yolo5测评-ubuntu环境下

目录

 

一、pytorch环境配置 

二、下载权重

三、运行detect.py

 四、运行test.py

---

一、pytorch环境配置 

vim ~/.condarc                        

channels:
  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/
  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/conda-forge/
  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/msys2/
show_channel_urls: true                       

conda create -n pytorch

source activate pytorch

conda install python

pip install --upgrade pip

pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple/

# pip install -r requirements.txt

# base ----------------------------------------
Cython
matplotlib>=3.2.2
numpy>=1.18.5
opencv-python>=4.1.2
pillow
PyYAML>=5.3
scipy>=1.4.1
tensorboard>=2.2
torch>=1.6.0
torchvision>=0.7.0
tqdm>=4.41.0

# coco ----------------------------------------
# pycocotools>=2.0

# export --------------------------------------
# packaging  # for coremltools
# coremltools==4.0
# onnx>=1.7.0
# scikit-learn==0.19.2  # for coreml quantization

# extras --------------------------------------
# thop  # FLOPS computation
# seaborn  # plotting

二、下载权重

bash download_weights.sh

三、运行detect.py

原图一： 

原图一检测结果： 

原图二： 

原图二检测结果： 

 

 四、运行test.py

真实标注框： 

 yolo5预测结果：

 PR曲线图：

git:https://github.com/lvxiaojie111/yolov5.git