szha commented on a change in pull request #20384:
URL: https://github.com/apache/incubator-mxnet/pull/20384#discussion_r659180198
##########
File path: python/mxnet/gluon/rnn/rnn_layer.py
##########
@@ -560,14 +494,10 @@ class GRU(_RNNLayer):
"""
def __init__(self, hidden_size, num_layers=1, layout='TNC',
dropout=0, bidirectional=False, input_size=0,
- i2h_weight_initializer=None, h2h_weight_initializer=None,
- i2h_bias_initializer='zeros', h2h_bias_initializer='zeros',
Review comment:
we will need an initializer for the fused parameter and use it as
default. With this default initializer for RNN layers, the bias terms should be
initialized as 0s.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
