base on YOLOv8 using TensorRT accelerate ! # YOLOv8-TensorRT `YOLOv8` using TensorRT accelerate ! --- [](https://github.com/triple-Mu/YOLOv8-TensorRT) [](https://github.com/triple-Mu/YOLOv8-TensorRT) [](https://developer.nvidia.com/tensorrt) [](https://github.com/triple-Mu/YOLOv8-TensorRT) [](https://github.com/triple-Mu/YOLOv8-TensorRT/blob/main/LICENSE) [](https://github.com/triple-Mu/YOLOv8-TensorRT/pulls) [](https://github.com/triple-Mu/YOLOv8-TensorRT) --- # Prepare the environment 1. Install `CUDA` follow [`CUDA official website`](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#download-the-nvidia-cuda-toolkit). 🚀 RECOMMENDED `CUDA` >= 11.4 2. Install `TensorRT` follow [`TensorRT official website`](https://developer.nvidia.com/nvidia-tensorrt-8x-download). 🚀 RECOMMENDED `TensorRT` >= 8.4 2. Install python requirements. ``` shell pip install -r requirements.txt ``` 3. Install [`ultralytics`](https://github.com/ultralytics/ultralytics) package for ONNX export or TensorRT API building. ``` shell pip install ultralytics ``` 5. Prepare your own PyTorch weight such as `yolov8s.pt` or `yolov8s-seg.pt`. ***NOTICE:*** Please use the latest `CUDA` and `TensorRT`, so that you can achieve the fastest speed ! If you have to use a lower version of `CUDA` and `TensorRT`, please read the relevant issues carefully ! # Normal Usage If you get ONNX from origin [`ultralytics`](https://github.com/ultralytics/ultralytics) repo, you should build engine by yourself. You can only use the `c++` inference code to deserialize the engine and do inference. You can get more information in [`Normal.md`](docs/Normal.md) ! Besides, other scripts won't work. # Export End2End ONNX with NMS You can export your onnx model by `ultralytics` API and add postprocess such as bbox decoder and `NMS` into ONNX model at the same time. ``` shell python3 export-det.py \ --weights yolov8s.pt \ --iou-thres 0.65 \ --conf-thres 0.25 \ --topk 100 \ --opset 11 \ --sim \ --input-shape 1 3 640 640 \ --device cuda:0 ``` #### Description of all arguments - `--weights` : The PyTorch model you trained. - `--iou-thres` : IOU threshold for NMS plugin. - `--conf-thres` : Confidence threshold for NMS plugin. - `--topk` : Max number of detection bboxes. - `--opset` : ONNX opset version, default is 11. - `--sim` : Whether to simplify your onnx model. - `--input-shape` : Input shape for you model, should be 4 dimensions. - `--device` : The CUDA deivce you export engine . You will get an onnx model whose prefix is the same as input weights. # Build End2End Engine from ONNX ### 1. Build Engine by TensorRT ONNX Python api You can export TensorRT engine from ONNX by [`build.py` ](build.py). Usage: ``` shell python3 build.py \ --weights yolov8s.onnx \ --iou-thres 0.65 \ --conf-thres 0.25 \ --topk 100 \ --fp16 \ --device cuda:0 ``` #### Description of all arguments - `--weights` : The ONNX model you download. - `--iou-thres` : IOU threshold for NMS plugin. - `--conf-thres` : Confidence threshold for NMS plugin. - `--topk` : Max number of detection bboxes. - `--fp16` : Whether to export half-precision engine. - `--device` : The CUDA deivce you export engine . You can modify `iou-thres` `conf-thres` `topk` by yourself. ### 2. Export Engine by Trtexec Tools You can export TensorRT engine by [`trtexec`](https://github.com/NVIDIA/TensorRT/tree/main/samples/trtexec) tools. Usage: ``` shell /usr/src/tensorrt/bin/trtexec \ --onnx=yolov8s.onnx \ --saveEngine=yolov8s.engine \ --fp16 ``` **If you installed TensorRT by a debian package, then the installation path of `trtexec` is `/usr/src/tensorrt/bin/trtexec`** **If you installed TensorRT by a tar package, then the installation path of `trtexec` is under the `bin` folder in the path you decompressed** # Build TensorRT Engine by TensorRT API Please see more information in [`API-Build.md`](docs/API-Build.md) ***Notice !!!*** We don't support YOLOv8-seg model now !!! # Inference ## 1. Infer with python script You can infer images with the engine by [`infer-det.py`](infer-det.py) . Usage: ``` shell python3 infer-det.py \ --engine yolov8s.engine \ --imgs data \ --show \ --out-dir outputs \ --device cuda:0 ``` #### Description of all arguments - `--engine` : The Engine you export. - `--imgs` : The images path you want to detect. - `--show` : Whether to show detection results. - `--out-dir` : Where to save detection results images. It will not work when use `--show` flag. - `--device` : The CUDA deivce you use. - `--profile` : Profile the TensorRT engine. ## 2. Infer with C++ You can infer with c++ in [`csrc/detect/end2end`](csrc/detect/end2end) . ### Build: Please set you own librarys in [`CMakeLists.txt`](csrc/detect/end2end/CMakeLists.txt) and modify `CLASS_NAMES` and `COLORS` in [`main.cpp`](csrc/detect/end2end/main.cpp). ``` shell export root=${PWD} cd csrc/detect/end2end mkdir -p build && cd build cmake .. make mv yolov8 ${root} cd ${root} ``` Usage: ``` shell # infer image ./yolov8 yolov8s.engine data/bus.jpg # infer images ./yolov8 yolov8s.engine data # infer video ./yolov8 yolov8s.engine data/test.mp4 # the video path ``` # TensorRT Segment Deploy Please see more information in [`Segment.md`](docs/Segment.md) # TensorRT Pose Deploy Please see more information in [`Pose.md`](docs/Pose.md) # TensorRT Cls Deploy Please see more information in [`Cls.md`](docs/Cls.md) # TensorRT Obb Deploy Please see more information in [`Obb.md`](docs/Obb.md) # DeepStream Detection Deploy See more in [`README.md`](csrc/deepstream/README.md) # Jetson Deploy Only test on `Jetson-NX 4GB`. See more in [`Jetson.md`](docs/Jetson.md) # Profile you engine If you want to profile the TensorRT engine: Usage: ``` shell python3 trt-profile.py --engine yolov8s.engine --device cuda:0 ``` # Refuse To Use PyTorch for Model Inference !!! If you need to break away from pytorch and use tensorrt inference, you can get more information in [`infer-det-without-torch.py`](infer-det-without-torch.py), the usage is the same as the pytorch version, but its performance is much worse. You can use `cuda-python` or `pycuda` for inference. Please install by such command: ```shell pip install cuda-python # or pip install pycuda ``` Usage: ``` shell python3 infer-det-without-torch.py \ --engine yolov8s.engine \ --imgs data \ --show \ --out-dir outputs \ --method cudart ``` #### Description of all arguments - `--engine` : The Engine you export. - `--imgs` : The images path you want to detect. - `--show` : Whether to show detection results. - `--out-dir` : Where to save detection results images. It will not work when use `--show` flag. - `--method` : Choose `cudart` or `pycuda`, default is `cudart`. ", Assign "at most 3 tags" to the expected json: {"id":"11053","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"