franciszchen
commented
4 years ago I see it, this is because of collate_fn mechanism. The reference can be found at https://stackoverflow.com/questions/52818145/why-pytorch-dataloader-behaves-differently-on-numpy-array-and-list.
In the RNN_train.py, assume s as 10, the out of getitem() in rnndata should be [10, 3, 224, 224] for each WSI.
In the dataloader, for the batch size of 128, the inputs in each loop of train_single() should be [128, 10, 3, 224, 224],
according to the code, the batch_size is 10 (it should be 128), and len(inputs) is 128 (it should be 10). These two variables are disordered. Just to verify this case.