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 to run demo.py on CPU #43

Open
mrlzla opened this issue May 23, 2017 · 2 comments
Open

How to run demo.py on CPU #43

mrlzla opened this issue May 23, 2017 · 2 comments

Comments

@mrlzla
Copy link

mrlzla commented May 23, 2017

So that's all the question ;)

@mrlzla mrlzla changed the title How to run demo.py on CPU model How to run demo.py on CPU May 23, 2017
@mrlzla
Copy link
Author

mrlzla commented May 31, 2017

I ran demo.py on CPU mode and GPU mode and I figured out that this model was faster on CPU rather GPU. What did I do wrong?
I just changed line 21 in squeezeDet.py:

 with tf.device('/gpu:{}'.format(gpu_id)):

with:

 with tf.device('/cpu:0'):

@Timen
Copy link

Timen commented Jun 13, 2017

Could you provide some more information, like the specs of your machine, which tensorflow version you are using and maybe any errors or abnormalities you are seeing between running cpu vs gpu.

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

No branches or pull requests

2 participants