File size: 8,278 Bytes
82ebedf |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 |
from dataclasses import dataclass
NUM_TIMESTEPS = 50
@dataclass
class TrainingConfig:
image_size = 64 # the generated image resolution
train_batch_size = 16
eval_batch_size = 16 # how many images to sample during evaluation
num_epochs = 2000
gradient_accumulation_steps = 1
learning_rate = 1e-4
lr_warmup_steps = 500
save_image_epochs = 100
save_model_epochs = 300
mixed_precision = "fp16" # `no` for float32, `fp16` for automatic mixed precision
output_dir = "ddpm-rct" # the model name locally and on the HF Hub
push_to_hub = False # whether to upload the saved model to the HF Hub
hub_private_repo = False
overwrite_output_dir = True # overwrite the old model when re-running the notebook
seed = 0
config = TrainingConfig()
from datasets import load_dataset
config.dataset_name = "frutiemax/rct_dataset"
dataset = load_dataset(config.dataset_name, split="train[0:4]")
# import matplotlib.pyplot as plt
# fig, axs = plt.subplots(1, 4, figsize=(16, 4))
# for i, image in enumerate(dataset[:4]["image"]):
# axs[i].imshow(image)
# axs[i].set_axis_off()
# fig.show()
from torchvision import transforms
preprocess = transforms.Compose(
[
transforms.Resize((config.image_size, config.image_size)),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.5], [0.5]),
]
)
def transform(examples):
images = [preprocess(image.convert("RGB")) for image in examples["image"]]
return {"images": images}
dataset.set_transform(transform)
import torch
train_dataloader = torch.utils.data.DataLoader(dataset, batch_size=config.train_batch_size, shuffle=True)
from diffusers import UNet2DModel
model = UNet2DModel(
sample_size=config.image_size, # the target image resolution
in_channels=3, # the number of input channels, 3 for RGB images
out_channels=3, # the number of output channels
layers_per_block=2, # how many ResNet layers to use per UNet block
block_out_channels=(256, 256, 512, 512, 1024, 1024), # the number of output channels for each UNet block
down_block_types=(
"DownBlock2D", # a regular ResNet downsampling block
"DownBlock2D",
"DownBlock2D",
"DownBlock2D",
"AttnDownBlock2D", # a ResNet downsampling block with spatial self-attention
"DownBlock2D",
),
up_block_types=(
"UpBlock2D", # a regular ResNet upsampling block
"AttnUpBlock2D", # a ResNet upsampling block with spatial self-attention
"UpBlock2D",
"UpBlock2D",
"UpBlock2D",
"UpBlock2D",
),
)
sample_image = dataset[0]["images"].unsqueeze(0)
print("Input shape:", sample_image.shape)
print("Output shape:", model(sample_image, timestep=0).sample.shape)
import torch
from PIL import Image
from diffusers import DDPMScheduler
noise_scheduler = DDPMScheduler(num_train_timesteps=NUM_TIMESTEPS)
noise = torch.randn(sample_image.shape)
import torch.nn.functional as F
from diffusers.optimization import get_cosine_schedule_with_warmup
optimizer = torch.optim.AdamW(model.parameters(), lr=config.learning_rate)
lr_scheduler = get_cosine_schedule_with_warmup(
optimizer=optimizer,
num_warmup_steps=config.lr_warmup_steps,
num_training_steps=(len(train_dataloader) * config.num_epochs),
)
from diffusers import DDPMPipeline
from diffusers.utils import make_image_grid
import math
import os
def evaluate(config, epoch, pipeline):
