yolo v3 照着论文一步步复现-iou

最新推荐文章于 2024-08-05 18:41:17 发布

松子木木

最新推荐文章于 2024-08-05 18:41:17 发布

阅读量188

点赞数

分类专栏：硕士阶段文章标签： pytorch 深度学习 python

本文链接：https://blog.csdn.net/puiopp63/article/details/120561662

版权

硕士阶段专栏收录该内容

22 篇文章 5 订阅

订阅专栏

pytorch 1.7.1 py3.8_cuda102_cudnn7_0
用pytorch提供的集成函数替换原有的手写函数
iou函数：

torchvision.ops.box_iou(boxes, boxes)

from torchvision import ops
import torch

def compute_iou(rec1, rec2):
    """
    computing IoU
    :param rec1: (y0, x0, y1, x1), which reflects
            (top, left, bottom, right)
    :param rec2: (y0, x0, y1, x1)
    :return: scala value of IoU
    """
    # computing area of each rectangles
    S_rec1 = (rec1[2] - rec1[0]) * (rec1[3] - rec1[1])
    S_rec2 = (rec2[2] - rec2[0]) * (rec2[3] - rec2[1])

    # computing the sum_area
    sum_area = S_rec1 + S_rec2

    # find the each edge of intersect rectangle
    left_line = max(rec1[1], rec2[1])
    right_line = min(rec1[3], rec2[3])
    top_line = max(rec1[0], rec2[0])
    bottom_line = min(rec1[2], rec2[2])

    # judge if there is an intersect
    if left_line >= right_line or top_line >= bottom_line:
        return 0
    else:
        intersect = (right_line - left_line) * (bottom_line - top_line)
        return intersect / (sum_area - intersect)


if __name__ == '__main__':
    boxes1=torch.Tensor([[20,20,30,30]])
    boxes2=torch.Tensor([[25,25,35,35]])
    iou = ops.box_iou(boxes1,boxes2)

    rect1 = (20,20,30,30)
    # (top, left, bottom, right)
    rect2 = (25,25,35,35)
    iou2 = compute_iou(rect1, rect2)
    print(iou2)

    print(iou.numpy()[0][0])