search

dennybritz / cnn-text-classification-tf

Convolutional Neural Network for Text Classification in Tensorflow
Apache License 2.0
5.65k stars 2.77k forks source link

Why the direction of concatting is `axis 3`? #167

Open rosefun opened 6 years ago

rosefun commented 6 years ago

https://github.com/for-research/cnn-text-classification-tf/blob/18762b459e21d9c70e5c242f8d43fc4e6db37a0d/text_cnn.py#L57

''' self.h_pool = tf.concat(pooled_outputs, 3) '''

Why it concats in axis = 3? Actually, I think it should concat in axis = 1 , which is the direction of the text length.