Chapter 6: A Journey Into Sound

[eiler-partner]

Hi,
I do not find the solution, why len(train_loader.dataset) is 0 and leads to this error.
Thank you for help.
Brds,
Patrick

[9] train(audionet, optimizer, torch.nn.CrossEntropyLoss(), train_loader, valid_loader, epochs=20, device=device)

ZeroDivisionError Traceback (most recent call last)
in
----> 1 train(audionet, optimizer, torch.nn.CrossEntropyLoss(), train_loader, valid_loader, epochs=20, device=device)

in train(model, optimizer, loss_fn, train_loader, val_loader, epochs, device)
14 optimizer.step()
15 training_loss += loss.data.item() * inputs.size(0)
---> 16 training_loss /= len(train_loader.dataset)
17
18 model.eval()

ZeroDivisionError: float division by zero

[MarcusFra]

I think it's due to the DataLoader object, which seems to be instantiated, but empty.

Have you set the correct path for your own environment and downloaded the data correctly in advance?

PATH_TO_ESC50 = Path.cwd() / 'esc50' # you might have to adjust this line, if your image directory is not '.../current_working_dir/esc50/'
train_esc50 = ESC50(PATH_TO_ESC50 / "train")
train_loader = torch.utils.data.DataLoader(train_esc50, batch_size = bs, shuffle = True)

[eiler-partner]

Hi,
That is so funny. I was doing that:
print(PATH_TO_ESC50)
print(train_esc50)
delivers
C:\Users\patri\Deep_Learning\I_pytorch_deep_learning\chapter6\esc50\audio
<main.ESC50 object at 0x000002820FBEFC10>
I took the original file and adaped the path an now it is running.