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

shape of output data #43

Closed
sfdn123 opened this issue Aug 31, 2018 · 3 comments
Closed

shape of output data #43

sfdn123 opened this issue Aug 31, 2018 · 3 comments

Comments

@sfdn123
Copy link

sfdn123 commented Aug 31, 2018

Hi.
I ran infer_optimized.py with my webcam by reference to #20 and #42
But, i cant understand why out.shape = (1, 360, 640) (line38 : out = sess.run(y, feed_dict={x: img}).
i think this should be(360, 640, 3) because this is RGB image.
Can anyone explain this reason?

@sfdn123
Copy link
Author

sfdn123 commented Sep 3, 2018

Hi.
After that, I understood (1, 360, 640) is Argmax. So, i used img_utils.py to show webcam images. But, fps drop to 80fps→12fps by showing images. im using gtx1080. Can i get more fps ?
Thanks.

@moemen95
Copy link
Collaborator

moemen95 commented Sep 3, 2018

the code which converts the argmax to an rgb image is very slow and not optimized as it is for looping on values and convert it to the correspond RGB color.

I don't know for now if there is a better algo or implementation for this.
I will try to get you something faster.
if i found something. i will let you know.

@sfdn123
Copy link
Author

sfdn123 commented Sep 4, 2018

Hi@moemen95
Thank you for your reply.
I understand, I am looking forward to it.

@sfdn123 sfdn123 closed this as completed Sep 4, 2018
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