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.

Sign up for GitHub

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

Jump to bottom

Does not work with Tensorflow #8

Open
Sohojoe opened this issue Jun 22, 2016 · 2 comments
Open

Does not work with Tensorflow #8

Sohojoe opened this issue Jun 22, 2016 · 2 comments

Comments

@Sohojoe
Copy link

Sohojoe commented Jun 22, 2016

I get the following error when running with TensorFlow (with GPU)

current context was not created by the StreamExecutor cuda_driver API: 0x2ccf300; a CUDA runtime call was likely performed without using a StreamExecutor context

Issue is that the code is referencing Theano directly:-
from theano.gradient import disconnected_grad

reference:- tensorflow/tensorflow#916
@sherjilozair
Copy link
Owner

it should be possible to use tf.stop_gradient to do this. However, this change should ideally belong to Keras backend, so that the DQN code becomes backend-agnostic.

@calclavia
Copy link

Use K.stop_gradient?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@sherjilozair @calclavia @Sohojoe