yolov8 tensorrt python推理

资源文件列表(大概)

文件名

大小

YOLOv8-TensorRT-main/

YOLOv8-TensorRT-main/build.py

1.87KB

YOLOv8-TensorRT-main/cmd.txt

864B

YOLOv8-TensorRT-main/config.py

17.9KB

YOLOv8-TensorRT-main/csrc/

YOLOv8-TensorRT-main/csrc/cls/

YOLOv8-TensorRT-main/csrc/cls/normal/

YOLOv8-TensorRT-main/csrc/cls/normal/cmake/

YOLOv8-TensorRT-main/csrc/cls/normal/cmake/FindTensorRT.cmake

5.17KB

YOLOv8-TensorRT-main/csrc/cls/normal/cmake/Function.cmake

408B

YOLOv8-TensorRT-main/csrc/cls/normal/CMakeLists.txt

1.85KB

YOLOv8-TensorRT-main/csrc/cls/normal/include/

YOLOv8-TensorRT-main/csrc/cls/normal/include/common.hpp

3.52KB

YOLOv8-TensorRT-main/csrc/cls/normal/include/filesystem.hpp

187.37KB

YOLOv8-TensorRT-main/csrc/cls/normal/include/yolov8-cls.hpp

7.37KB

YOLOv8-TensorRT-main/csrc/cls/normal/main.cpp

61.69KB

YOLOv8-TensorRT-main/csrc/deepstream/

YOLOv8-TensorRT-main/csrc/deepstream/CMakeLists.txt

1.52KB

YOLOv8-TensorRT-main/csrc/deepstream/config_yoloV8.txt

3.06KB

YOLOv8-TensorRT-main/csrc/deepstream/custom_bbox_parser/

YOLOv8-TensorRT-main/csrc/deepstream/custom_bbox_parser/nvdsparsebbox_yoloV8.cpp

4.77KB

YOLOv8-TensorRT-main/csrc/deepstream/deepstream_app_config.txt

2.56KB

YOLOv8-TensorRT-main/csrc/deepstream/labels.txt

625B

YOLOv8-TensorRT-main/csrc/deepstream/README.md

2.08KB

YOLOv8-TensorRT-main/csrc/detect/

YOLOv8-TensorRT-main/csrc/detect/end2end/

YOLOv8-TensorRT-main/csrc/detect/end2end/cmake/

YOLOv8-TensorRT-main/csrc/detect/end2end/cmake/FindTensorRT.cmake

5.17KB

YOLOv8-TensorRT-main/csrc/detect/end2end/cmake/Function.cmake

408B

YOLOv8-TensorRT-main/csrc/detect/end2end/CMakeLists.txt

1.85KB

YOLOv8-TensorRT-main/csrc/detect/end2end/include/

YOLOv8-TensorRT-main/csrc/detect/end2end/include/common.hpp

3.71KB

YOLOv8-TensorRT-main/csrc/detect/end2end/include/filesystem.hpp

187.37KB

YOLOv8-TensorRT-main/csrc/detect/end2end/include/yolov8.hpp

11.8KB

YOLOv8-TensorRT-main/csrc/detect/end2end/main.cpp

5.6KB

YOLOv8-TensorRT-main/csrc/detect/normal/

YOLOv8-TensorRT-main/csrc/detect/normal/cmake/

YOLOv8-TensorRT-main/csrc/detect/normal/cmake/FindTensorRT.cmake

5.17KB

YOLOv8-TensorRT-main/csrc/detect/normal/cmake/Function.cmake

408B

YOLOv8-TensorRT-main/csrc/detect/normal/CMakeLists.txt

1.99KB

YOLOv8-TensorRT-main/csrc/detect/normal/include/

YOLOv8-TensorRT-main/csrc/detect/normal/include/common.hpp

3.71KB

YOLOv8-TensorRT-main/csrc/detect/normal/include/filesystem.hpp

187.37KB

YOLOv8-TensorRT-main/csrc/detect/normal/include/yolov8.hpp

13.2KB

YOLOv8-TensorRT-main/csrc/detect/normal/main.cpp

5.81KB

YOLOv8-TensorRT-main/csrc/jetson/

YOLOv8-TensorRT-main/csrc/jetson/detect/

YOLOv8-TensorRT-main/csrc/jetson/detect/CMakeLists.txt

1.53KB

YOLOv8-TensorRT-main/csrc/jetson/detect/include/

