search

facebookresearch / DetectAndTrack

The implementation of an algorithm presented in the CVPR18 paper: "Detect-and-Track: Efficient Pose Estimation in Videos"
Apache License 2.0
1k stars 186 forks source link

simple way for trying demo #19

Closed Sanketyeru closed 6 years ago

Sanketyeru commented 6 years ago
  1. could you please provide a simple command for trying this system. I do not want to train the model. I would like to Just test it on a video file and see the output. I am using your docker file for this.
  2. I am on the system with the following description: OS: Ubuntu 16.04 GPU: GTX 1070Ti (8Gb) CUDA : 9 cuDNN : 7.0

I tried using all_requirements file to create new conda environment but out of them 32 packages are not available for installation. can you provide a working solution for installing this system locally?
thanks in advance.

rohitgirdhar commented 6 years ago
  1. is tracked in https://github.com/facebookresearch/DetectAndTrack/issues/6
  2. In case the specific versions are not available, you can try running with the latest versions.
Sanketyeru commented 6 years ago

Can you please point to the specific file in this repo for only tracking and an example command so as to run tracking without evaluation