Skip to content

Instantly share code, notes, and snippets.

Last active August 27, 2023 18:43
Star You must be signed in to star a gist
What would you like to do?
PyTorch Image File Paths With Dataset Dataloader
import torch
from torchvision import datasets
class ImageFolderWithPaths(datasets.ImageFolder):
"""Custom dataset that includes image file paths. Extends
# override the __getitem__ method. this is the method that dataloader calls
def __getitem__(self, index):
# this is what ImageFolder normally returns
original_tuple = super(ImageFolderWithPaths, self).__getitem__(index)
# the image file path
path = self.imgs[index][0]
# make a new tuple that includes original and the path
tuple_with_path = (original_tuple + (path,))
return tuple_with_path
# instantiate the dataset and dataloader
data_dir = "your/data_dir/here"
dataset = ImageFolderWithPaths(data_dir) # our custom dataset
dataloader = torch.utils.DataLoader(dataset)
# iterate over data
for inputs, labels, paths in dataloader:
# use the above variables freely
print(inputs, labels, paths)
Copy link

Thanks; hard to imagine that ImageFolder doesn't have this function / flag

Copy link

May I ask under what license this snippet is released?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment