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.
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.