# Run Examples

Follow the steps below to run the Post-Training Optimization Tool with one of the sample configuration files delivered with the Intel® Distribution of OpenVINO™ toolkit release package. 

In the instructions below, the Post-Training Optimization Tool directory `<INSTALL_DIR>/deployment_tools/tools/post_training_optimization_toolkit` is referred to as `<POT_DIR>`. `<INSTALL_DIR>` is the directory where Intel&reg; Distribution of OpenVINO&trade; toolkit is installed.

Sample configuration files are located in the `<POT_DIR>/configs/examples` folder.

1. Move to the Model Downloader folder:
   ```sh
   cd <POT_DIR>/libs/open_model_zoo/tools/downloader
   ```

2. Launch the `downloader` tool to download a model from the Open Model Zoo repository:
   ```sh
   python3 downloader.py --name <MODEL_NAME>
   ```

3. Launch `converter` tool to generate the IRv10 model:
   ```sh
   python3 converter.py --name <MODEL_NAME> --mo <PATH_TO_MODEL_OPTIMIZER>/mo.py
   ```
   python converter.py --name faster_rcnn_resnet50_coco --mo "C:\Program Files (x86)\IntelSWTools\openvino_2020.2.117\deployment_tools\model_optimizer\mo.py"

4. Update model/weights fields in the example config file you want to launch.

5. Update `config` section of the desired example config with a path to the AccuracyChecker config file if needed. If you want to use
Open Model Zoo config files, update the dataset definitions file `<POT_DIR>/libs/open_model_zoo/tools/accuracy_checker/dataset_definitions.yml`.

   If you have custom predefined engine section, override the path to the dataset and annotations inside the config.

6. Update dataset definitions file `<POT_DIR>/libs/open_model_zoo/tools/accuracy_checker/dataset_definitions.yml`.
 with necessary paths to your dataset (in case you don't have predefined Engine section).

7. Launch the Post-Training Optimization Tool with the required config file from the `<POT_DIR>` directory:
   ```
   cd <POT_DIR>
   python main.py -c "C:\Program Files (x86)\IntelSWTools\openvino_2020.2.117\deployment_tools\tools\post_training_optimization_toolkit\configs\examples\accuracy_checker\faster_rcnn_resnet50_coco.yaml"
   ```