detect baseing tensorRT to speed up. deadline-6.30 15:00

[SHIDi233]

Attemp to use Yolo v10 and integrate it into tensorRT. Now find out a repository (https://github.com/l-sf/Linfer) to use C++ and tensorRT to speed up the detecting action. This afternoon I'll complete and test it.

[SHIDi233]

---

• [x] export tolov10 model to onnx.

  1. download source code from THU

  git clone https://github.com/THU-MIG/yolov10
  cd yolov10
  conda create -n yolov10 python=3.9
  conda activate yolov10
  pip install -r requirements.txt
  pip install -e .

2. modify ultralytics/engine/exporter.py as follows:

   # line 369
   output_names = ["output0", "output1"] if isinstance(self.model, SegmentationModel) else ["output"]
   dynamic = True
          if dynamic:
              dynamic = {'images': {0: 'batch'}} 
              if isinstance(self.model, SegmentationModel):
                  dynamic['output0'] = {0: 'batch', 2: 'anchors'} 
                  dynamic['output1'] = {0: 'batch', 2: 'mask_height', 3: 'mask_width'} 
              elif isinstance(self.model, DetectionModel):
                  dynamic['output'] = {0: 'batch'} 

3. export onnx model There is an unknow problem, so use this pyscript to download your model.

   
   # Import libraries
   import os
   import cv2
   import numpy as np
   import matplotlib.pyplot as plt

from zipfile import ZipFile from urllib.request import urlretrieve import argparse

Define the function to download the model

parser = argparse.ArgumentParser(description='Process some integers.') parser.add_argument( '--model', choices=['yolov10n', 'yolov10s', 'yolov10m', 'yolov10b', 'yolov10l', 'yolov10x'], default='yolov10n', help='Model to download' )

args = parser.parse_args()

def download_model(model):

url = "https://github.com/THU-MIG/yolov10/releases/download/v1.1/" + model + ".pt"
# Downloading zip file using urllib package.
print("Downloading the model...")
urlretrieve(url, model + ".pt")
print("Model downloaded successfully!")

Call the function to download the model

download_model(args.model)

use this command to download.
```bash
   python download.py  --model yolov10n

If downloaded, then start to convert it to onnx.

   yolo export model=yolov10n.pt format=onnx format=onnx opset=13 simplify

---

• [ ] install cuda,tensorRT and opencv.

reference to: https://github.com/l-sf/Notes/blob/main/notes/Ubuntu20.04_install_tutorials.md#%E4%BA%94cuda--cudnn--tensorrt-install

---

• [ ] compile engine

  cd Linfer/workspace
  # 修改其中的onnx路径
  bash compile_engine.sh

  ---

• [ ] build and run

1. build

   cd Linfer
   mkdir build && cd build
   cmake .. && make -j4

2. run

   cd Linfer/workspace
   ./pro