Test loss

[raimis]

Which function is supposed to compute the test loss? Can we clean it up?

torchmd-net/torchmdnet/module.py

Lines 61 to 69 in 2f6e190

	def validation_step(self, batch, batch_idx, *args):
	if len(args) == 0 or (len(args) > 0 and args[0] == 0):
	# validation step
	return self.step(batch, mse_loss, "val")
	# test step
	return self.step(batch, l1_loss, "test")
	def test_step(self, batch, batch_idx):
	return self.step(batch, l1_loss, "test")

Ping: @PhilippThoelke @stefdoerr

[giadefa]

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 <#120>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AB3KUOS7ZM4JKNDTJ52GK5LV3RX6PANCNFSM5743WLMQ> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

[PhilippThoelke]

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.