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 on a mp4 video? #19

Closed
cedricve opened this issue Mar 11, 2017 · 5 comments
Closed

How to run on a mp4 video? #19

cedricve opened this issue Mar 11, 2017 · 5 comments

Comments

@cedricve
Copy link

cedricve commented Mar 11, 2017

Awesome contribution! I've looked in the demo script, and saw there is support for processing videos? However I tried it, but didn't succeeded in running it properly.

Any tips or howto, I get following error. Tried to install gtk2.0 seperately.

cv2.destroyAllWindows()
cv2.error: /io/opencv/modules/highgui/src/window.cpp:577: error: (-2) The function is not implemented. Rebuild the library with Windows, GTK+ 2.x or Carbon support. If you are on Ubuntu or Debian, install libgtk2.0-dev and pkg-config, then re-run cmake or configure script in function cvDestroyAllWindows
@cedricve
Copy link
Author

Ok looks like video related functionality and GTK is not supported.

  • video related functionality is not supported (not compiled with FFmpeg)
  • for example cv.imshow() will not work (not compiled with GTK+ 2.x or Carbon support)

https://pypi.python.org/pypi/opencv-python

@cedricve
Copy link
Author

ended up with compiling opencv from source and using the .so library directly.

@BichenWuUCB
Copy link
Owner

@cedricve Thanks for your interest. As a matter of fact, though SqueezeDet's speed definitely satisfies normal video's frame rate, but since it takes each frame as an independent input, in our previous experiments, we observed some discontinuity in prediction results between neighboring frames. We are currently working on improving SqueezeDet's performance on videos. So, stay tuned!

@cedricve
Copy link
Author

@BichenWuUCB cool, I'll use your classifier in the @kerberos-io project (www.kerberos.io). If you need some data, let me know..

@acmaheri
Copy link

acmaheri commented May 8, 2019

@BichenWuUCB are you already done on improving SqueezeDet's performance on videos?

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

3 participants