WZMIAOMIAO/deep-learning-for-image-processing · error · ValueError

image: {} isn't RGB mode.

Error message

image: {} isn't RGB mode.

What it means

The TensorBoard demo dataset opens each image with PIL and requires mode 'RGB'; any grayscale, palette, RGBA, or CMYK image raises ValueError including its path when __getitem__ is called. This guarantees the transformed tensor has 3 channels for the model and TensorBoard visualization.

Source

Thrown at pytorch_classification/tensorboard_test/my_dataset.py:35

            img = Image.open(img_path)
            w, h = img.size
            ratio = w / h
            if ratio > 10 or ratio < 0.1:
                delete_img.append(index)
                # print(img_path, ratio)

        for index in delete_img[::-1]:
            self.images_path.pop(index)
            self.images_class.pop(index)

    def __len__(self):
        return len(self.images_path)

    def __getitem__(self, item):
        img = Image.open(self.images_path[item])
        # RGB为彩色图片，L为灰度图片
        if img.mode != 'RGB':
            raise ValueError("image: {} isn't RGB mode.".format(self.images_path[item]))
        label = self.images_class[item]

        if self.transform is not None:
            img = self.transform(img)

        return img, label

    @staticmethod
    def collate_fn(batch):
        # 官方实现的default_collate可以参考
        # https://github.com/pytorch/pytorch/blob/67b7e751e6b5931a9f45274653f4f653a4e6cdf6/torch/utils/data/_utils/collate.py
        images, labels = tuple(zip(*batch))

        images = torch.stack(images, dim=0)
        labels = torch.as_tensor(labels)
        return images, labels

View on GitHub (pinned to 1ec3fe6f37)

Solutions

1. Add .convert('RGB') after Image.open so all images are normalized to RGB.
2. Pre-convert offending files to RGB JPEG/PNG before training.
3. Exclude non-RGB files when building the image list in __init__.

Example fix

// before
img = Image.open(self.images_path[item])
if img.mode != 'RGB':
    raise ValueError("image: {} isn't RGB mode.".format(self.images_path[item]))
// after
img = Image.open(self.images_path[item]).convert('RGB')

from PIL import Image
bad = [p for p in images_path if Image.open(p).mode != 'RGB']
if bad:
    raise ValueError(f"non-RGB images found: {bad}")

def is_rgb_image(path) -> bool:
    with Image.open(path) as img:
        return img.mode == 'RGB'

try:
    for images, labels in train_loader:
        ...  # train step
except ValueError as e:
    if "isn't RGB mode" in str(e):
        logging.error("convert to RGB: %s", e)
    raise

When it happens

Trigger: Iterating a DataLoader over a folder that contains an image whose PIL img.mode != 'RGB' (e.g. an 'L'-mode grayscale PNG among RGB JPEGs).

Common situations: Mixed-format test folders assembled for TensorBoard experiments, screenshots saved with alpha, images exported from tools defaulting to palette mode.

Related errors

• image: {} isn't RGB mode.
• image: {} isn't RGB mode.
• image: {} isn't RGB mode.
• dataset have {} classes, but input {}
• dataset have {} classes, but input {}

AI-assisted analysis of WZMIAOMIAO/deep-learning-for-image-processing@1ec3fe6f37 (2026-08-30). Data as JSON: /api/errors/dc7ab4e07880ef0a. Report an issue: GitHub.