You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When I convert my LSTM models that uses mask_zero=True, I get very different prediction results. When I test it in the original Keras model it seems to be working fine. When I try predictions with Keras.js, it gives me a very skewed result for whatever input. When I turn this setting off, it seems to be working fine..
The text was updated successfully, but these errors were encountered:
When I convert my LSTM models that uses mask_zero=True, I get very different prediction results. When I test it in the original Keras model it seems to be working fine. When I try predictions with Keras.js, it gives me a very skewed result for whatever input. When I turn this setting off, it seems to be working fine..
The text was updated successfully, but these errors were encountered: