WanjieZhan

我也遇到了相同的问题，好像是因为batch_dot()改版了，跟原来的不一样了！

我把capsulelayers.py 中的call()修改成了这样 def call(self, inputs, training=None): # inputs.shape=[None, input_num_capsule, input_dim_capsule] # inputs_expand.shape=[None, 1, input_num_capsule, input_dim_capsule] inputs_expand = K.expand_dims(inputs, 1) # Replicate num_capsule dimension to prepare being multiplied by W #...