YOLOv11尝鲜测试五分钟极简配置

给算法爸爸上香2024-10-06 12:35

ultralytics团队在最近又推出了YOLOv11，不知道在有生之年能不能看到YOLOv100呢哈哈。

根据官方文档，在 Python>=3.8并且PyTorch>=1.8的环境下即可安装YOLOv11，因此之前YOLOv8的环境是可以直接用的。

安装YOLOv11：

bash 复制代码

pip install ultralytics

命令行测试：

bash 复制代码

yolo predict model=yolo11n.pt source='https://ultralytics.com/images/bus.jpg'

或者

bash 复制代码

yolo predict model=yolo11n.pt source='=bus.jpg'

得到结果：

bash 复制代码

Ultralytics 8.3.1 🚀 Python-3.9.19 torch-1.8.0+cu111 CUDA:0 (NVIDIA GeForce RTX 3070 Laptop GPU, 8192MiB)
YOLO11n summary (fused): 238 layers, 2,616,248 parameters, 0 gradients, 6.5 GFLOPs

image 1/1 D:\document\VScode_workspace\ultralytics-8.3.1\bus.jpg: 640x480 4 persons, 1 bus, 0.0ms
Speed: 11.5ms preprocess, 0.0ms inference, 0.0ms postprocess per image at shape (1, 3, 640, 480)
Results saved to runs\detect\predict2
💡 Learn more at https://docs.ultralytics.com/modes/predict
VS Code: view Ultralytics VS Code Extension ⚡ at https://docs.ultralytics.com/integrations/vscode

python脚本测试：

python 复制代码

from ultralytics import YOLO

# Load a model
model = YOLO("yolo11n.pt")

# Train the model
train_results = model.train(
    data="coco8.yaml",  # path to dataset YAML
    epochs=100,  # number of training epochs
    imgsz=640,  # training image size
    device="cpu",  # device to run on, i.e. device=0 or device=0,1,2,3 or device=cpu
)

# Evaluate model performance on the validation set
metrics = model.val()

# Perform object detection on an image
results = model("zidane.jpg")
results[0].show()

# Export the model to ONNX format
path = model.export(format="onnx")  # return path to exported model

测试结果如下：