做 ps pr 赚钱的 网站,wordpress国内视频教程,ps做网站浏览器预览,大都会app用不了Yolov8目标检测 目录 Yolov8目标检测一、准备数据集二、源码下载配置2.1 下载库2.2 修改配置2.3 训练2.4 验证2.5 测试2.6 模型导出2.7 本地测试 一、准备数据集
Yolov8只支持yolo格式的数据#xff0c;所以#xff0c;需要将数据集格式调整为
datasets|images|train|00000…Yolov8目标检测 目录 Yolov8目标检测一、准备数据集二、源码下载配置2.1 下载库2.2 修改配置2.3 训练2.4 验证2.5 测试2.6 模型导出2.7 本地测试 一、准备数据集
Yolov8只支持yolo格式的数据所以需要将数据集格式调整为
datasets|images|train|000000.jpg000001.jpgtest|100000.jpg100001.jpglabels|train|000000.txt000001.txttest|100000.txt100001.txt二、源码下载配置
2.1 下载库
pip install ultralytics2.2 修改配置
新建一个模型配置文件yolov8.yaml里面添加数据路径和类别
train: /home/dxfcv/workspace/sunsirui/label/dataset/train/images
val: /home/dxfcv/workspace/sunsirui/label/dataset/test/images
nc: 3
names: [cement,metal,plastics]2.3 训练
具体参数可参看链接
yolo taskdetect modetrain modelyolov8s.pt datayolov8.yaml batch8 epochs100 imgsz640 workers16 device0训练完会生成一个文件夹存放所有结果
2.4 验证
yolo taskdetect modeval modelruns/detect/train/weights/best.pt datayolov8.yaml device02.5 测试
yolo taskdetect modepredict modelruns/detect/train/weights/best.pt source/home/dxfcv/workspace/sunsirui/label/dataset/images device0在生成的predict文件夹下就能看到效果了(像标注的效果)
2.6 模型导出
yolo taskdetect modeexport modelruns/detect/train/weights/best.pt formatonnx2.7 本地测试
使用不同方式(比如opencv)调图片去检测结果会在对应文件夹下出现
from ultralytics import YOLO
from PIL import Image
import cv2model YOLO(/home/dxfcv/workspace/sunsirui/label/dataset/runs/detect/train/weights/best.onnx)
# accepts all formats - image/dir/Path/URL/video/PIL/ndarray. 0 for webcam
# results model.predict(source0)
# results model.predict(sourcefolder, showTrue) # Display preds. Accepts all YOLO predict arguments# # from PIL
# im1 Image.open(bus.jpg)
# results model.predict(sourceim1, saveTrue) # save plotted images# from ndarray
im2 cv2.imread(/home/dxfcv/workspace/sunsirui/label/dataset/images/camera2_200025.jpg)
results model.predict(sourceim2, saveTrue, save_txtTrue) # save predictions as labels# from list of PIL/ndarray
# results model.predict(source[im1, im2]
