chenchongthu / NARRE

This is our implementation of NARRE:Neural Attentional Regression with Review-level Explanations
107 stars 48 forks source link

Can not run train.py #13

Closed dianziliu closed 3 years ago

dianziliu commented 3 years ago

tf.einsum() raises an error becuse self.h_drop_u.shape=[None, 16,100 ]. I don't know what happened. Can you tell me how to solve this problem?