# Sample some images from random noise (this is the backward diffusion process).
# The default pipeline output type is `List[PIL.Image]`
images = pipeline(
batch_size=config.eval_batch_size,
generator=torch.manual_seed(config.seed), num_inference_steps=NUM_TIMESTEPS
).images
# Make a grid out of the images
image_grid = make_image_grid(images, rows=4, cols=4)
# Save the images
test_dir = os.path.join(config.output_dir, "samples")
os.makedirs(test_dir, exist_ok=True)
image_grid.save(f"{test_dir}/{epoch:04d}.png")
from accelerate import Accelerator
from huggingface_hub import HfFolder, Repository, whoami
from tqdm.auto import tqdm
from pathlib import Path
import os
def get_full_repo_name(model_id: str, organization: str = None, token: str = None):
if token is None:
token = HfFolder.get_token()
if organization is None:
username = whoami(token)["name"]
return f"{username}/{model_id}"
else:
return f"{organization}/{model_id}"
def train_loop(config, model, noise_scheduler, optimizer, train_dataloader, lr_scheduler):
# Initialize accelerator and tensorboard logging
accelerator = Accelerator(
mixed_precision=config.mixed_precision,
gradient_accumulation_steps=config.gradient_accumulation_steps,
log_with="tensorboard",
project_dir=os.path.join(config.output_dir, "logs"),
)
if accelerator.is_main_process:
if config.push_to_hub:
repo_name = get_full_repo_name(Path(config.output_dir).name)
repo = Repository(config.output_dir, clone_from=repo_name)
elif config.output_dir is not None:
os.makedirs(config.output_dir, exist_ok=True)
accelerator.init_trackers("train_example")
# Prepare everything
# There is no specific order to remember, you just need to unpack the
# objects in the same order you gave them to the prepare method.
model, optimizer, train_dataloader, lr_scheduler = accelerator.prepare(
model, optimizer, train_dataloader, lr_scheduler
)
global_step = 0
# Now you train the model
for epoch in range(config.num_epochs):
progress_bar = tqdm(total=len(train_dataloader), disable=not accelerator.is_local_main_process)
progress_bar.set_description(f"Epoch {epoch}")
for step, batch in enumerate(train_dataloader):
clean_images = batch["images"]
# Sample noise to add to the images
noise = torch.randn(clean_images.shape).to(clean_images.device)
bs = clean_images.shape[0]
# Sample a random timestep for each image
timesteps = torch.randint(
0, noise_scheduler.config.num_train_timesteps, (bs,), device=clean_images.device
).long()
# Add noise to the clean images according to the noise magnitude at each timestep
# (this is the forward diffusion process)
noisy_images = noise_scheduler.add_noise(clean_images, noise, timesteps)
with accelerator.accumulate(model):
# Predict the noise residual
noise_pred = model(noisy_images, timesteps, return_dict=False)[0]
loss = F.mse_loss(noise_pred, noise)
accelerator.backward(loss)
accelerator.clip_grad_norm_(model.parameters(), 1.0)
optimizer.step()
lr_scheduler.step()
optimizer.zero_grad()
progress_bar.update(1)
logs = {"loss": loss.detach().item(), "lr": lr_scheduler.get_last_lr()[0], "step": global_step}
progress_bar.set_postfix(**logs)
accelerator.log(logs, step=global_step)
global_step += 1
# After each epoch you optionally sample some demo images with evaluate() and save the model
if accelerator.is_main_process:
pipeline = DDPMPipeline(unet=accelerator.unwrap_model(model), scheduler=noise_scheduler)
if (epoch + 1) % config.save_image_epochs == 0 or epoch == config.num_epochs - 1:
evaluate(config, epoch, pipeline)
if (epoch + 1) % config.save_model_epochs == 0 or epoch == config.num_epochs - 1:
if config.push_to_hub:
repo.push_to_hub(commit_message=f"Epoch {epoch}", blocking=True)
else:
pipeline.save_pretrained(config.output_dir)
from accelerate import notebook_launcher
args = (config, model, noise_scheduler, optimizer, train_dataloader, lr_scheduler)
notebook_launcher(train_loop, args, num_processes=1)
import glob
sample_images = sorted(glob.glob(f"{config.output_dir}/samples/*.png"))
Image.open(sample_images[-1]) |