issue about the conv2d operation

[kelvinleen]

as in https://github.com/guoyinwang/LEAM/issues/6#issue-347848059, the implementation is not same as what the paper shows in equation 3.

i think line50 in model.py should be replaced as follows: G = tf.expand_dims(G, axis=-1) # bsc1 filter: ngram1 filter_num:1 Att_v = tf.contrib.layers.conv2d(G, num_outputs=1, kernel_size=[opt.ngram,1], padding='SAME',activation_fn=tf.nn.relu) #b * s * c * 1 Att_v = tf.squeeze(Att_v,)

[SCAUapc]

I have the same problem as you. And i agree with you. But I wish can get the reply by the author

[AlexMoreo]

I think you are right. I had to do exactly the same modification (If only had I see your comment before... :D)