interpretable-han-for-document-classification-with-keras
interpretable-han-for-document-classification-with-keras copied to clipboard
Tensorflow 2 upgrade
Hi,
I have an issue with the dummy layer you defined as:
dummy_layer = Lambda( lambda x: att_layer._get_attention_weights(x) )(prev_tensor)
It is not working in Tensorflow 2. Based on my search, we need to convert it to a subclass layer. Could you please help with this issue? How this subclass layer should be defined inside "show_word_attention(self, x)" function?
Thanks