in train_instruct_pix2pix.py [0:0]
def main():
args = parse_args()
if args.non_ema_revision is not None:
deprecate(
"non_ema_revision!=None",
"0.15.0",
message=(
"Downloading 'non_ema' weights from revision branches of the Hub is deprecated. Please make sure to"
" use `--variant=non_ema` instead."
),
)
logging_dir = os.path.join(args.output_dir, args.logging_dir)
accelerator_project_config = ProjectConfiguration(
total_limit=args.checkpoints_total_limit, logging_dir=logging_dir
)
accelerator = Accelerator(
gradient_accumulation_steps=args.gradient_accumulation_steps,
mixed_precision=args.mixed_precision,
log_with=args.report_to,
project_config=accelerator_project_config,
)
generator = torch.Generator(device=accelerator.device).manual_seed(args.seed)
if args.report_to == "wandb":
if not is_wandb_available():
raise ImportError("Make sure to install wandb if you want to use it for logging during training.")
import wandb
# Make one log on every process with the configuration for debugging.
logging.basicConfig(
format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
datefmt="%m/%d/%Y %H:%M:%S",
level=logging.INFO,
)
logger.info(accelerator.state, main_process_only=False)
if accelerator.is_local_main_process:
datasets.utils.logging.set_verbosity_warning()
transformers.utils.logging.set_verbosity_warning()
diffusers.utils.logging.set_verbosity_info()
else:
datasets.utils.logging.set_verbosity_error()
transformers.utils.logging.set_verbosity_error()
diffusers.utils.logging.set_verbosity_error()
# If passed along, set the training seed now.
if args.seed is not None:
set_seed(args.seed)
# Handle the repository creation
if accelerator.is_main_process:
if args.push_to_hub:
if args.hub_model_id is None:
repo_name = get_full_repo_name(Path(args.output_dir).name, token=args.hub_token)
else:
repo_name = args.hub_model_id
create_repo(repo_name, exist_ok=True, token=args.hub_token)
repo = Repository(args.output_dir, clone_from=repo_name, token=args.hub_token)
with open(os.path.join(args.output_dir, ".gitignore"), "w+") as gitignore:
if "step_*" not in gitignore:
gitignore.write("step_*\n")
if "epoch_*" not in gitignore:
gitignore.write("epoch_*\n")
elif args.output_dir is not None:
os.makedirs(args.output_dir, exist_ok=True)
# Load scheduler, tokenizer and models.
noise_scheduler = DDPMScheduler.from_pretrained(args.pretrained_model_name_or_path, subfolder="scheduler")
tokenizer = CLIPTokenizer.from_pretrained(
args.pretrained_model_name_or_path, subfolder="tokenizer", revision=args.revision
)
text_encoder = CLIPTextModel.from_pretrained(
args.pretrained_model_name_or_path, subfolder="text_encoder", revision=args.revision
)
vae = AutoencoderKL.from_pretrained(args.pretrained_model_name_or_path, subfolder="vae", revision=args.revision)
unet = UNet2DConditionModel.from_pretrained(
args.pretrained_model_name_or_path, subfolder="unet", revision=args.non_ema_revision
)
# InstructPix2Pix uses an additional image for conditioning. To accommodate that,
# it uses 8 channels (instead of 4) in the first (conv) layer of the UNet. This UNet is
# then fine-tuned on the custom InstructPix2Pix dataset. This modified UNet is initialized
# from the pre-trained checkpoints. For the extra channels added to the first layer, they are
# initialized to zero.
if accelerator.is_main_process:
logger.info("Initializing the InstructPix2Pix UNet from the pretrained UNet.")
in_channels = 8
out_channels = unet.conv_in.out_channels
unet.register_to_config(in_channels=in_channels)
with torch.no_grad():
new_conv_in = nn.Conv2d(
in_channels, out_channels, unet.conv_in.kernel_size, unet.conv_in.stride, unet.conv_in.padding
)
new_conv_in.weight.zero_()
new_conv_in.weight[:, :4, :, :].copy_(unet.conv_in.weight)
unet.conv_in = new_conv_in
# Freeze vae and text_encoder
vae.requires_grad_(False)
text_encoder.requires_grad_(False)
