Football Players Detection using YOLOV11 | Kaggle

!pip install comet_ml

import comet_mlcomet_ml.login(project_name="c")

?Comet - Build Better Models Faster

?yolov11訓練

100輪一眨眼訓練完了

然而comet接不到yolo的sdk

優秀

?訓練17輪map就0.99了

?

v5訓練100輪才0.6

有了，就是訓練輪次不夠

效果和11比差遠了

?map在50輪后才穩定上升

有邊框信息了

本地detect讀取邊界框信息

w torch==2.5.1 torchvision --index-url https://download.pytorch.org/whl/cu124
w ultralytics

windows下torch能要我命 睡個午覺先

from ultralytics import YOLO
import numpy as np
# 加載模型
model = YOLO('./best.pt')# 執行預測并獲取結果
results = model.predict(source='./valid/images/screenshot-20250504103355_png.rf.71febf531b60b1e416aece6136e28388.jpg')# 遍歷結果
for result in results:boxes = result.boxes  # 獲取所有檢測到的邊框for box in boxes:print("BoundingBox: ", box.xyxy)  # 輸出邊框坐標(x1, y1, x2, y2)print("Confidence: ", box.conf)   # 置信度分數print("Class: ", box.cls)         # 類別IDprint("物體是: ",model.names[int(box.cls.item()) ],"范圍為: ",box.xyxy.cpu().numpy())