How to Run a Reference Pipeline using Local Input Files

Download & Install the Pipeline from NGC

Please refer to Setup section to install this Pipeline.

Note down the pipeline ID during the pipeline installation as it would be used in a later section to trigger a job with input files.

A pipeline can be triggered via Clara CLI.

For this created pipeline, sample input files are available within the SDK in the zipped test data file.

Once you execute ./download_input.sh fromo the pipeline folder, you will see the test data at input/app_ds_torso folder.

cd /path-to-the-pipeline/

Trigger the pipeline (upload input files to Clara API Server) with the pipeline ID in the previous section.

clara create jobs -n deepstream-batch-test -p <pipeline ID> -f input/app_ds_torso/

When the above step is completed, you should be able to see the following result in the terminal (UUID of Job and Payload may be different).

JOB ID:f3170b457f5c41879951e6da8f37341e
PAYLOAD ID:12bb398cb54844d5958d51e66e10713a

Note down this job ID and payload ID as they would be used in a later section to access output files.

Then, execute the job:

clara start job -j <JOB ID>

Once the job has completed successfully, we can download output payload by using clara download command.

Output payload files are located under /operators/deepstream/ folder. We can use the following command to download output files:

clara download <Job ID>:/operators/deepstream/* result # download files into result folder

Then, you can see the output video file using the following command:

google-chrome result/output.mp4 # View the video output using Chrome which has a built-in viewer for H.264 file.

If you are working with the server machine, the payload folder is directly accessible at the default payload folder /clara/payloads/<Payload ID>/.