-
Notifications
You must be signed in to change notification settings - Fork 281
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
The details of "samples one sub-graph at one training iteration" #12
Comments
Sure, we use the hard mode and thus it is a one-shot vector. Something like this in PyTorch:
During the forward, you could use:
|
How do you implement the backward process? |
If you implement forward in the above style, it can automatically backward in PyTorch. |
Thanks for the code snippet! |
Can you talk about the details of "samples one sub-graph at one training iteration"?
As far as I know, the result of Gumbel Softmax may not be a one hot vector. It may be a vector like [0.96, 0.01, 0.01, 0.01, 0.01].
When you sample one sub-graph at training, do you just drop all the connections with weights 0.01?
Thanks.
The text was updated successfully, but these errors were encountered: