Home Available Analyses FAQ Docs
Sign In

DeepGraphPose (Wu et al. 2020)


Analysis description

DGP is a semi supervised model which can run on top of other tracking algorithms, such as DLC. Since DLC developers have put in a lot of work into their GUI (and made it open source!), our algorithm can be run using the same filestructure as DLC.

Useful links
DeepGraphPose (Wu et al. 2020) Paper Link
DeepGraphPose (Wu et al. 2020) Github Repo Link
DeepGraphPose (Wu et al. 2020) Bash Script Link
DeepGraphPose (Wu et al. 2020) Demo Link
How to use this analysis

Inputs:

Raw data: (zip file) Use DLC’s GUI to preprocess data and collect labels. This will create a project directory with the name format [task]-[scorer]-[date].
Inside this directory, create a directory called ‘videos_dgp’, and add to this directory any other videos on which you want to run DGP at test time.
Then zip the [task]-[scorer]-[date] directory and upload it here.

Config: (yaml) a file named ‘config.yaml’ with one entry: datapath: [task]-[scorer]-[date]
Where [task]-[scorer]-[date] is the name of the raw data .zip file you created.

Outputs:

logs: log output from the job.
process_results: predicted videos and CSV and h5 files with predicted x-y marker positions.


You must login to use an analysis.

  • Twitter
  • Github
  • Dribbble