Yolov8 照片偵測後如何抓物體座標位置 @ NetYea 網頁設計

結果圖：
Yolov8 照片偵測後如何抓物體座標位置

座標：

[[ 16 290]
[412 491]
[740 626]
[283 631]
[146 651]
[ 32 710]]
5.0
image 1/1 D:\yolo\bus.jpg: 640x480 4 persons, 1 bus, 1 stop sign, 83.9ms
Speed: 3.0ms preprocess, 83.9ms inference, 4.0ms postprocess per image at shape (1, 3, 640, 480)
tensor([[ 22.3412, 228.0822, 802.0841, 754.3939]], device='cuda:0')
準確率 0.879738450050354
x,y: [[412 491]]
0.0
tensor([[ 47.5999, 398.8344, 244.2552, 903.1386]], device='cuda:0')
準確率 0.873720109462738
x,y: [[146 651]]
0.0
tensor([[670.3670, 376.9174, 810.0000, 875.0829]], device='cuda:0')
準確率 0.8693700432777405
x,y: [[740 626]]
0.0
tensor([[220.5713, 405.7240, 344.5589, 857.2506]], device='cuda:0')
準確率 0.819391667842865
x,y: [[283 631]]
11.0
tensor([[7.7698e-02, 2.5441e+02, 3.2119e+01, 3.2465e+02]], device='cuda:0')
準確率 0.44594067335128784
x,y: [[ 16 290]]
0.0
tensor([[3.2650e-02, 5.4988e+02, 6.4001e+01, 8.6930e+02]], device='cuda:0')
準確率 0.29976797103881836
x,y: [[ 32 710]]

複製代碼

NetYea 網頁設計

NetYea 網頁設計發表在痞客邦留言(0) 人氣()

NetYea 網頁設計