YOLOv8-TensorRT-main/csrc/jetson/detect/include/common.hpp

4.34KB

YOLOv8-TensorRT-main/csrc/jetson/detect/include/yolov8.hpp

9.75KB

YOLOv8-TensorRT-main/csrc/jetson/detect/main.cpp

5.41KB

YOLOv8-TensorRT-main/csrc/jetson/pose/

YOLOv8-TensorRT-main/csrc/jetson/pose/CMakeLists.txt

1.68KB

YOLOv8-TensorRT-main/csrc/jetson/pose/include/

YOLOv8-TensorRT-main/csrc/jetson/pose/include/common.hpp

4.37KB

YOLOv8-TensorRT-main/csrc/jetson/pose/include/yolov8-pose.hpp

12.65KB

YOLOv8-TensorRT-main/csrc/jetson/pose/main.cpp

6.81KB

YOLOv8-TensorRT-main/csrc/jetson/segment/

YOLOv8-TensorRT-main/csrc/jetson/segment/CMakeLists.txt

1.68KB

YOLOv8-TensorRT-main/csrc/jetson/segment/include/

YOLOv8-TensorRT-main/csrc/jetson/segment/include/common.hpp

4.37KB

YOLOv8-TensorRT-main/csrc/jetson/segment/include/yolov8-seg.hpp

12.7KB

YOLOv8-TensorRT-main/csrc/jetson/segment/main.cpp

6.17KB

YOLOv8-TensorRT-main/csrc/obb/

YOLOv8-TensorRT-main/csrc/obb/normal/

YOLOv8-TensorRT-main/csrc/obb/normal/cmake/

YOLOv8-TensorRT-main/csrc/obb/normal/cmake/FindTensorRT.cmake

5.17KB

YOLOv8-TensorRT-main/csrc/obb/normal/cmake/Function.cmake

408B

YOLOv8-TensorRT-main/csrc/obb/normal/CMakeLists.txt

1.84KB

YOLOv8-TensorRT-main/csrc/obb/normal/include/

YOLOv8-TensorRT-main/csrc/obb/normal/include/common.hpp

3.7KB

YOLOv8-TensorRT-main/csrc/obb/normal/include/filesystem.hpp

187.37KB

YOLOv8-TensorRT-main/csrc/obb/normal/include/yolov8-obb.hpp

11.19KB

YOLOv8-TensorRT-main/csrc/obb/normal/main.cpp

5.09KB

YOLOv8-TensorRT-main/csrc/pose/

YOLOv8-TensorRT-main/csrc/pose/normal/

YOLOv8-TensorRT-main/csrc/pose/normal/cmake/

YOLOv8-TensorRT-main/csrc/pose/normal/cmake/FindTensorRT.cmake

5.17KB

YOLOv8-TensorRT-main/csrc/pose/normal/cmake/Function.cmake

408B

YOLOv8-TensorRT-main/csrc/pose/normal/CMakeLists.txt

1.99KB

YOLOv8-TensorRT-main/csrc/pose/normal/include/

YOLOv8-TensorRT-main/csrc/pose/normal/include/common.hpp

3.74KB

YOLOv8-TensorRT-main/csrc/pose/normal/include/filesystem.hpp

187.37KB

YOLOv8-TensorRT-main/csrc/pose/normal/include/yolov8-pose.hpp

12.69KB

YOLOv8-TensorRT-main/csrc/pose/normal/main.cpp

6.98KB

YOLOv8-TensorRT-main/csrc/segment/

YOLOv8-TensorRT-main/csrc/segment/normal/

YOLOv8-TensorRT-main/csrc/segment/normal/CMakeLists.txt

1.7KB

YOLOv8-TensorRT-main/csrc/segment/normal/include/

YOLOv8-TensorRT-main/csrc/segment/normal/include/common.hpp

4.37KB

YOLOv8-TensorRT-main/csrc/segment/normal/include/yolov8-seg.hpp

13.59KB

YOLOv8-TensorRT-main/csrc/segment/normal/main.cpp

6.18KB

YOLOv8-TensorRT-main/csrc/segment/simple/

YOLOv8-TensorRT-main/csrc/segment/simple/CMakeLists.txt

1.7KB

YOLOv8-TensorRT-main/csrc/segment/simple/include/

YOLOv8-TensorRT-main/csrc/segment/simple/include/common.hpp

