ppocrv3 detection inference

[alicera]

请问我的对ppocrv3 detection inference理解是否正确?

前处理:

1. resize 960x960
2. pixel 除以 255
3. 'std': [0.229, 0.224, 0.225], 'mean': [0.485, 0.456, 0.406],

inference: 1. pred= [0.5 0.5 0.5 0.1 0.1 0.1 0.1 0.5 0.5 0.5 0.1 0.1 0.1 0.1 ]

2. 设定阀值 thres = 0.3

3. 结果转成 BINARY [1 1 1 0 0 0 0 1 1 1 0 0 0 0]

4. get the object box cv::findContours cv::minAreaRect