Yolov5n V7.0

🚀 YOLOv5目標檢測項目

本項目基於YOLOv5實現目標檢測，可用於計算機視覺領域的物體識別任務。支持模型的安裝、預測和在自定義數據集上進行微調。

🚀 快速開始

安裝YOLOv5

pip install -U yolov5

加載模型並進行預測

import yolov5

# load model
model = yolov5.load('fcakyon/yolov5n-v7.0')
  
# set model parameters
model.conf = 0.25  # NMS confidence threshold
model.iou = 0.45  # NMS IoU threshold
model.agnostic = False  # NMS class-agnostic
model.multi_label = False  # NMS multiple labels per box
model.max_det = 1000  # maximum number of detections per image

# set image
img = 'https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg'

# perform inference
results = model(img)

# inference with larger input size
results = model(img, size=640)

# inference with test time augmentation
results = model(img, augment=True)

# parse results
predictions = results.pred[0]
boxes = predictions[:, :4] # x1, y1, x2, y2
scores = predictions[:, 4]
categories = predictions[:, 5]

# show detection bounding boxes on image
results.show()

# save results into "results/" folder
results.save(save_dir='results/')

在自定義數據集上微調模型

yolov5 train --img 640 --batch 16 --weights fcakyon/yolov5n-v7.0 --epochs 10 --device cuda:0

📦 安裝指南

使用以下命令安裝YOLOv5：

pip install -U yolov5

💻 使用示例

基礎用法

import yolov5

# load model
model = yolov5.load('fcakyon/yolov5n-v7.0')
  
# set model parameters
model.conf = 0.25  # NMS confidence threshold
model.iou = 0.45  # NMS IoU threshold
model.agnostic = False  # NMS class-agnostic
model.multi_label = False  # NMS multiple labels per box
model.max_det = 1000  # maximum number of detections per image

# set image
img = 'https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg'

# perform inference
results = model(img)

# parse results
predictions = results.pred[0]
boxes = predictions[:, :4] # x1, y1, x2, y2
scores = predictions[:, 4]
categories = predictions[:, 5]

# show detection bounding boxes on image
results.show()

# save results into "results/" folder
results.save(save_dir='results/')

高級用法

# inference with larger input size
results = model(img, size=640)

# inference with test time augmentation
results = model(img, augment=True)

📄 許可證

本項目採用GPL-3.0許可證。

📚 詳細文檔

模型信息

標籤信息

本項目包含以下標籤：

• 目標檢測
• 計算機視覺
• 視覺
• YOLO
• YOLOv5