【Hugging Face系列教程】Train a diffusion model 训练扩散模型【DDPM，最原始的diffusion版本】

from： https://huggingface.co/docs/diffusers/tutorials/basic_training#train-the-model

Hugging Face系列教程【手写代码】： https://github.com/huggingface/diffusion-models-class/blob/main/unit1/02_diffusion_models_from_scratch.ipynb

---

Training configuration 训练配置

from dataclasses import dataclass

@dataclass
class TrainingConfig:
    image_size = 128  # the generated image resolution
    train_batch_size = 16
    eval_batch_size = 16  # how many images to sample during evaluation
    num_epochs = 50
    gradient_accumulation_steps = 1
    learning_rate = 1e-4
    lr_warmup_steps = 500
    save_image_epochs = 10
    save_model_epochs = 30
    mixed_precision = "fp16"  # `no` for float32, `fp16` for automatic mixed precision
    output_dir = "ddpm-butterflies-128"  # the model name locally and on the HF Hub

    push_to_hub = True  # whether to upload the saved model to the HF Hub
    hub_model_id = "<your-username>/<my-awesome-model>"  # the name of the repository to create on the HF Hub
    hub_private_repo = False
    overwrite_output_dir = True  # overwrite the old model when re-running the notebook
    seed = 0


config = TrainingConfig()

图像可视化

import matplotlib.pyplot as plt

fig, axs = plt.subplots(1, 4, figsize=(16, 4))
for i, image in enumerate(dataset[:4]["image"]):  # BGR格式
    axs[i].imshow(image)
    axs[i].set_axis_off()
fig.show()

需要转化为 RGB格式 送入神经网络

在训练过程中，使用MySQLDatasets的set_transform方法动态应用 preprocess 函数：

def transform(examples):
    images = [preprocess(image.convert("RGB")) for image in examples["image"]]
    return {"images": images}


dataset.set_transform(transform)

定义模型：Create a UNet2DModel

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=(128, 128, 256, 256, 512, 512),  # 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",
    ),
)

快速检查样本图像形状是否与模型输出形状匹配通常是一个好主意：

sample_image = dataset[0]["images"].unsqueeze(0)
print("Input shape:", sample_image.shape)

print("Output shape:", model(sample_image, timestep=0).sample.shape)

DDPM 添加噪声

让我们来看看DDPM函数，并使用 add_noise 方法将一些随机噪声添加到之前的 sample_image 中：

import torch
from PIL import Image
from diffusers import DDPMScheduler

noise_scheduler = DDPMScheduler(num_train_timesteps=1000)
noise = torch.randn(sample_image.shape)
timesteps = torch.LongTensor([50])
noisy_image = noise_scheduler.add_noise(sample_image, noise, timesteps) 

Image.fromarray(((noisy_image.permute(0, 2, 3, 1) + 1.0) * 127.5).type(torch.uint8).numpy()[0]) # 转化为BGR格式显示

添加噪声后的图片显示：

训练模型

首先，你需要一个优化器和一个学习率调度器：

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),
)

现在，您可以使用TensorAccelerate将所有这些组件打包在一个训练循环中，以轻松实现TensorBoard日志记录、梯度累积和混合精度训练。🤗要将模型上传到Hub，编写一个函数来获取您的存储库名称和信息，然后将其推送到Hub。

from accelerate import Accelerator
from huggingface_hub import create_repo, upload_folder
from tqdm.auto import tqdm
from pathlib import Path
import os

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.output_dir is not None:
            os.makedirs(config.output_dir, exist_ok=True)
        if config.push_to_hub:
            repo_id = create_repo(
                repo_id=config.hub_model_id or Path(config.output_dir).name, exist_ok=True
            ).repo_id
        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, device=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,
                dtype=torch.int64
            )

            # 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:
                    upload_folder(
                        repo_id=repo_id,
                        folder_path=config.output_dir,
                        commit_message=f"Epoch {epoch}",
                        ignore_patterns=["step_*", "epoch_*"],
                    )
                else:
                    pipeline.save_pretrained(config.output_dir)

这是一段相当长的代码！但是，您🤗将训练循环、所有训练参数和进程数（您可以将此值更改为可用的GPU数）传递给函数以用于训练：

from accelerate import notebook_launcher

args = (config, model, noise_scheduler, optimizer, train_dataloader, lr_scheduler)

notebook_launcher(train_loop, args, num_processes=1)

结果展示

训练完成后，看看扩散模型生成的最终图像！

import glob

sample_images = sorted(glob.glob(f"{config.output_dir}/samples/*.png"))
Image.open(sample_images[-1])

后续精进