# Create EMA for the unet.
if args.use_ema:
ema_unet = EMAModel(unet.parameters(), model_cls=UNet2DConditionModel, model_config=unet.config)
if args.enable_xformers_memory_efficient_attention:
if is_xformers_available():
import xformers
xformers_version = version.parse(xformers.__version__)
if xformers_version == version.parse("0.0.16"):
logger.warn(
"xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
)
unet.enable_xformers_memory_efficient_attention()
else:
raise ValueError("xformers is not available. Make sure it is installed correctly")
# `accelerate` 0.16.0 will have better support for customized saving
if version.parse(accelerate.__version__) >= version.parse("0.16.0"):
# create custom saving & loading hooks so that `accelerator.save_state(...)` serializes in a nice format
def save_model_hook(models, weights, output_dir):
if args.use_ema:
ema_unet.save_pretrained(os.path.join(output_dir, "unet_ema"))
for i, model in enumerate(models):
model.save_pretrained(os.path.join(output_dir, "unet"))
# make sure to pop weight so that corresponding model is not saved again
weights.pop()
def load_model_hook(models, input_dir):
if args.use_ema:
load_model = EMAModel.from_pretrained(os.path.join(input_dir, "unet_ema"), UNet2DConditionModel)
ema_unet.load_state_dict(load_model.state_dict())
ema_unet.to(accelerator.device)
del load_model
for i in range(len(models)):
# pop models so that they are not loaded again
model = models.pop()
# load diffusers style into model
load_model = UNet2DConditionModel.from_pretrained(input_dir, subfolder="unet")
model.register_to_config(**load_model.config)
model.load_state_dict(load_model.state_dict())
del load_model
accelerator.register_save_state_pre_hook(save_model_hook)
accelerator.register_load_state_pre_hook(load_model_hook)
if args.gradient_checkpointing:
unet.enable_gradient_checkpointing()
# Enable TF32 for faster training on Ampere GPUs,
# cf https://pytorch.org/docs/stable/notes/cuda.html#tensorfloat-32-tf32-on-ampere-devices
if args.allow_tf32:
torch.backends.cuda.matmul.allow_tf32 = True
if args.scale_lr:
args.learning_rate = (
args.learning_rate * args.gradient_accumulation_steps * args.train_batch_size * accelerator.num_processes
)
# Initialize the optimizer
if args.use_8bit_adam:
try:
import bitsandbytes as bnb
except ImportError:
raise ImportError(
"Please install bitsandbytes to use 8-bit Adam. You can do so by running `pip install bitsandbytes`"
)
optimizer_cls = bnb.optim.AdamW8bit
else:
optimizer_cls = torch.optim.AdamW
optimizer = optimizer_cls(
unet.parameters(),
lr=args.learning_rate,
betas=(args.adam_beta1, args.adam_beta2),
weight_decay=args.adam_weight_decay,
eps=args.adam_epsilon,
)
# Get the datasets: you can either provide your own training and evaluation files (see below)
# or specify a Dataset from the hub (the dataset will be downloaded automatically from the datasets Hub).
# In distributed training, the load_dataset function guarantees that only one local process can concurrently
# download the dataset.
if args.dataset_name is not None:
# Downloading and loading a dataset from the hub.
dataset = load_dataset(
args.dataset_name,
args.dataset_config_name,
cache_dir=args.cache_dir,
)
else:
data_files = {}
if args.train_data_dir is not None:
data_files["train"] = os.path.join(args.train_data_dir, "**")
dataset = load_dataset(
"imagefolder",
data_files=data_files,
cache_dir=args.cache_dir,
)
# See more about loading custom images at
# https://huggingface.co/docs/datasets/main/en/image_load#imagefolder
# Preprocessing the datasets.
# We need to tokenize inputs and targets.
column_names = dataset["train"].column_names
# 6. Get the column names for input/target.
dataset_columns = DATASET_NAME_MAPPING.get(args.dataset_name, None)
if args.original_image_column is None:
original_image_column = dataset_columns[0] if dataset_columns is not None else column_names[0]
else:
original_image_column = args.original_image_column
if original_image_column not in column_names:
raise ValueError(
f"--original_image_column' value '{args.original_image_column}' needs to be one of: {', '.join(column_names)}"
)
if args.edit_prompt_column is None:
edit_prompt_column = dataset_columns[1] if dataset_columns is not None else column_names[1]
else:
edit_prompt_column = args.edit_prompt_column
if edit_prompt_column not in column_names:
raise ValueError(
f"--edit_prompt_column' value '{args.edit_prompt_column}' needs to be one of: {', '.join(column_names)}"
)
if args.edited_image_column is None:
edited_image_column = dataset_columns[2] if dataset_columns is not None else column_names[2]
else:
edited_image_column = args.edited_image_column
if edited_image_column not in column_names:
raise ValueError(
f"--edited_image_column' value '{args.edited_image_column}' needs to be one of: {', '.join(column_names)}"
)
