Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

How i change the Initializers #61

Closed
InkdyeHuang opened this issue Apr 24, 2019 · 1 comment
Closed

How i change the Initializers #61

InkdyeHuang opened this issue Apr 24, 2019 · 1 comment
Labels

Comments

@InkdyeHuang
Copy link

Describe the question(问题描述)
A clear and concise description of what the question is.

Additional context
Add any other context about the problem here.

Operating environment(运行环境):

  • python version [e.g. 3.6]
  • tensorflow version [e.g. 1.4.0,]
  • deepctr version [e.g. 0.3.2,]
@shenweichen
Copy link
Owner

Hi @InkdyeHuang
in deepctr v0.3.4,you can modify the code of initializers of embeding layer in
deepctr.input_embedding line53-95 ,the code is like

embeddings_initializer=RandomNormal( mean=0.0, stddev=init_std, seed=seed)

and for initializers of DNN, look at code at
deepctr.layers.core line144-157
the code is like

initializer=glorot_normal(seed=self.seed)

@shenweichen shenweichen pinned this issue Jul 20, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

2 participants