【YOLOv11】ultralytics最新作品yolov11 AND 模型的训练、推理、验证、导出以及使用

news2024/11/26 1:58:55

一 ultralytics公司的最新作品YOLOV11

1 yolov11的创新

2 安装YOLOv11

3 PYTHON Guide

二训练

三验证

四推理

五导出模型

六使用

文档：https://docs.ultralytics.com/models/yolo11/

代码链接：https://github.com/ultralytics/ultralytics

Performance Metrics

关键特性

◆增强的特征提取能力：YOLO11采用了改进的主干和颈部架构，增强了特征提取能力，能够实现更精确的目标检测和复杂任务的执行。

◆优化的效率和速度：YOLO11引入了精细化的架构设计和优化的训练流程，提供更快的处理速度，并在准确性和性能之间保持最佳平衡。

◆参数更少、精度更高：通过模型设计的改进，YOLO11m在COCO数据集上实现了更高的平均精度（mAP），同时使用的参数比YOLOv8m少22%，使其在计算上更加高效，而不牺牲准确性。

◆跨环境的适应性：YOLO11可以无缝部署在各种环境中，包括边缘设备、云平台和支持NVIDIA GPU的系统，确保最大的灵活性。

◆支持广泛任务：无论是目标检测、实例分割、图像分类、姿态估计还是定向目标检测（OBB），YOLO11都旨在应对一系列计算机视觉挑战。

支持的任务和模式

YOLO11建立在YOLOv8中引入的多功能模型范围之上，为各种计算机视觉任务提供增强的支持:

该表提供了YOLO11模型变体的概述，展示了它们在特定任务中的适用性以及与Inference、Validation、Training和Export等操作模式的兼容性。从实时检测到复杂的分割任务，这种灵活性使YOLO11适用于计算机视觉的广泛应用。

一 ultralytics公司的最新作品YOLOV11

1 yolov11的创新

■ yolov8 VS yolov11

YOLOv5，YOLOv8和YOLOv11均是ultralytics公司的作品，ultralytics出品必属精品。

具体创新点：

① 深度（depth）和宽度（width）

YOLOv8和YOLOv11是基本上完全不同。

② C3k2机制

C3k2有参数为c3k，其中在网络的浅层c3k设置为False。C3k2就相当于YOLOv8中的C2f。

③ C2PSA机制

下图为C2PSA机制的原理图。

④ 解耦头

解耦头中的分类检测头增加了两个DWConv。

▲Conv

def autopad(k, p=None, d=1):  # kernel, padding, dilation

    """Pad to 'same' shape outputs."""

    if d > 1:

        k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k]  # actual kernel-size

    if p is None:

        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad

return p


class Conv(nn.Module):

    """Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)."""


    default_act = nn.SiLU()  # default activation


    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):

        """Initialize Conv layer with given arguments including activation."""

        super().__init__()

        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False)

        self.bn = nn.BatchNorm2d(c2)

        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()


    def forward(self, x):

        """Apply convolution, batch normalization and activation to input tensor."""

        return self.act(self.bn(self.conv(x)))


    def forward_fuse(self, x):

        """Perform transposed convolution of 2D data."""

        return self.act(self.conv(x))

▲Conv2d

torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, padding_mode='zeros')

▲DWConv

DWConv 代表 Depthwise Convolution（深度卷积），是一种在卷积神经网络中常用的高效卷积操作。它主要用于减少计算复杂度和参数量。

class DWConv(Conv):

    """Depth-wise convolution."""


    def __init__(self, c1, c2, k=1, s=1, d=1, act=True):  # ch_in, ch_out, kernel, stride, dilation, activation

        """Initialize Depth-wise convolution with given parameters."""

        super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), d=d, act=act)

2 安装YOLOv11

# Clone the ultralytics repository
git clone https://github.com/ultralytics/ultralytics

# 创建conda环境yolov11
conda create -n yolov11 python=3.9
conda activate yolov11

# Navigate to the cloned directory
cd ultralytics
# Install the package in editable mode for development
pip install -e . -i https://pypi.tuna.tsinghua.edu.cn/simple

pip install onnx -i  https://pypi.tuna.tsinghua.edu.cn/simple
pip install onnxslim -i  https://pypi.tuna.tsinghua.edu.cn/simple
pip install onnxruntime -i  https://pypi.tuna.tsinghua.edu.cn/simple
# opencv
pip install opencv-python -i  https://pypi.tuna.tsinghua.edu.cn/simple
pip install opencv-contrib-python -i  https://pypi.tuna.tsinghua.edu.cn/simple

3 PYTHON Guide

from ultralytics import YOLO

# Create a new YOLO model from scratch

model = YOLO("yolo11n.yaml")

# Load a pretrained YOLO model (recommended for training)

model = YOLO("yolo11n.pt")

# Train the model using the 'coco8.yaml' dataset for 3 epochs

results = model.train(data="coco8.yaml", epochs=3)

# Evaluate the model's performance on the validation set

results = model.val()

# Perform object detection on an image using the model

results = model("https://ultralytics.com/images/bus.jpg")

# Export the model to ONNX format

success = model.export(format="onnx")

CLI AND PYTHON 示例：https://docs.ultralytics.com/tasks/detect/#models

二训练

# Build a new model from YAML and start training from scratch

yolo detect train data=coco8.yaml model=yolo11n.yaml epochs=100 imgsz=640

# Start training from a pretrained *.pt model

yolo detect train data=coco8.yaml model=yolo11n.pt epochs=100 imgsz=640

# Build a new model from YAML, transfer pretrained weights to it and start training

yolo detect train data=coco8.yaml model=yolo11n.yaml pretrained=yolo11n.pt epochs=100 imgsz=640

示例：

# Load a COCO-pretrained YOLO11n model and train it on the COCO8 example dataset for 100 epochs

yolo train model=yolo11n.pt data=coco8.yaml epochs=100 imgsz=640

训练产物：

三验证

yolo detect val model=yolo11n.pt  # val official model

# 使用自己的模型

yolo detect val model=path/to/best.pt  # val custom model

示例：

yolo detect val model=yolo11n.pt

效果图：

四推理

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

# 使用自己的模型

yolo detect predict model=path/to/best.pt source='https://ultralytics.com/images/bus.jpg'  # predict with custom model

示例：

yolo detect predict model=yolo11n.pt source='ultralytics/assets/bus.jpg'

效果图：

五导出模型

yolo export model=yolo11n.pt format=onnx  # export official model

yolo export model=path/to/best.pt format=onnx  # export custom trained model

示例：

yolo export model=yolo11n.pt format=onnx

六使用

代码如下：

from ultralytics import YOLO
# Load a model
model = YOLO("yolo11n.onnx")  # load a custom model
# Predict with the model
results = model("ultralytics/assets/zidane.jpg")
# 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
    # obb = result.obb  # Oriented boxes object for OBB outputs
    result.show()  # display to screen
    result.save(filename="result.jpg")  # save to disk
pass

效果图：