# Preprocessing the datasets.
# We need to tokenize input captions and transform the images.
def tokenize_captions(captions):
inputs = tokenizer(
captions, max_length=tokenizer.model_max_length, padding="max_length", truncation=True, return_tensors="pt"
)
return inputs.input_ids
# Preprocessing the datasets.
train_transforms = transforms.Compose(
[
transforms.CenterCrop(args.resolution) if args.center_crop else transforms.RandomCrop(args.resolution),
transforms.RandomHorizontalFlip() if args.random_flip else transforms.Lambda(lambda x: x),
]
)
def preprocess_images(examples):
original_images = np.concatenate(
[convert_to_np(image, args.resolution) for image in examples[original_image_column]]
)
edited_images = np.concatenate(
[convert_to_np(image, args.resolution) for image in examples[edited_image_column]]
)
# We need to ensure that the original and the edited images undergo the same
# augmentation transforms.
images = np.concatenate([original_images, edited_images])
images = torch.tensor(images)
images = 2 * (images / 255) - 1
return train_transforms(images)
def preprocess_train(examples):
# Preprocess images.
preprocessed_images = preprocess_images(examples)
# Since the original and edited images were concatenated before
# applying the transformations, we need to separate them and reshape
# them accordingly.
original_images, edited_images = preprocessed_images.chunk(2)
original_images = original_images.reshape(-1, 3, args.resolution, args.resolution)
edited_images = edited_images.reshape(-1, 3, args.resolution, args.resolution)
# Collate the preprocessed images into the `examples`.
examples["original_pixel_values"] = original_images
examples["edited_pixel_values"] = edited_images
# Preprocess the captions.
captions = [caption for caption in examples[edit_prompt_column]]
examples["input_ids"] = tokenize_captions(captions)
return examples
with accelerator.main_process_first():
if args.max_train_samples is not None:
dataset["train"] = dataset["train"].shuffle(seed=args.seed).select(range(args.max_train_samples))
# Set the training transforms
train_dataset = dataset["train"].with_transform(preprocess_train)
def collate_fn(examples):
original_pixel_values = torch.stack([example["original_pixel_values"] for example in examples])
original_pixel_values = original_pixel_values.to(memory_format=torch.contiguous_format).float()
edited_pixel_values = torch.stack([example["edited_pixel_values"] for example in examples])
edited_pixel_values = edited_pixel_values.to(memory_format=torch.contiguous_format).float()
input_ids = torch.stack([example["input_ids"] for example in examples])
return {
"original_pixel_values": original_pixel_values,
"edited_pixel_values": edited_pixel_values,
"input_ids": input_ids,
}
# DataLoaders creation:
train_dataloader = torch.utils.data.DataLoader(
train_dataset,
shuffle=True,
collate_fn=collate_fn,
batch_size=args.train_batch_size,
num_workers=args.dataloader_num_workers,
)
# Scheduler and math around the number of training steps.
overrode_max_train_steps = False
num_update_steps_per_epoch = math.ceil(len(train_dataloader) / args.gradient_accumulation_steps)
if args.max_train_steps is None:
args.max_train_steps = args.num_train_epochs * num_update_steps_per_epoch
overrode_max_train_steps = True
lr_scheduler = get_scheduler(
args.lr_scheduler,
optimizer=optimizer,
num_warmup_steps=args.lr_warmup_steps * args.gradient_accumulation_steps,
num_training_steps=args.max_train_steps * args.gradient_accumulation_steps,
)
# Prepare everything with our `accelerator`.
unet, optimizer, train_dataloader, lr_scheduler = accelerator.prepare(
unet, optimizer, train_dataloader, lr_scheduler
)
if args.use_ema:
ema_unet.to(accelerator.device)
# For mixed precision training we cast the text_encoder and vae weights to half-precision
# as these models are only used for inference, keeping weights in full precision is not required.
weight_dtype = torch.float32
if accelerator.mixed_precision == "fp16":
weight_dtype = torch.float16
elif accelerator.mixed_precision == "bf16":
weight_dtype = torch.bfloat16
# Move text_encode and vae to gpu and cast to weight_dtype
text_encoder.to(accelerator.device, dtype=weight_dtype)
vae.to(accelerator.device, dtype=weight_dtype)
# We need to recalculate our total training steps as the size of the training dataloader may have changed.
num_update_steps_per_epoch = math.ceil(len(train_dataloader) / args.gradient_accumulation_steps)
if overrode_max_train_steps:
args.max_train_steps = args.num_train_epochs * num_update_steps_per_epoch
# Afterwards we recalculate our number of training epochs
args.num_train_epochs = math.ceil(args.max_train_steps / num_update_steps_per_epoch)
