C3V Validation Guide

This is the document on how to test the YOLOv8s detection map with the COCO 2017. We provide hybrid quantization to convert the model.

1. Prerequest

1.1. Provided Files

Download Hybrid_Quantization_Resources.zip and unzip the provided zipped file. We use 'provided_files' to represent the folder where you unzip the file to. The folder structure is as follows:

Open

1.2. Conda Environment Setup

Please refer to the Setup_Miniconda3_Environment(Hybrid_Quantization).pdf to set up the Conda environment named quantize_yolov8s_demo on Ubuntu PC and Python 3.8 on C3V.

1.3. Data Preparation(Ubuntu PC)

Download the COCO 2017 train and validation images and their annotations for evaluation. Unzip the downloaded files and organize them according to the folder structure shown below.

Open

Copy the prepare_inputs folder from the provided_files/python_scripts/ directory to your desired location. Then open a terminal within the prepare_inputs folder. In the terminal, activate the Conda environment 3.8_python, and run the following commands.

Once it's finished, the folder should contain the following new items:

Later in this documentation, all references to the prepare_inputs will refer to this one.

2. Model Transition (Ubuntu PC / Acuity)

Set up the Conda environment named 3.8.10_python_acuity by referring to the Acuity package requirements in Section 4 of the C3V_AI_Platform_20240605.pdf.

Place

• hy_layer.txt (provided_files/)

• yolov8s_demo.onnx (provided_files/)

• transform_yolov8s_demo_acuity_6.30.7.py (provided_files/python_scripts/)

• processed_inputs_for_quantization folder (prepare_inputs/)

• inputs_for_acuity_quantization.txt (prepare_inputs/)

in an empty folder. Open a terminal within the folder, activate the Conda environment 3.8.10_python_acuity, and then:

Set the environment variables based on your folder structure and placement. The version for acuity_examples is 5272e22.

Import, quantize, and export model by:

Once the export is finished, a folder should be named ovxlib_application_nbg_unify. Under this folder:

• Modify vnn_pre_process.c

  • In the function _load_input_meta()

• Modify vnn_post_process.c

3. Model Inference (C3V Board)

3.2. Inference by Python

3.2.1 Build the project (Ubuntu PC)

Then import the modified ovxlib_application_nbg_unify folder into the Vivante IDE and build the project with the proper build configurations. Related information can be found in Section 6 of the C3V_AI_Platform_20240605.pdf

Copy these to the C3V board.

• built project folder

• processed_i8_bin_for_validation.zip (prepare_inputs/)

• c3v_inference_yolov8s_demo.py (provided_files/python_scripts/c3v_pipeline/)

3.2.2. Inference (C3V Board)

Unzip processed_i8_bin_for_validation.zip to the built project folder and move c3v_inference_yolov8s_demo.py to the built project folder.

Open a terminal within the built project folder, give the execute permission to the executable by:

Then activate the Conda environment 3.8_python, and run the following command.

This command may take some time. Once complete, you should find two new files:

• c3v_inputs_order.txt

• Inference_Raw_Predictions.zip

Copy them back to the Ubuntu PC.

3.2.3. Evaluation (Ubuntu PC / C3V)

Place these files in an empty folder.

• Inference_Raw_Predictions.zip

• c3v_inputs_order.txt

• processed_i8_bin_for_validation_meta_info.json (prepare_inputs/)

• process_outputs_to_coco_format.py (provided_files/python_scripts/c3v_pipeline/)

• coco_eval.py (provided_files/python scripts/c3v_pipeline/)

Open a terminal within the folder, activate conda environment 3.8_python, and run:

The results will be printed in the terminal as follows:

3.3. Inference by C code

3.3.1. Prepare the environment (C3V Board)

3.3.2. Prepare the project (Ubuntu PC/C3V)

Download the mapTestTools_v1.1.zip and unzip the provided zipped file. The project code tree is like this：

1. Copy these three files to the framework/model folder, the files were exported by the acuity toolkit in this step: C3V Validation Guide | 3.1. Transition (Ubuntu PC / Acuity)

• network_binary.nb

• vnn_yolov8sdemo.c

• vnn_yolov8sdemo.h

2. Modify model/vnn_model.c like this.

3.3.3. Build and Evaluation (C3V Board)

Copy the project files to the C3V, copy the val2017 dataset to the C3V, and build it on C3V Ubuntu with follow command.

Do the map test using follow command

The results will be printed in the terminal as follows: