03_pytorch_computer_vision.ipynb crossEntropyLoss()

[Jiammmmmin]

it seems that I need to convert the `y` to `torch.tensor(y)`, but it does not help. Anyone else having the same problem as me?

[rithvikshetty]

Try doing it with torch.tensor(y).type(torch.LongTensor)

[mrdbourke]

Hi @Jiammmmmin ,

How did you go with this?

I was just able to run the example notebook with no issues, see here: https://www.learnpytorch.io/03_pytorch_computer_vision/

Did you perhaps check your dataloader code?

Example:

from torch.utils.data import DataLoader

# Setup the batch size hyperparameter
BATCH_SIZE = 32

# Turn datasets into iterables (batches)
train_dataloader = DataLoader(train_data, # dataset to turn into iterable
    batch_size=BATCH_SIZE, # how many samples per batch? 
    shuffle=True # shuffle data every epoch?
)

test_dataloader = DataLoader(test_data,
    batch_size=BATCH_SIZE,
    shuffle=False # don't necessarily have to shuffle the testing data
)

# Let's check out what we've created
print(f"Dataloaders: {train_dataloader, test_dataloader}") 
print(f"Length of train dataloader: {len(train_dataloader)} batches of {BATCH_SIZE}")
print(f"Length of test dataloader: {len(test_dataloader)} batches of {BATCH_SIZE}")

Or your loss_fn code?

What happens when you run print(y)?