HierarchicalAttentionNetworks
HierarchicalAttentionNetworks copied to clipboard
Masking error
Trying to run the network in Google Colab, throws an error due to the mask dimensions:

Running it on the computer returns ValueError: Dimensions must be equal, but are 15 and 100 for 'hierarchical_attention_network_2/mul' (op: 'Mul') with input shapes: [?,15], [?,15,100].
Any help on how to fix this much appreciated, Cheers!
Trying to run the network in Google Colab, throws an error due to the mask dimensions:
Running it on the computer returns ValueError: Dimensions must be equal, but are 15 and 100 for 'hierarchical_attention_network_2/mul' (op: 'Mul') with input shapes: [?,15], [?,15,100]. Any help on how to fix this much appreciated, Cheers!
I have met the same problem, somebody comes to help me!
removing 'mask_zero=True' in the embedding layer definition fixed the error for me. Hope it helps!
Hi, it fixed the problem but the model predicts padding (0 class). Any explanation for this ?