Increase the CUDA memory twice then stop increasing

8

That’s because you’re still returning “loss” which unless you have torch.no_grad() holds onto a lot of data so that you can call loss.backward() in the future.

Put everything in a function (including the GPU copies of input and targets) or use del.

...

def step(input, targets):
    inputs, targets = inputs.to(device), targets.to(device)
    optimizer.zero_grad()

    loss, predicted_output = forward_pass(model, inputs, targets, loss_criterion)

    error_ = error(predicted_output.data.cpu(), targets.data.cpu().long().squeeze())

    running_loss.update(loss.item(), inputs.size(0))
    running_error.update(error_.item(), inputs.size(0))

for i in range(50):
    for idx, (inputs, targets) in enumerate(loaders):
        step(input, targets)
2 Likes