yolov5体验

无须安装CUDA，只需要有NVIDIA图形驱动即可

1. 安装Miniconda

miniconda下载地址

1.1 安装细节

• 一个对勾都不要选择
  

1.2 配置环境变量

在环境变量Path中添加如下变量

C:\Server\miniconda
C:\Server\miniconda\Scripts
C:\Server\miniconda\Library\bin

2. 创建虚拟环境

2.1 创建虚拟环境yolov5

conda create -n yolov5

2.2 进入虚拟环境

conda activate yolov5

• 若出现如下错误

CommandNotFoundError: Your shell has not been properly configured to use 'conda activate'.
To initialize your shell, run
 
    $ conda init <SHELL_NAME>
 
Currently supported shells are:
  - bash
  - fish
  - tcsh
  - xonsh
  - zsh
  - powershell
 
See 'conda init --help' for more information and options.
 
IMPORTANT: You may need to close and restart your shell after running 'conda init

Windows：执行如下命令后即可使用命令conda activate yolov5

conda init cmd.exe

Linux：执行如下命令后即可使用命令conda activate yolov5

conda init bash

2.3 更换清华镜像源

清华镜像网站

3. PyTorch安装

3.1 进入pytorch官网下载v1.8.2

• 本人显卡为1650,故选择CUDA 10.2版本执行命令

3.2 网速过慢

1. 使用迅雷下载文件
   https://download.pytorch.org/whl/lts/1.8/cu102/torch-1.8.2%2Bcu102-cp38-cp38-win_amd64.whl
2. 使用pip安装

pip install  C:\torch-1.8.2+cu102-cp38-cp38-win_amd64.whl

3. 执行3.1中命令（本人采用CUDA版本为10.2）

pip3 install torch==1.8.2 torchvision==0.9.2 torchaudio==0.8.2 --extra-index-url https://download.pytorch.org/whl/lts/1.8/cu102

4. yolov5源码下载

4.1 github下载source

https://github.com/ultralytics/yolov5/releases/v7.0/

4.2 下载

• 使用迅雷下载红框选中的源码下载即可
• 解压至C:
  

4.3 修改requirments.txt

1. 注释掉torch和torchvision，若不注释，会使用CPU
2. numpy版本号更改1.20.3
3. Pillow版本号更改为5.3.0

# YOLOv5 🚀 requirements
# Usage: pip install -r requirements.txt

# Base ------------------------------------------------------------------------
gitpython
ipython  # interactive notebook
matplotlib>=3.2.2
numpy==1.20.3
# numpy>=1.18.5
opencv-python>=4.1.1
Pillow==8.3.0
# Pillow>=7.1.2
psutil  # system resources
PyYAML>=5.3.1
requests>=2.23.0
scipy>=1.4.1
thop>=0.1.1  # FLOPs computation
# torch>=1.7.0  # see https://pytorch.org/get-started/locally (recommended)
# torchvision>=0.8.1
tqdm>=4.64.0
# protobuf<=3.20.1  # https://github.com/ultralytics/yolov5/issues/8012

# Logging ---------------------------------------------------------------------
tensorboard>=2.4.1
# clearml>=1.2.0
# comet

# Plotting --------------------------------------------------------------------
pandas>=1.1.4
seaborn>=0.11.0

# Export ----------------------------------------------------------------------
# coremltools>=6.0  # CoreML export
# onnx>=1.9.0  # ONNX export
# onnx-simplifier>=0.4.1  # ONNX simplifier
# nvidia-pyindex  # TensorRT export
# nvidia-tensorrt  # TensorRT export
# scikit-learn<=1.1.2  # CoreML quantization
# tensorflow>=2.4.1  # TF exports (-cpu, -aarch64, -macos)
# tensorflowjs>=3.9.0  # TF.js export
# openvino-dev  # OpenVINO export

# Deploy ----------------------------------------------------------------------
# tritonclient[all]~=2.24.0

# Extras ----------------------------------------------------------------------
# mss  # screenshots
# albumentations>=1.0.3
# pycocotools>=2.0  # COCO mAP
# roboflow
# ultralytics  # HUB https://hub.ultralytics.com

4.4 下载yolov5s.pt

https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5s.pt

4.5 将yolov5s.pt放入yolov5-7.0目录下

4.6 测试

python detect.py --weights .\yolov5s.pt

• 结果

detect: weights=['.\\yolov5s.pt'], source=data\images, data=data\coco128.yaml, imgsz=[640, 640], conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs\detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False, vid_stride=1
YOLOv5  2022-11-22 Python-3.8.18 torch-1.8.2+cu102 CUDA:0 (NVIDIA GeForce GTX 1650, 4096MiB)

Fusing layers...
YOLOv5s summary: 213 layers, 7225885 parameters, 0 gradients, 16.4 GFLOPs
image 1/2 C:\WorkSpace\OpenCV\yolov5-7.0\data\images\bus.jpg: 640x480 4 persons, 1 bus, 14.0ms
image 2/2 C:\WorkSpace\OpenCV\yolov5-7.0\data\images\zidane.jpg: 384x640 2 persons, 2 ties, 11.0ms
Speed: 1.0ms pre-process, 12.5ms inference, 3.5ms NMS per image at shape (1, 3, 640, 640)
Results saved to runs\detect\exp2