Error in PyTorch DataLoder

[MostafaMagdSalama]

i got this error when i train a model (srgan)

KeyError: Caught KeyError in DataLoader worker process 0. Original Traceback (most recent call last): File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop data = fetcher.fetch(index) File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/_utils/fetch.py", line 44, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/content/drive/My Drive/PyTorch--master/datasets.py", line 67, in getitem img = Image.open(self.images[i], mode='r') KeyError: 0 how how many epoch i should do to make a good model? i'm training the model in google colab thanks

[goudantongxue]

for d in train_folders:
    for i in os.listdir(d):
        img_path = os.path.join(d, i)
        img = Image.open(img_path, mode='r')
        if img.width >= min_size and img.height >= min_size:
            train_images.append(img_path)

there is something wrong. For the first line, train folders is a string and so for d in train_folders doesn't work.

[goudantongxue]

for d in train_folders:
    for i in os.listdir(d):
        img_path = os.path.join(d, i)
        img = Image.open(img_path, mode='r')
        if img.width >= min_size and img.height >= min_size:
            train_images.append(img_path)

there is something wrong. For the first line, train folders is a string and so for d in train_folders doesn't works.

Sorry, now i know that d is a list. hahaha

[JIAZhenZ]

How can I download the training datasets? thanks

[lucidBrot]

@JIAZhenZ when you search (CTRLF) in the readme for "download", you will find:

Model checkpoints are available here.

While the authors of the paper trained their models on a 350k-image subset of the ImageNet data, I simply used about 120k COCO images (train2014 and val2014 folders). They're a lot easier to obtain. If you wish to do the same, you can download them from the links listed in my other tutorial.

So: [ training direct link ], [validation direct link]