Closed Hyperion-shuo closed 2 years ago
So, the released code is for tensorflow graph mode, so the transform matrix is a graph op which generates a different random matrix each time it's evaluated in a sess.run
call. Lemme know if you still have any confusion.
I see, the transform matrix is an option not a constant, thank you so much.
The paper says for each mini-batch randomly draw a categorical distribution. But in the code i only find the transform_matrix generate once in _create_network function, and is not change during trainning. Maybe i just miss it, the training option uses q_heads, and q_heads read transform_matrix from Network's kwargs, but i can't find where it update.