How-To Guide

How-To Run on the ICICLE Instance

The ICICLE instance of the ML Field Planner is accessible here.

1. You can either login with your TACC account or via CILogin.
2. Once logged in, navigate to the Camera Traps Edge Simulator Dashboard by selected ML Edge on the left side menu and then clicking on the Go to Analysis Environment box.
3. To prepare an analysis run, first select a select. You can either choose a model from the dropdown menu or click the provide model id button above the dropdown. We currently only support Patra model card IDs, you can find a list of models by navigating to ML Hub --> models and choosing Patra as the Platform.
4. After the model has been selected, choose a dataset to run the model against. There is a button to choose between a video or image dataset. For both, we provide example datasets, but if you would like to test against your own data, select provide dataset id and provide a url to your dataset.
5. Next, select a site to run the experiment from the dropdown. The ICICLE deployment of ML Field Planner has access to hardware at two sites, Chameleon and TACC, each with different types of hardware available.
6. After selecting the site, select the type of hardware to run on.
7. Finally, to run the ML pipeline with any advanced features provide a JSON in the Advanced Config text field. For a list of features supported by the Camera Traps Edge Software, see the README.
8. Click the Analyze button to being the analysis.
9. You should see your analyses, including this one experiments under the submission button in the Analyses table. From the table, you can view the status of the job and even jump to an archive of the run directory. Note the UUID of the experiment.
10. To view metrics captured by the CKN, select the CKN Dashboard on the left menu and then select Camera Traps. Choose your username in the first dropdown and then choose your experiment UUID in the second dropdown.