You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Is your feature request related to a problem? Please describe.
Currently, some modules (.py files) which are not supposed to be run have a main function as a kind of sanity check for the person writing the nn.Module or whatever. Most commonly we check for the input and output Tensor shapes to make sure the dims are correct. For example we might check that the output of a Generator should have the same size as its input with the same number of channels.
Describe the solution you'd like
All of the above sanity checks should be written separately with pytest.
Additional context
Please write tests that make sure the shapes of output torch.Tensors are correct after going through the generator or discriminator.
The text was updated successfully, but these errors were encountered:
Is your feature request related to a problem? Please describe.
Currently, some modules (.py files) which are not supposed to be run have a main function as a kind of sanity check for the person writing the nn.Module or whatever. Most commonly we check for the input and output Tensor shapes to make sure the dims are correct. For example we might check that the output of a Generator should have the same size as its input with the same number of channels.
Describe the solution you'd like
All of the above sanity checks should be written separately with pytest.
Additional context
Please write tests that make sure the shapes of output torch.Tensors are correct after going through the generator or discriminator.
The text was updated successfully, but these errors were encountered: