ProjectDimlight

I suppose there are still space of improvements... I made my attempt: https://github.com/ProjectDimlight/RuCalculus/blob/main/samples/%E5%BF%AB%E6%8E%92.%E5%85%A5 Maybe lambda calculus fits Classical Chinese more?

Hello, I suggest that the shape of the tf.nn.max_pool in the for-loop should be: ksize = [1, h_size, w_size, 1] instead of : ksize = [1, h_size, h_size, 1] As...