Getting an error.

[ayushg647]

KeyError: 'You have to pass data to augmentations as named arguments, for example: aug(image=image)'

Got this error when implementing the statement "for X_test, y_test in test_dataloader:" in the testing loop., while making the computer vision model on the fashion dataset according to the tutorial.
How to rectify the error...

[mrdbourke]

Hi @ayushg647 ,

It's a bit hard to troubleshoot your error without seeing your code.

What have you tried so far?

Have you tried to reference the code here: https://www.learnpytorch.io/03_pytorch_computer_vision/

You could compare your code to that in the notebook and see if you're doing the right steps.

[mrdbourke]

Hmm, I'm not sure what might be happening here.

I just ran all of the code in notebook 03 and it worked for me.

Do you mind sharing your code and showing me where the error is coming from?

[ayushg647]

Import tqdm for progress bar

from tqdm.auto import tqdm

Set the seed and start the timer

torch.manual_seed(42)
train_time_start_on_cpu = timer()

Set the number of epochs (we'll keep this small for faster training times)

epochs = 3

Create training and testing loop

for epoch in tqdm(range(epochs)):
print(f"Epoch: {epoch}\n-------")
### Training
train_loss = 0
# Add a loop to loop through training batches
for batch, (X, y) in enumerate(train_dataloader):
model_0.train()
# 1. Forward pass
y_pred = model_0(X)

    # 2. Calculate loss (per batch)
    loss = loss_fn(y_pred, y)
    train_loss += loss # accumulatively add up the loss per epoch 

    # 3. Optimizer zero grad
    optimizer.zero_grad()

    # 4. Loss backward
    loss.backward()

    # 5. Optimizer step
    optimizer.step()

    # Print out how many samples have been seen
    if batch % 400 == 0:
        print(f"Looked at {batch * len(X)}/{len(train_dataloader.dataset)} samples")

# Divide total train loss by length of train dataloader (average loss per batch per epoch)
train_loss /= len(train_dataloader)

### Testing
# Setup variables for accumulatively adding up loss and accuracy 
test_loss, test_acc = 0, 0 
model_0.eval()
with torch.inference_mode():
    for X_test, y_test in test_dataloader:
        # 1. Forward pass
        test_pred = model_0(X)
       
        # 2. Calculate loss (accumatively)
        test_loss += loss_fn(test_pred, y) # accumulatively add up the loss per epoch

        # 3. Calculate accuracy (preds need to be same as y_true)
        test_acc += accuracy_fn(y_true=y, y_pred=test_pred.argmax(dim=1))
    
    # Calculations on test metrics need to happen inside torch.inference_mode()
    # Divide total test loss by length of test dataloader (per batch)
    test_loss /= len(test_dataloader)

    # Divide total accuracy by length of test dataloader (per batch)
    test_acc /= len(test_dataloader)

## Print out what's happening
print(f"\nTrain loss: {train_loss:.5f} | Test loss: {test_loss:.5f}, Test acc: {test_acc:.2f}%\n")

Calculate training time

train_time_end_on_cpu = timer()
total_train_time_model_0 = print_train_time(start=train_time_start_on_cpu,
end=train_time_end_on_cpu,
device=str(next(model_0.parameters()).device))

[ayushg647]

for X_test, y_test in test_dataloader:
im getting an error in this line

[ayushg647]

Basically im not able to iterate on the test_loader

[4833R11Y45]

did you find the fix?