|
def linear_mapping_weightnorm(inputs, out_dim, in_dim=None, dropout=1.0, var_scope_name="linear_mapping"): |
you are not using V_norm any where except from initialization of variable tensor g. and according to the paper https://arxiv.org/abs/1602.07868, g should be a scalar instead of a variable tensor. correct me if I am wrong.
conv_seq2seq/seq2seq/encoders/conv_encoder_utils.py
Line 59 in 78a6e4e
you are not using
V_normany where except from initialization of variable tensorg. and according to the paper https://arxiv.org/abs/1602.07868, g should be a scalar instead of a variable tensor. correct me if I am wrong.