Better definition of loss

1

Hi,
Is it better to define a custom loss function in the following way
‘’’
class loss(torch.nn.Module):
code for loss
‘’’
or is is better to implement it as a normal function.

2

Whatever fits to your problem.
Pytorch losses are defined as modules because they may contain weights.

3

So the way loss is implemented wont affect the speed,right?

4

Nope. In the end using a nn.Module is a workaround. You will be more or less end up calling the same function than if you code it as a function.

1 Like