原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
For each image, the output of our object detector is a set of bounding boxes , where B is likely to be larger than the number of ground truth bounding boxes in the training set. The first step in the evaluation is to associate each detection with a ground truth label so that we have a set . For each of the predicted bounding boxes
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c050b.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8