Using Model Repository

1. CD into a directory where pipelines will be stored, e.g.

mkdir -p ~/.clara/pipelines
cd ~/.clara/pipelines

2. Use clara pull pipeline to download the pipeline definition

clara pull pipeline clara_ai_livertumor_pipeline

3. Unzip test data

unzip app_livertumor-input_v1.zip -d input

4. Unzip and register the model

unzip app_livertumor-model_v1.zip
clara create model -p segmentation_liver_v1/ -t tensorflow

5. Install pipeline

clara create pipeline -p liver-tumor-pipeline-model-repo.yaml

6. Verify that the pipeline is correctly stored by using the following command line and look for the newly created pipeline UID.

clara list pipelines

1. Verify that the stored pipeline is correct by examining the output of the following command

clara describe pipeline -p <pipeline ID>

Using Legacy Pipeline Service

1. CD into a directory where pipelines will be stored, e.g.

mkdir -p ~/.clara/pipelines
cd ~/.clara/pipelines

2. Use clara pull pipeline to download the pipeline definition

clara pull pipeline clara_ai_livertumor_pipeline

3. Unzip test data

unzip app_livertumor-input_v1.zip -d input

4. Unzip and Install model

sudo unzip app_livertumor-model_v1.zip -d /clara/common/models/

5. Install pipeline

clara create pipeline -p liver-tumor-pipeline.yaml

6. Verify that the pipeline is correctly stored

clara list pipelines

7. Verify that the stored pipeline is correct by examining the output of the following command

clara describe pipeline -p <pipeline ID>