Indexing issue in model/lib/model_AV_new.py

bill9800 / speech_separation

Include some core functions and model to handle speech separation

MIT License

153 stars 61 forks source link

Indexing issue in model/lib/model_AV_new.py #18

Open vitrioil opened 4 years ago

vitrioil commented 4 years ago

I have created a pull request addressing the indexing issue (#17) . Keras during run time adds another dimension at axis 0 which becomes the batch axis. Hence, sliced() function slices through the second last dimension viz. embedding and not the people_num.