-
Notifications
You must be signed in to change notification settings - Fork 6.8k
Conversation
Hey @barry-jin , Thanks for submitting the PR
CI supported jobs: [clang, windows-gpu, edge, centos-cpu, centos-gpu, miscellaneous, unix-gpu, website, sanity, unix-cpu, windows-cpu] Note: |
python/mxnet/gluon/rnn/rnn_layer.py
Outdated
i2h_weight_initializer=None, h2h_weight_initializer=None, | ||
i2h_bias_initializer='zeros', h2h_bias_initializer='zeros', |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
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.
@mxnet-bot run ci [centos-gpu] |
Jenkins CI successfully triggered : [centos-gpu] |
@mxnet-bot run ci [centos-gpu] |
Jenkins CI successfully triggered : [centos-gpu] |
@mxnet-bot run ci [centos-gpu] |
Jenkins CI successfully triggered : [centos-gpu] |
Description
Use only one parameter for rnn_layer in stead of multiple parameters to improve performance.
Checklist
Essentials
Changes
Comments