4.37KB

YOLOv8-TensorRT-main/csrc/segment/simple/include/yolov8-seg.hpp

12.74KB

YOLOv8-TensorRT-main/csrc/segment/simple/main.cpp

6.18KB

YOLOv8-TensorRT-main/data/

YOLOv8-TensorRT-main/data/bus.jpg

476.01KB

YOLOv8-TensorRT-main/data/highway.mp4

3.74MB

YOLOv8-TensorRT-main/data/zidane.jpg

164.99KB

YOLOv8-TensorRT-main/docs/

YOLOv8-TensorRT-main/docs/API-Build.md

719B

YOLOv8-TensorRT-main/docs/Cls.md

2.61KB

YOLOv8-TensorRT-main/docs/Jetson.md

4.66KB

YOLOv8-TensorRT-main/docs/Normal.md

2.11KB

YOLOv8-TensorRT-main/docs/Obb.md

2.73KB

YOLOv8-TensorRT-main/docs/Pose.md

2.89KB

YOLOv8-TensorRT-main/docs/Segment.md

6.22KB

YOLOv8-TensorRT-main/docs/star.md

172B

YOLOv8-TensorRT-main/export-det.py

3.06KB

YOLOv8-TensorRT-main/infer-det-without-torch.py

2.97KB

YOLOv8-TensorRT-main/infer-det.py

3.12KB

YOLOv8-TensorRT-main/models/

YOLOv8-TensorRT-main/models/api.py

13.45KB

YOLOv8-TensorRT-main/models/common.py

6.26KB

YOLOv8-TensorRT-main/models/cudart_api.py

6.02KB

YOLOv8-TensorRT-main/models/engine.py

14.13KB

YOLOv8-TensorRT-main/models/pycuda_api.py

5.21KB

YOLOv8-TensorRT-main/models/torch_utils.py

3.96KB

YOLOv8-TensorRT-main/models/utils.py

8.48KB

YOLOv8-TensorRT-main/models/__init__.py

556B

YOLOv8-TensorRT-main/models/__pycache__/

YOLOv8-TensorRT-main/models/__pycache__/common.cpython-39.pyc

6.82KB

YOLOv8-TensorRT-main/models/__pycache__/cudart_api.cpython-39.pyc

5.06KB

YOLOv8-TensorRT-main/models/__pycache__/engine.cpython-39.pyc

12.13KB

YOLOv8-TensorRT-main/models/__pycache__/torch_utils.cpython-39.pyc

3.31KB

YOLOv8-TensorRT-main/models/__pycache__/utils.cpython-39.pyc

7.25KB

YOLOv8-TensorRT-main/models/__pycache__/__init__.cpython-39.pyc

554B

YOLOv8-TensorRT-main/onnx_inference.py

3.94KB

YOLOv8-TensorRT-main/output/

YOLOv8-TensorRT-main/output/output_video.mp4

16.92MB

YOLOv8-TensorRT-main/README.md

7.12KB

YOLOv8-TensorRT-main/requirements.txt

158B

YOLOv8-TensorRT-main/trt-profile.py

767B

YOLOv8-TensorRT-main/video_inference.py

4.32KB

YOLOv8-TensorRT-main/video_inference_without_torch.py

3.78KB

YOLOv8-TensorRT-main/weights/

YOLOv8-TensorRT-main/weights/yolov8n.engine

9.58MB

YOLOv8-TensorRT-main/weights/yolov8n.onnx

12.24MB

YOLOv8-TensorRT-main/weights/yolov8n.pt

6.23MB

YOLOv8-TensorRT-main/__pycache__/

YOLOv8-TensorRT-main/__pycache__/config.cpython-39.pyc

14.56KB

资源内容介绍

yolov8 tensorrt python推理

