laitathei / YOLOv7-ONNX-RKNN-HORIZON-TensorRT-Segmentation

Inference YOLOv7 segmentation on ONNX, RKNN, Horizon and TensorRT

YOLOv7-ONNX-RKNN-HORIZON-TensorRT-Segmentation

Remark: This repo only support 1 batch size

Video source: https://www.youtube.com/watch?v=n3Dru5y3ROc&t=0s

git clone --recursive https://github.com/laitathei/YOLOv7-ONNX-RKNN-HORIZON-TensorRT-Segmentation.git

0. Environment Setting

torch: 1.10.1+cu102
torchvision: 0.11.2+cu102
onnx: 1.10.0
onnxruntime: 1.10.0

# For tensorrt
torch: 1.11.0+cu113
torchvision: 0.12.0+cu113
TensorRT: 8.6.1

1. Yolov7 Prerequisite

cd yolov7
pip3 install -r requirements.txt

2. Convert Pytorch model to ONNX

Remember to change the variable to your setting.

python3 pytorch2onnx.py --weights ./model/yolov7-seg.pt --include onnx --img-size 480 640 --simplify

3. RKNN Prerequisite

Install the wheel according to your python version

cd rknn-toolkit2/packages
pip3 install rknn_toolkit2-1.5.0+1fa95b5c-cpxx-cpxx-linux_x86_64.whl

4. Convert ONNX model to RKNN

Remember to change the variable to your setting To improve perfermance, you can change ./config/yolov7-seg-xxx-xxx.quantization.cfg layer type. Please follow official document hybrid quatization part and reference to example program to modify your codes.

python3 onnx2rknn_step1.py

Add following setting into ./config/yolov7-seg-xxx-xxx.quantization.cfg

custom_quantize_layers:
    528_shape4_Slice_315: float16
    638_shape4_Slice_391: float16
    748_shape4_Slice_467: float16
    528_int8: float16
    638_int8: float16
    748_int8: float16

python3 onnx2rknn_step2.py

5. RKNN-Lite Inference

python3 rknn_lite_inference.py

6. Horizon Prerequisite

wget -c ftp://[e-mail]/ai_toolchain/ai_toolchain.tar.gz --ftp-password=xj3ftp@123$%
tar -xvf ai_toolchain.tar.gz
cd ai_toolchain/
pip3 install h*

7. Convert ONNX model to Horizon

get onnx file with opset 11

python3 pytorch2onnx.py --weights ./model/yolov7-seg.pt --include onnx --img-size 480 640 --simplify --opset 11

Remember to change the variable to your setting include yolov7seg_config.yaml

sh 01_check.sh
sh 02_preprocess.sh
sh 03_build.sh

8. Horizon Inference

python3 horizion_simulator_inference.py
python3 horizion_onboard_inference.py

9. Onnx Runtime Inference

python3 onnxruntime_inference.py

10. Convert ONNX model to TensorRT

Remember to change the variable to your setting

python3 onnx2trt.py

11. TensorRT Inference

python3 tensorrt_inference.py

Reference

https://blog.csdn.net/magic_ll/article/details/131944207
https://blog.csdn.net/weixin_45377629/article/details/124582404#t18
https://github.com/ibaiGorordo/ONNX-YOLOv8-Instance-Segmentation