• State TI Thinks Resolved
  • Locked Locked
  • Replies 1 reply
  • Answers 1 answer
  • Subscribers 98 subscribers
  • Views 171 views
  • Users 0 members are here
Support feedback
Options
Options
Related

This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

SK-TDA4VM: transfer learning, model compilation, model deployment and evaluation

reebs j
Prodigy 20 points

Part Number: SK-TDA4VM

After model training(yolo-s-lite) in model composer of edgeaistudio I download the model and artifacts. Then how to load and put model in specific folder in target device SK-TDA4VM. Is there any proper procedure or steps to run sample object detection from custom dataset trained model.

Regards

Reebs

  • 0
    TI__Mastermind 24041 points

    Hi,

    After custom model training on edgeai studio please follow below steps to do inferencing on target device.

    1. Download the compiled model artifacts to SK-TDA4VM target.
    2. Create new yaml file, lets say custom_object_detection.yaml, and copy contains of object_detection.yaml(std provided file with sdk).
    3. Modify the custom_object_detection.yaml, Under models: section of yaml file, give path to downloaded model artifacts directory.
    4. Provide viz_threshold value based on your application specific requirement.

    Note : 

    You can refer to /opt/model_zoo/ directory where we have model artifacts of different models to better understand how to provide directory path in yaml files.

    Regards,

    Pratik