 9999999
     shard_width: int = 6
     index_width: int = 4
-    splits: Dict[str, float] = {
-        'train': 0.75,
-        'val': 0.15,
-        'test': 0.1
-    }
+    splits: TrainSplitConfig
     shuffle_train: bool = True
     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
@@ -96,7 +136,6 @@ 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
@@ -104,18 +143,8 @@ class TrainDecoderConfig(BaseModel):
     tracker: TrackerConfig
     load: DecoderLoadConfig
 
-    @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)
+    @classmethod
+    def from_json_path(cls, json_path):
+        with open(json_path) as f:
+            config = json.load(f)
+        return cls(**config)

dalle2_pytorch/trainer.py

@@ -1,5 +1,6 @@
 import time
 import copy
+from pathlib import Path
 from math import ceil
 from functools import partial, wraps
 from collections.abc import Iterable
@@ -55,6 +56,10 @@ 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):
@@ -128,12 +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
@@ -191,7 +190,7 @@ class EMA(nn.Module):
         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.]))
+        self.register_buffer('step', torch.tensor([0]))
 
     def restore_ema_model_device(self):
         device = self.initted.device
@@ -287,7 +286,47 @@ class DiffusionPriorTrainer(nn.Module):
 
         self.max_grad_norm = max_grad_norm
 
-        self.register_buffer('step', torch.tensor([0.]))
+        self.register_buffer('step', torch.tensor([0]))
+
+    def save(self, path, overwrite = True):
+        path = Path(path)
+        assert not (path.exists() and not overwrite)
+        path.parent.mkdir(parents = True, exist_ok = True)
+
+        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()
+        )
+
+        if self.use_ema:
+            save_obj = {**save_obj, 'ema': self.ema_diffusion_prior.state_dict()}
+
+        torch.save(save_obj, str(path))
+
+    def load(self, path, only_model = False, strict = True):
+        path = Path(path)
+        assert path.exists()
+
+        loaded_obj = torch.load(str(path))
+
+        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()}')
+
+        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
+
+        self.scaler.load_state_dict(loaded_obj['scaler'])
+        self.optimizer.load_state_dict(loaded_obj['optimizer'])
+
+        if self.use_ema:
+            assert 'ema' in loaded_obj
+            self.ema_diffusion_prior.load_state_dict(loaded_obj['ema'], strict = strict)
 
     def update(self):
         if exists(self.max_grad_norm):
@@ -410,6 +449,57 @@ class DecoderTrainer(nn.Module):
 
         self.register_buffer('step', torch.tensor([0.]))
 
+    def save(self, path, overwrite = True):
+        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(),
+            step = self.step.item()
+        )
+
+        for ind in range(0, self.num_unets):
+            scaler_key = f'scaler{ind}'
+            optimizer_key = f'scaler{ind}'
+            scaler = getattr(self, scaler_key)
+            optimizer = getattr(self, optimizer_key)
+            save_obj = {**save_obj, scaler_key: scaler.state_dict(), optimizer_key: optimizer.state_dict()}
+
+        if self.use_ema:
+            save_obj = {**save_obj, 'ema': self.ema_unets.state_dict()}
+
+        torch.save(save_obj, str(path))
+
+    def load(self, path, only_model = False, strict = True):
+        path = Path(path)
+        assert path.exists()
+
+        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.step.copy_(torch.ones_like(self.step) * loaded_obj['step'])
+
+        if only_model:
+            return
+
+        for ind in range(0, self.num_unets):
+            scaler_key = f'scaler{ind}'
+            optimizer_key = f'scaler{ind}'
+            scaler = getattr(self, scaler_key)
+            optimizer = getattr(self, optimizer_key)
+
+            scaler.load_state_dict(loaded_obj[scaler_key])
+            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)
+
     @property
     def unets(self):
         return nn.ModuleList([ema.ema_model for ema in self.ema_unets])

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 = '0.4.0',
+  version = '0.4.8',
   license='MIT',
   description = 'DALL-E 2',
   author = 'Phil Wang',

train_decoder.py

@@ -1,11 +1,10 @@
 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 json
 import torchvision
 import torch
 from torchmetrics.image.fid import FrechetInceptionDistance
@@ -86,20 +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.
@@ -421,15 +406,15 @@ def initialize_training(config):
 
     dataloaders = create_dataloaders (
         available_shards=all_shards,
-        img_preproc = config.img_preproc,
-        train_prop = config.data["splits"]["train"],
-        val_prop = config.data["splits"]["val"],
-        test_prop = config.data["splits"]["test"],
+        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()
     )
 
-    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}")
@@ -449,9 +434,7 @@ def initialize_training(config):
 @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))
-    with open(config_file) as f:
-        config = json.load(f)
-    config = TrainDecoderConfig(**config)
+    config = TrainDecoderConfig.from_json_path(config_file)
     initialize_training(config)
 
 

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