Week 1: June 02 ~ June 08

Preliminaries

The official GSoC coding period started on June 2. During our kickoff meeting on Friday, 30 June, we reviewed the project and foundational plan for developing a demo computer vision exercise that utilizes the ONNX Deep Learning Model.

Objectives

• Explore the file and folder architecture of the RoboticsAcademy Docker image
• Create a demo exercise by cloning the basic Computer Vision exercise
• Manually upload an ONNX deep learning model to the workspace/code directory inside RADI
• Run the Human Detection and Digit Classification exercises using the manually uploaded ONNX model
• Create a file upload widget that allows uploading of ONNX models
• Dynamically upload ONNX models to the workspace/code directory inside RADI via the widget

Execution

Demo exercise

Running Demo Human Detection exercise with Manually Uploaded ONNX Model

Running Demo Digit Classification exercise with Manually Uploaded ONNX Model

The figurate is the execution of the Upload ONNX model.

Results

References

[1] Basic Computer Vision Exercise