DA-RNN-in-Tensorflow-2-and-PyTorch icon indicating copy to clipboard operation
DA-RNN-in-Tensorflow-2-and-PyTorch copied to clipboard

Published 20 hours ago • verified publisher icon kaelzhang

Question about keras implementation while dealing Y

Open juanguang opened this issue 1 year ago • 1 comments

Hi, I wonder did you still include y_T here? I dont see the code which abandan y_T should line 439 be: Y = inputs[:, T-1, -self.y_dim:] so that it matches the dimension you wrote in the comment? https://github.com/kaelzhang/DA-RNN-in-Tensorflow-2-and-PyTorch/blob/1a30c3dffd7e8556c775480faa500d84fed5334c/da_rnn/keras/model.py#L435

juanguang avatar Sep 07 '23 18:09 juanguang

Please refer to the implementation of pytorch. Actually I don't have time to figure out the issue for tf implementation, but pytorch one is ok.

kaelzhang avatar Sep 08 '23 13:09 kaelzhang