faceboxes自定义encode

1.基于ssd改的，

2.只能做人脸检测，不能返回关键点，不能做人脸识别，能做抓拍机。

3.基于cpu实时。

      import numpy as np
      # anchors = np.array([[16, 32], [32, 16], [40, 40]])
      import itertools
      import torch
      def iou( box1, box2):
       '''Compute the intersection over union of two set of boxes, each box is [x1,y1,x2,y2].
       Args:
       box1: (tensor) bounding boxes, sized [N,4].
       box2: (tensor) bounding boxes, sized [M,4].
       Return:
       (tensor) iou, sized [N,M].
       '''
       N = box1.size(0)
       M = box2.size(0)
       lt = torch.max(  # left top
       box1[:, :2].unsqueeze(1).expand(N, M, 2),  # [N,2] -> [N,1,2] -> [N,M,2]
       box2[:, :2].unsqueeze(0).expand(N, M, 2),  # [M,2] -> [1,M,2] -> [N,M,2]
       )
       rb = torch.min(  # right bottom
       box1[:, 2:].unsqueeze(1).expand(N, M, 2),  # [N,2] -> [N,1,2] -> [N,M,2]
       box2[:, 2:].unsqueeze(0)
  
 

文章来源: blog.csdn.net，作者：网奇，版权归原作者所有，如需转载，请联系作者。

原文链接：blog.csdn.net/jacke121/article/details/86765519