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-Detection.git
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
cd yolov7
pip3 install -r requirements.txt
Remember to change the variable to your setting.
python3 pytorch2onnx.py --weights ./model/yolov7-tiny.pt --simplify --img-size 480 640 --max-wh 640 --topk-all 100 --end2end --grid
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
Install ONNX modifier and start flask service
cd onnx-modifier
pip3 install -r requirements.txt
pip3 install onnx==1.10.0
python3 app.py
Enter http://127.0.0.1:5000/
Cut the below part of the network
Add the new output and download it
Move the modified newtork to replace the old one
mv ./onnx-modifier/modified_onnx/modified_{model_name}-{input_height}-{input_width}.onnx ./model/{model_name}-{input_height}-{input_width}.onnx
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
python3 onnx2rknn_step2.py
python3 rknn_lite_inference.py
wget -c ftp://[email protected]/ai_toolchain/ai_toolchain.tar.gz --ftp-password=xj3ftp@123$%
tar -xvf ai_toolchain.tar.gz
cd ai_toolchain/
pip3 install h*
get onnx file with opset 11
python3 pytorch2onnx.py --weights ./model/yolov7-tiny.pt --simplify --img-size 480 640 --max-wh 640 --topk-all 100 --end2end --grid --opset 11
Follow Step 4
to delete part of model, and run remove_value_list.py
to remove corresponding value in model
Remember to change the variable to your setting include yolov7det_config.yaml
sh 01_check.sh
sh 02_preprocess.sh
sh 03_build.sh
python3 horizion_simulator_inference.py
python3 horizion_onboard_inference.py
python3 onnxruntime_inference.py
Use the ONNX file come from Step 4
Remember to change the variable to your setting
python3 onnx2trt.py
python3 tensorrt_inference.py
Convert model from onnx to blob format via https://blobconverter.luxonis.com/
python3 blob_inference.py
https://blog.csdn.net/magic_ll/article/details/131944207
https://github.com/ibaiGorordo/ONNX-YOLOv8-Instance-Segmentation