Problem with pytorch dataset.imageFolder with custom dataset in Google Colab - python-imaging-library

Question

I am trying to load a dataset for a classification task using pytorch, this is the code i use:
data_transforms = {
'train': transforms.Compose([
transforms.RandomRotation(2.8),
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize((0.5), (0.5))
]),
'valid': transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize((0.5), (0.5))
])
}
print(os.listdir())
# TODO: Load the datasets with ImageFolder
image_datasets = {x: datasets.ImageFolder(os.path.join("/content/drive/MyDrive/DatasetPersonale", x),
data_transforms[x])
for x in ['train', 'valid']}
# TODO: Using the image datasets and the trainforms, define the dataloaders
batch_size = 32
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=batch_size,
shuffle=True, num_workers=4)
for x in ['train', 'valid']}
class_names = image_datasets['train'].classes
print(class_names)
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'valid']}
the code worked fine but as my dataset was in grayscale, I needed to convert it to RGB so I used this code:
rootdir = '/content/drive/MyDrive/DatasetPersonale/trainRGB'
print("Train")
for subdir, dirs, files in os.walk(rootdir):
for file in files:
filePath = os.path.join(subdir, file)
name = os.path.basename(filePath)
img=Image.open(filePath, mode="r")
print(img.mode)
if img.mode != "RGB":
RGBimg=img.convert("RGB")
RGBimg.save(filePath,format=jpeg)
now my images are still jpeg, but now they are RGB and not L. the problem is that if I go to rerun the code to load the dataset I get this error
FileNotFoundError Traceback (most recent call last)
<ipython-input-15-3dace4b0f21b> in <module>()
19 image_datasets = {x: datasets.ImageFolder(os.path.join("/content/drive/MyDrive/DatasetPersonale", x),
20 data_transforms[x])
---> 21 for x in ['trainRGB', 'validRGB']}
22
23 # TODO: Using the image datasets and the trainforms, define the dataloaders
4 frames
<ipython-input-15-3dace4b0f21b> in <dictcomp>(.0)
19 image_datasets = {x: datasets.ImageFolder(os.path.join("/content/drive/MyDrive/DatasetPersonale", x),
20 data_transforms[x])
---> 21 for x in ['trainRGB', 'validRGB']}
22
23 # TODO: Using the image datasets and the trainforms, define the dataloaders
/usr/local/lib/python3.7/dist-packages/torchvision/datasets/folder.py in __init__(self, root, transform, target_transform, loader, is_valid_file)
311 transform=transform,
312 target_transform=target_transform,
--> 313 is_valid_file=is_valid_file)
314 self.imgs = self.samples
/usr/local/lib/python3.7/dist-packages/torchvision/datasets/folder.py in __init__(self, root, loader, extensions, transform, target_transform, is_valid_file)
144 target_transform=target_transform)
145 classes, class_to_idx = self.find_classes(self.root)
--> 146 samples = self.make_dataset(self.root, class_to_idx, extensions, is_valid_file)
147
148 self.loader = loader
/usr/local/lib/python3.7/dist-packages/torchvision/datasets/folder.py in make_dataset(directory, class_to_idx, extensions, is_valid_file)
190 "The class_to_idx parameter cannot be None."
191 )
--> 192 return make_dataset(directory, class_to_idx, extensions=extensions, is_valid_file=is_valid_file)
193
194 def find_classes(self, directory: str) -> Tuple[List[str], Dict[str, int]]:
/usr/local/lib/python3.7/dist-packages/torchvision/datasets/folder.py in make_dataset(directory, class_to_idx, extensions, is_valid_file)
100 if extensions is not None:
101 msg += f"Supported extensions are: {', '.join(extensions)}"
--> 102 raise FileNotFoundError(msg)
103
104 return instances
FileNotFoundError: Found no valid file for the classes .ipynb_checkpoints. Supported extensions are: .jpg, .jpeg, .png, .ppm, .bmp, .pgm, .tif, .tiff, .webp
Does someone know why this error appears? I checked the extension of all the files and they are jpeg.
Thank you.

Answer 1

Problem: This is because of .ipynb_checkpoints folder inside the folder /content/drive/MyDrive/DatasetPersonale/trainRGB which contains files (invalid images) cannot be read as images that have valid extensions (.jpg, .jpeg, .png, .ppm, .bmp, .pgm, .tif, .tiff, .webp).
Solution: You can save all your images in a subfolder namely 'images' and then change your root folder to /content/drive/MyDrive/DatasetPersonale/trainRGB/images to avoid reading the .ipynb_checkpoints folder with your images.