torchmd-net
torchmd-net copied to clipboard
Test loss
Which function is supposed to compute the test loss? Can we clean it up?
https://github.com/torchmd/torchmd-net/blob/2f6e19091ce161edb86568fe9a2af291a69b38d3/torchmdnet/module.py#L61-L69
Ping: @PhilippThoelke @stefdoerr
Because of the way lighting works we could only do it this way
On Mon, Aug 29, 2022 at 10:27 AM Raimondas Galvelis < @.***> wrote:
Which function is supposed to compute the test loss? Can we clean it up?
https://github.com/torchmd/torchmd-net/blob/2f6e19091ce161edb86568fe9a2af291a69b38d3/torchmdnet/module.py#L61-L69
Ping: @PhilippThoelke https://github.com/PhilippThoelke @stefdoerr https://github.com/stefdoerr
— Reply to this email directly, view it on GitHub https://github.com/torchmd/torchmd-net/issues/120, or unsubscribe https://github.com/notifications/unsubscribe-auth/AB3KUOS7ZM4JKNDTJ52GK5LV3RX6PANCNFSM5743WLMQ . You are receiving this because you are subscribed to this thread.Message ID: @.***>
Loss is computed in step
, no matter if during train, val or test. The function validation_step
is called by pytorch-lightning to evaluate the model on all validation dataloaders. test_step
is only called at the end of training or via trainer.test(...)
. Since we want to compute test loss during training, one of the validation dataloaders contains the test set.