# We need to initialize the trackers we use, and also store our configuration.
# The trackers initializes automatically on the main process.
if accelerator.is_main_process:
accelerator.init_trackers("instruct-pix2pix", config=vars(args))
# Train!
total_batch_size = args.train_batch_size * accelerator.num_processes * args.gradient_accumulation_steps
logger.info("***** Running training *****")
logger.info(f" Num examples = {len(train_dataset)}")
logger.info(f" Num Epochs = {args.num_train_epochs}")
logger.info(f" Instantaneous batch size per device = {args.train_batch_size}")
logger.info(f" Total train batch size (w. parallel, distributed & accumulation) = {total_batch_size}")
logger.info(f" Gradient Accumulation steps = {args.gradient_accumulation_steps}")
logger.info(f" Total optimization steps = {args.max_train_steps}")
global_step = 0
first_epoch = 0
# Potentially load in the weights and states from a previous save
if args.resume_from_checkpoint:
if args.resume_from_checkpoint != "latest":
path = os.path.basename(args.resume_from_checkpoint)
else:
# Get the most recent checkpoint
dirs = os.listdir(args.output_dir)
dirs = [d for d in dirs if d.startswith("checkpoint")]
dirs = sorted(dirs, key=lambda x: int(x.split("-")[1]))
path = dirs[-1] if len(dirs) > 0 else None
if path is None:
accelerator.print(
f"Checkpoint '{args.resume_from_checkpoint}' does not exist. Starting a new training run."
)
args.resume_from_checkpoint = None
else:
accelerator.print(f"Resuming from checkpoint {path}")
accelerator.load_state(os.path.join(args.output_dir, path))
global_step = int(path.split("-")[1])
resume_global_step = global_step * args.gradient_accumulation_steps
first_epoch = global_step // num_update_steps_per_epoch
resume_step = resume_global_step % (num_update_steps_per_epoch * args.gradient_accumulation_steps)
# Only show the progress bar once on each machine.
progress_bar = tqdm(range(global_step, args.max_train_steps), disable=not accelerator.is_local_main_process)
progress_bar.set_description("Steps")
for epoch in range(first_epoch, args.num_train_epochs):
unet.train()
train_loss = 0.0
for step, batch in enumerate(train_dataloader):
# Skip steps until we reach the resumed step
if args.resume_from_checkpoint and epoch == first_epoch and step < resume_step:
if step % args.gradient_accumulation_steps == 0:
progress_bar.update(1)
continue
with accelerator.accumulate(unet):
# We want to learn the denoising process w.r.t the edited images which
# are conditioned on the original image (which was edited) and the edit instruction.
# So, first, convert images to latent space.
latents = vae.encode(batch["edited_pixel_values"].to(weight_dtype)).latent_dist.sample()
latents = latents * vae.config.scaling_factor
# Sample noise that we'll add to the latents
noise = torch.randn_like(latents)
bsz = latents.shape[0]
# Sample a random timestep for each image
timesteps = torch.randint(0, noise_scheduler.num_train_timesteps, (bsz,), device=latents.device)
timesteps = timesteps.long()
# Add noise to the latents according to the noise magnitude at each timestep
# (this is the forward diffusion process)
noisy_latents = noise_scheduler.add_noise(latents, noise, timesteps)
# Get the text embedding for conditioning.
encoder_hidden_states = text_encoder(batch["input_ids"])[0]
# Get the additional image embedding for conditioning.
# Instead of getting a diagonal Gaussian here, we simply take the mode.
original_image_embeds = vae.encode(batch["original_pixel_values"].to(weight_dtype)).latent_dist.mode()
# Conditioning dropout to support classifier-free guidance during inference. For more details
# check out the section 3.2.1 of the original paper https://arxiv.org/abs/2211.09800.
if args.conditioning_dropout_prob is not None:
random_p = torch.rand(bsz, device=latents.device, generator=generator)
# Sample masks for the edit prompts.
prompt_mask = random_p < 2 * args.conditioning_dropout_prob
prompt_mask = prompt_mask.reshape(bsz, 1, 1)
# Final text conditioning.
null_conditioning = text_encoder(tokenize_captions([""]).to(accelerator.device))[0]
encoder_hidden_states = torch.where(prompt_mask, null_conditioning, encoder_hidden_states)
# Sample masks for the original images.
image_mask_dtype = original_image_embeds.dtype
image_mask = 1 - (
(random_p >= args.conditioning_dropout_prob).to(image_mask_dtype)
* (random_p < 3 * args.conditioning_dropout_prob).to(image_mask_dtype)
)
image_mask = image_mask.reshape(bsz, 1, 1, 1)
