Don't be worried by complexity of this banner, with latest version of docker installed correctly, you can run Deep Video Analytics in minutes locally (even without a GPU) using a single command.
Architecture, data & processing model
Libraries used/modified in code and their licenses
|Library||Link to the license|
|Original CRNN code by Baoguang Shi||MIT License|
|Object Detector App using TF Object detection API||MIT License|
|CRF as RNN||MIT License|
|Segment annotator||BSD 3-clause|
|TF Object detection API||Apache 2.0|
|Open Images Pre-trained network||Apache 2.0|
Following libraries & frameworks are installed when building/running the container
- FFmpeg (not linked, called via a Subprocess)
- All packages in requirements.txt & used in Dockerfiles.
License & Copyright
Copyright 2016-2017, Akshay Bhat, Cornell University, All rights reserved.
Deep Video Analytics is currently in active development. The license will be relaxed once a stable release version is reached. Please contact me for more information. For more information see answer on this issue