commit | 4c80bdee913b8c6bd0760b94ee6cbdb7a165b1b2 | [log] [tgz] |
---|---|---|
author | Cindy Liu <hcindyl@google.com> | Mon Jul 27 22:41:50 2020 -0700 |
committer | Cindy Liu <hcindyl@google.com> | Tue Jul 28 11:05:22 2020 -0700 |
tree | 5ebf8afb28666e05d5dda890d3fac8251d0e51a4 | |
parent | 2e85f71c73e5e5e53a7e19c306f35f35b1220ec5 [diff] |
Enable mp4 input in video pipeline - Enable HW video decoder for video file src - Adjust the render_size scaling mechanism - Take care of stride in the inference frame (glbox generates stride as multiples of 4) Currently we need to pass the decoded stream through mtkmdp, and this plugin has many bugs (not supporting GL, format error to rsvgoverlay,etc.). The POR is to use v4l2convert instead. Bug: 151393184 Tested: edgetpu_demo --device Tested: edgetpu_detect (with webcam) Tested: edgetpu_classify (with image) Change-Id: Ic448069c1a950e077a4ff62ba84aedffebbc9c31
Python API to run inference on image data coming from the camera.
python3 setup.py sdist python3 setup.py bdist python3 setup.py sdist_wheel
Install stdeb
package by running apt-get install python3-stdeb
or pip3 install stdeb
. Then to generate debian folder run:
python3 setup.py --command-packages=stdeb.command debianize
To build debian pacakge run:
dpkg-buildpackage -b -rfakeroot -us -uc -tc