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

Conv2D channels_last in the Keras #57

Closed
cherishing78 opened this issue Jul 28, 2017 · 1 comment
Closed

Conv2D channels_last in the Keras #57

cherishing78 opened this issue Jul 28, 2017 · 1 comment

Comments

@cherishing78
Copy link

cherishing78 commented Jul 28, 2017 •
edited
Loading

Hi Vince, I've noticed that the default mode of Conv2D function in the Keras is channels_last. In the 57th line and 73rd line of the NN_keras.py, the Reshape operation sets the channels as the first dimension. In my test, the function cannot work properly. The mountain_car_continuous works well because the dim == 1 and dim[0] == 1.
@VinF VinF mentioned this issue Jul 28, 2017
Merged
@VinF
Copy link
Owner

VinF commented Jul 28, 2017

Hi, it should be fixed (PR #58).

@VinF VinF closed this as completed Jul 28, 2017
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
2 participants
@VinF @cherishing78