-
Li Dong authored
The LayerNorm gamma and beta should be initialized by .fill_(1.0) and .zero_(). reference links: https://github.com/tensorflow/tensorflow/blob/989e78c412a7e0f5361d4d7dfdfb230c8136e749/tensorflow/contrib/layers/python/layers/layers.py#L2298 https://github.com/tensorflow/tensorflow/blob/989e78c412a7e0f5361d4d7dfdfb230c8136e749/tensorflow/contrib/layers/python/layers/layers.py#L2308
d0d9b384