# YOLOv8-TensorRT`YOLOv8` using TensorRT accelerate !---[![Build Status](https://img.shields.io/endpoint.svg?url=https%3A%2F%2Factions-badge.atrox.dev%2Fatrox%2Fsync-dotenv%2Fbadge&style=flat)](https://github.com/triple-Mu/YOLOv8-TensorRT)[![Python Version](https://img.shields.io/badge/Python-3.8--3.10-FFD43B?logo=python)](https://github.com/triple-Mu/YOLOv8-TensorRT)[![img](https://badgen.net/badge/icon/tensorrt?icon=azurepipelines&label)](https://developer.nvidia.com/tensorrt)[![C++](https://img.shields.io/badge/CPP-11%2F14-yellow)](https://github.com/triple-Mu/YOLOv8-TensorRT)[![img](https://badgen.net/github/license/triple-Mu/YOLOv8-TensorRT)](https://github.com/triple-Mu/YOLOv8-TensorRT/blob/main/LICENSE)[![img](https://badgen.net/github/prs/triple-Mu/YOLOv8-TensorRT)](https://github.com/triple-Mu/YOLOv8-TensorRT/pulls)[![img](https://img.shields.io/github/stars/triple-Mu/YOLOv8-TensorRT?color=ccf)](https://github.com/triple-Mu/YOLOv8-TensorRT)---# Prepare the environment1. Install `CUDA` follow [`CUDA official website`](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#download-the-nvidia-cuda-toolkit). ð RECOMMENDED `CUDA` >= 11.42. Install `TensorRT` follow [`TensorRT official website`](https://developer.nvidia.com/nvidia-tensorrt-8x-download). ð RECOMMENDED `TensorRT` >= 8.42. 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 UsageIf 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 NMSYou can export your onnx model by `ultralytics` API and add postprocess such as bbox decoder and `NMS` into ONNX model at the same time.``` shellpython3 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 apiYou can export TensorRT engine from ONNX by [`build.py` ](build.py).Usage:``` shellpython3 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 ToolsYou 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 APIPlease 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 scriptYou can infer images with the engine by [`infer-det.py`](infer-det.py) .Usage:``` shellpython3 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).``` shellexport root=${PWD}cd csrc/detect/end2endmkdir -p build && cd buildcmake ..makemv 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 DeployPlease see more information in [`Segment.md`](docs/Segment.md)# TensorRT Pose DeployPlease see more information in [`Pose.md`](docs/Pose.md)# TensorRT Cls DeployPlease see more information in [`Cls.md`](docs/Cls.md)# TensorRT Obb DeployPlease see more information in [`Obb.md`](docs/Obb.md)# DeepStream Detection DeploySee more in [`README.md`](csrc/deepstream/README.md)# Jetson DeployOnly test on `Jetson-NX 4GB`.See more in [`Jetson.md`](docs/Jetson.md)# Profile you engineIf you want to profile the TensorRT engine:Usage:``` shellpython3 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:```shellpip install cuda-python# orpip install pycuda```Usage:``` shellpython3 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`.

用户评论 (0)

发表评论

您的昵称:

评分

评论内容:

验证码:

yolov8 tensorrt python推理

资源文件列表(大概)

资源内容介绍

用户评论 (0)

发表评论

相关资源

InstantTexture.zip

数据结构任务书.zip

ROS 2 密钥 ros.key

linkage-mapper3.0