运行Huggingface Diffuser教程时遇NameError错误求助

我在学习Huggingface Diffusers基础训练教程时，运行训练代码出现以下错误：

╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ in <cell line: 5>:5                                                                              │
│                                                                                                  │
│ /usr/local/lib/python3.10/dist-packages/accelerate/launchers.py:103 in notebook_launcher         │
│                                                                                                  │
│   100 │   │   │   print("Launching training on one GPU.")                                        │
│   101 │   │   else:                                                                              │
│   102 │   │   │   print("Launching training on one CPU.")                                        │
│ ❱ 103 │   │   function(*args)                                                                    │
│   104 │   else:                                                                                  │
│   105 │   │   if num_processes is None:                                                          │
│   106 │   │   │   raise ValueError(                                                              │
│ in train_loop:28                                                                                 │
│ in get_full_repo_name:13                                                                         │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
NameError: name '{myusername}' is not defined

我尝试在代码中插入个人用户名但未解决，相关代码如下：

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",
        logging_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)

这个错误是因为whoami(token)["name"]无法正确获取你的Hugging Face用户名，或者你未完成Hub登录，以下是三种解决方式：

1. 手动指定用户名（最直接） #

修改get_full_repo_name函数，直接替换为你的Hugging Face用户名，跳过自动获取逻辑：

def get_full_repo_name(model_id: str, organization: str = None, token: str = None):
    # 替换成你的Hugging Face用户名
    username = "你的HF用户名"
    if organization is None:
        return f"{username}/{model_id}"
    else:
        return f"{organization}/{model_id}"

2. 完成Hugging Face Hub登录 #

如果想保留自动获取逻辑，需要确保已登录Hub：

• 命令行登录：

huggingface-cli login

• 或者在代码中手动传入token：

from huggingface_hub import login
login(token="你的HF访问令牌")

登录后whoami(token)就能正确返回用户名信息。

3. 关闭推送到Hub的功能 #

如果暂时不需要将模型推送到Hub，可将config.push_to_hub设置为False，这样代码会跳过get_full_repo_name的调用，直接本地保存模型。

内容的提问来源于stack exchange，提问作者Gamma1