Open hannahgym opened 3 years ago
The ids are only used to generate the results dictionary in eval mode, the ids are not being passed into the model.generate_sentence call. See line here in lcrn_trainer.py
Sorry, nevermind...you are right. The ground truth labels are appended to the image features and passed into the evaluation....not sure where to go from here then...
here code , ground truth labels are passed to the model on eval mode!!!!
could you please correct me if i am wrong?
thanks.