Content Comparison

...

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:

...

Please refer to the Setup_Miniconda3_Environment(C3VHybrid_ValidationQuantization).pdf to set up the Conda environment named quantize_yolov8s_demo on Ubuntu PC and Python 3.8 on C3V.

...

python prepare_quantization_dataset.py
python prepare_validation_dataset_i8_bin.py

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

...

• hy_layer.txt (provided_files/)

• yolov8s_inspirendemo.onnx (provided_files/)

• transform_yolov8s_inspirendemo_acuity_6.30.7.py (provided_files/python_scripts/)

• processed_inputs_for_quantization folder (prepare_inputs/)

• inputs_for_acuity_quantization.txt (prepare_inputs/)

...

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

...

python transform_yolov8s_inspirendemo_acuity_6.30.7.py

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

...

input_meta_tab[0].image.scale[0] = 0.00392156862
input_meta_tab[0].image.scale[1] = 0.00392156862
input_meta_tab[0].image.scale[2] = 0.00392156862

• Modify vnn_post_process.c

Modify vnn_post_process.c according to modify_vnn_post_process_c .txt in the provided_files/ directory.

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 5 6 of the C3V_AI_Platform_20240605.pdf

...

• built project folder

• processed_i8_bin_for_validation.zip (prepare_inputs/)

• c3v_inference_yolov8s_inspirendemo.py (provided_files/python_scripts/c3v_pipeline/)

...

Unzip processed_i8_bin_for_validation.zip to the built project folder and move c3v_inference_yolov8s_inspirendemo.py to the built project folder.

...

chmod +x ./Debug/yolov8sinspirenyolov8sdemo

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

python c3v_inference_yolov8s_inspirendemo.py

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

...

sudo apt update
sudo apt install python3-pip libopencv-dev libjsoncpp-dev
pip install pycocotools

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: https://sunplus.atlassian.net/wiki/spaces/C3/pages/2354020355/C3V+validationValidation+Guide#3.1.-Transition-(Ubuntu-PC-%2F-Acuity)

• network_binary.nb

• vnn_yolov8sinspirenyolov8sdemo.c

• vnn_yolov8sinspirenyolov8sdemo.h

2. Modify model/vnn_model.c like this.

vsi_nn_graph_t *
vnn_CreateGraph(const char *data_file_name, vsi_nn_context_t in_ctx,
				const vsi_nn_preprocess_map_element_t *pre_process_map,
				uint32_t pre_process_map_count,
				const vsi_nn_postprocess_map_element_t *post_process_map,
				uint32_t post_process_map_count)
{
	return vnn_CreateYolov8sInspirenCreateYolov8sDemo(data_file_name, in_ctx, pre_process_map, pre_process_map_count, post_process_map,
									post_process_map_count);
} /* vnn_CreateGraph() */

void vnn_ReleaseGraph(vsi_nn_graph_t *graph, vsi_bool release_ctx)
{
	vnn_ReleaseYolov8sInspirenReleaseYolov8sDemo(graph, release_ctx);
} /* vnn_ReleaseGraph() */

...