# Final image conditioning.
original_image_embeds = image_mask * original_image_embeds
# Concatenate the `original_image_embeds` with the `noisy_latents`.
concatenated_noisy_latents = torch.cat([noisy_latents, original_image_embeds], dim=1)
# Get the target for loss depending on the prediction type
if noise_scheduler.config.prediction_type == "epsilon":
target = noise
elif noise_scheduler.config.prediction_type == "v_prediction":
target = noise_scheduler.get_velocity(latents, noise, timesteps)
else:
raise ValueError(f"Unknown prediction type {noise_scheduler.config.prediction_type}")
# Predict the noise residual and compute loss
model_pred = unet(concatenated_noisy_latents, timesteps, encoder_hidden_states).sample
loss = F.mse_loss(model_pred.float(), target.float(), reduction="mean")
# Gather the losses across all processes for logging (if we use distributed training).
avg_loss = accelerator.gather(loss.repeat(args.train_batch_size)).mean()
train_loss += avg_loss.item() / args.gradient_accumulation_steps
# Backpropagate
accelerator.backward(loss)
if accelerator.sync_gradients:
accelerator.clip_grad_norm_(unet.parameters(), args.max_grad_norm)
optimizer.step()
lr_scheduler.step()
optimizer.zero_grad()
# Checks if the accelerator has performed an optimization step behind the scenes
if accelerator.sync_gradients:
if args.use_ema:
ema_unet.step(unet.parameters())
progress_bar.update(1)
global_step += 1
accelerator.log({"train_loss": train_loss}, step=global_step)
train_loss = 0.0
if global_step % args.checkpointing_steps == 0:
if accelerator.is_main_process:
save_path = os.path.join(args.output_dir, f"checkpoint-{global_step}")
accelerator.save_state(save_path)
logger.info(f"Saved state to {save_path}")
logs = {"step_loss": loss.detach().item(), "lr": lr_scheduler.get_last_lr()[0]}
progress_bar.set_postfix(**logs)
if global_step >= args.max_train_steps:
break
if accelerator.is_main_process:
if (
(args.val_image_url is not None)
and (args.validation_prompt is not None)
and (epoch % args.validation_epochs == 0)
):
logger.info(
f"Running validation... \n Generating {args.num_validation_images} images with prompt:"
f" {args.validation_prompt}."
)
# create pipeline
if args.use_ema:
# Store the UNet parameters temporarily and load the EMA parameters to perform inference.
ema_unet.store(unet.parameters())
ema_unet.copy_to(unet.parameters())
pipeline = StableDiffusionInstructPix2PixPipeline.from_pretrained(
args.pretrained_model_name_or_path,
unet=unet,
revision=args.revision,
torch_dtype=weight_dtype,
)
pipeline = pipeline.to(accelerator.device)
pipeline.set_progress_bar_config(disable=True)
# run inference
original_image = download_image(args.val_image_url)
edited_images = []
with torch.autocast(str(accelerator.device), enabled=accelerator.mixed_precision == "fp16"):
for _ in range(args.num_validation_images):
edited_images.append(
pipeline(
args.validation_prompt,
image=original_image,
num_inference_steps=20,
image_guidance_scale=1.5,
guidance_scale=7,
generator=generator,
).images[0]
)
for tracker in accelerator.trackers:
if tracker.name == "wandb":
wandb_table = wandb.Table(columns=WANDB_TABLE_COL_NAMES)
for edited_image in edited_images:
wandb_table.add_data(
wandb.Image(original_image), wandb.Image(edited_image), args.validation_prompt
)
tracker.log({"validation": wandb_table})
if args.use_ema:
# Switch back to the original UNet parameters.
ema_unet.restore(unet.parameters())
del pipeline
torch.cuda.empty_cache()
# Create the pipeline using the trained modules and save it.
accelerator.wait_for_everyone()
if accelerator.is_main_process:
unet = accelerator.unwrap_model(unet)
if args.use_ema:
ema_unet.copy_to(unet.parameters())
pipeline = StableDiffusionInstructPix2PixPipeline.from_pretrained(
args.pretrained_model_name_or_path,
text_encoder=accelerator.unwrap_model(text_encoder),
vae=accelerator.unwrap_model(vae),
unet=unet,
revision=args.revision,
)
pipeline.save_pretrained(args.output_dir)
if args.push_to_hub:
repo.push_to_hub(commit_message="End of training", blocking=False, auto_lfs_prune=True)
accelerator.end_training()