I use google tft model from pytorch.
My question is : what does validation_step_output tft’s attribute contain ? When I debug my code I see that is still empty when calling on_validation_epoch_end, why??
def on_validation_epoch_end(self):
self.on_epoch_end(self.validation_step_outputs)
self.validation_step_outputs.clear()
here I get self.validation_step_outputs empty list as mentioned before.
while this function is responsible of adding the val_loss into the list I think
def validation_step(self, batch, batch_idx):
x, y = batch
log, out = self.step(x, y, batch_idx)
log.update(self.create_log(x, y, out, batch_idx))
self.validation_step_outputs.append(log)
return log