yoloV8基础使用教程

$$yoloV8基础使用教程$$

---

yoloV8代码：https://github.com/ultralytics/ultralytics

官方文档

yolov8多折交叉验证

---

安装

pip install ultralytics

使用

---

if __name__ == '__main__':
    # from ultralytics.yolo.engine.model import YOLO
    from ultralytics import YOLO
    # 1 加载模型
    model = YOLO(r'yolov8s-seg.pt')  # load a pretrained model (recommended for training)
    # 2 训练模型
    model.train(data='Test.yaml', epochs=500, imgsz=1801,batch=6,project="./test",name="Test")
    # 3 验证模型
    metrics = model.val(data="Test.yaml")  # 在验证集上评估模型性能
    # 4 模型预测
    results = model.predict(source=r"D:\dataset\Test\images\val",  imgsz=1801 ,save=True,batch=2)  # save plotted images
    # 5 导出所需模式（以onnx为例）
    model.export(format='onnx',imgsz=(701,1801)) # imgsz 高宽

Test.yaml

path: D:\dataset\Test  # dataset root dir
train: images/train  # train images (relative to 'path')
val: images/val  # val images (relative to 'path')
test:  # test images (optional)

# Classes
names:
  0: C1
  1: C2

一 加载模型的三种方式和训练模型

from ultralytics import YOLO

# Load a model
model = YOLO('yolov8n.yaml')  # build a new model from YAML
model = YOLO('yolov8n.pt')  # load a pretrained model (recommended for training)
model = YOLO('yolov8n.yaml').load('yolov8n.pt')  # build from YAML and transfer weights

# Train the model
model.train(data='coco128.yaml', epochs=100, imgsz=640)

训练可传参数

二 预测

inputs = [img, img]  # list of numpy arrays
results = model(inputs)  # list of Results objects

for result in results:
    boxes = result.boxes  # Boxes object for bbox outputs
    masks = result.masks  # Masks object for segmentation masks outputs
    probs = result.probs  # Class probabilities for classification outputs

results = model.predict(source=r"D:\dataset\Test\images\val", save=True,batch=1)

预测可传数据源

预测可传参数

三 验证评估

from ultralytics import YOLO

# Load a model
model = YOLO('yolov8n.pt')  # load an official model
model = YOLO('path/to/best.pt')  # load a custom model

# Validate the model
metrics = model.val()  # no arguments needed, dataset and settings remembered
metrics.box.map    # map50-95
metrics.box.map50  # map50
metrics.box.map75  # map75
metrics.box.maps   # a list contains map50-95 of each category

评估可传参数

四 导出

from ultralytics import YOLO

# Load a model
model = YOLO('yolov8n.pt')  # load an official model
model = YOLO('path/to/best.pt')  # load a custom trained

# Export the model
model.export(format='onnx')

导出可传参数

# Map head to model, trainer, validator, and predictor classes
TASK_MAP = {
    'classify': [
        ClassificationModel, yolo.v8.classify.ClassificationTrainer, yolo.v8.classify.ClassificationValidator,
        yolo.v8.classify.ClassificationPredictor],
    'detect': [
        DetectionModel, yolo.v8.detect.DetectionTrainer, yolo.v8.detect.DetectionValidator,
        yolo.v8.detect.DetectionPredictor],
    'segment': [
        SegmentationModel, yolo.v8.segment.SegmentationTrainer, yolo.v8.segment.SegmentationValidator,
        yolo.v8.segment.SegmentationPredictor],
    'pose': [PoseModel, yolo.v8.pose.PoseTrainer, yolo.v8.pose.PoseValidator, yolo.v8.pose.PosePredictor]}

根据task选择

self.trainer = TASK_MAP[self.task][1](overrides=overrides, _callbacks=self.callbacks,algObj=algObj)