-
* sequence loss function for seq2seq loss * loss raises and docstring updated * detailed docstring * moving initializer one line down * change order of arguments, sparse_crossent * Use tf.stack instead of tf.pack.
24466c2e
从无法访问的项目Fork
* sequence loss function for seq2seq loss * loss raises and docstring updated * detailed docstring * moving initializer one line down * change order of arguments, sparse_crossent * Use tf.stack instead of tf.pack.