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

Possibilities for Including the Adjoint Method #2

Closed
eozd opened this issue Feb 27, 2020 · 2 comments · Fixed by #3
Closed

Possibilities for Including the Adjoint Method #2

eozd opened this issue Feb 27, 2020 · 2 comments · Fixed by #3

Comments

@eozd
Copy link
Contributor

eozd commented Feb 27, 2020

Hi,

In the readme you mention that adjoint method is not yet available due to limitations of tensorflow. I would like to ask a status update on this, i.e. do you have any ideas how one can incorporate the adjoint method into this tensorflow implementation? Or do you think that is entirely impossible in the current version of tensorflow?

Thanks and kind regards

@titu1994
Copy link
Owner

It is definitely possible to implement in general. However, I am unable to implement it in the context of the framework that has been developed.

I'm not experienced enough in manipulating a custom gradient on Tensorflow.

@renmengye
Copy link

Could you describe what exactly is the problem and have an example snippet? Based on the your description I understood, TF custom gradient should allow you to define the gradients to the variables created inside, no?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging a pull request may close this issue.

3 participants