1
Clone Repository
Run `git clone https://github.com/open-edge-platform/training_extensions` to obtain the source code.
2
Set Up Environment
Create a virtual environment and install dependencies using `python -m venv venv; source venv/bin/activate; pip install -e ote_cli/ -c external/model-preparation-algorithm/constraints.txt`.
3
Prepare Dataset
Annotate and organize your dataset, for example using CVAT, and split into training and validation sets.
4
Train Model
Use the CLI command `ote train <template.yaml> --train-data-roots <path> --train-ann-file <file> --val-data-roots <path> --val-ann-files <file> --save-model-to <output>` to start training.
5
Evaluate and Export
Evaluate the trained model on validation data and export it to OpenVINO IR or ONNX formats for deployment.