yolo目标检测实战

该博客主要介绍了：

1. 如何制作yolo目标检测数据集

2.如何在自己的数据集上训练yolo

3.训练好后的模型如何进行推理

1.数据标注

关于数据如何标注，请查看这篇博文

2.数据集目录结构

重点关注红框内部的结构

images: 图片目录

images/train: 训练集图片

iamges/val: 验证集图片

labels 同理

3.数据配置文件

存放位置

# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ./card_data  # dataset root dir
train: images/train  # train images (relative to 'path') 4 images
val: images/val  # val images (relative to 'path') 4 images
test:  # test images (optional)

names:
  0: name
  1: type
  2: race
  3: attr
  4: lv

names 是物体类别，在这个案例中，我自己制作了一个数据集，目的是为了从图片中提取特定文本片段，下图给出了一个直观示例：

4.训练环境配置

python 3.10

pytorch  2.1  # 2.2版本执行的时候报错了
ultralytics    8.1.20

5.训练

from ultralytics import YOLO

# Load a model
model = YOLO('yolov8n.pt')  # load a pretrained model (recommended for training)

# Train the model
results = model.train(data='./data.yml', epochs=100, imgsz=640, batch=32)

print(1)

6.预测

from ultralytics import YOLO

# Load a model
# model = YOLO('yolov8n.pt')  # load an official model
model = YOLO('./runs/detect/train/weights/best.pt')  # load a custom model

# Predict with the model
results = model('./test_imgs')  # predict on an image

# Run batched inference on a list of images
# results = model(['im1.jpg', 'im2.jpg'])  # return a list of Results objects

# Process results list
for result in results:
    boxes = result.boxes  # Boxes object for bounding box outputs
    masks = result.masks  # Masks object for segmentation masks outputs
    keypoints = result.keypoints  # Keypoints object for pose outputs
    probs = result.probs  # Probs object for classification outputs
    result.show()  # display to screen
    result.save(filename='result.jpg')  # save to disk