Something wrong for CIFAR experiments about ganomaly

[samet-akcay]

I tried to replicate the error, but couldn't. By default the training data should be of size 45000, which is why the tensor size is 45000. Have you tried mnist? If so can you run python train.py --dataset cifar10?

[ybpaopao]

@samet-akcay Hi, I tried to run python train.py --dataset cifar10 as you mentioned. However, it raise the same problem as follows:

Training model Ganomaly.
0%| | 0/781 [00:00<?, ?it/s]Traceback (most recent call last):
File "train.py", line 47, in
main()
File "train.py", line 44, in main
model.train()
File "/media/yangbiao/disk1/ganomaly-master/lib/model.py", line 307, in train
self.train_epoch()
File "/media/yangbiao/disk1/ganomaly-master/lib/model.py", line 272, in train_epoch
for data in tqdm(self.dataloader['train'], leave=False, total=len(self.dataloader['train'])):
File "/usr/local/lib/python3.5/dist-packages/tqdm/_tqdm.py", line 719, in iter
for obj in iterable:
File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line 281, in next
return self._process_next_batch(batch)
File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line 301, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
IndexError: Traceback (most recent call last):
File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line 55, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line 55, in
samples = collate_fn([dataset[i] for i in batch_indices])
File "/usr/local/lib/python3.5/dist-packages/torchvision/datasets/cifar.py", line 83, in getitem
img, target = self.train_data[index], self.train_labels[index]
IndexError: index 48784 is out of bounds for axis 0 with size 45000
PS: The index number (all numbers are larger than 45000) changes every time when I run "run python train.py --dataset cifar10". I guess whether the problem is caused by the version issue of the third-part libraries, such as torchvision and tqdm? 3Q

[samet-akcay]

Maybe. I've used torchvision 0.1.9 and tqdm 4.15.0. Do you get any error when you run mnist?

[ybpaopao]

@samet-akcay Yes, I got the same errors when I run mnist. I will check the versions of torchvision and tqdm.

[ybpaopao]

@samet-akcay Hi, I'm glad to tell you that I can enjoy your code when I use torchvision 0.1.9 and tqdm 4.15.0. So, I think you can update your readme file to avoid such errors. ３Ｑ!