Open CS-Jackson opened 5 years ago
During inference, I notice that you first resize the picture as input, but the annotations used in counting mAP doesn't change, is it right, or do I miss something?
The annation is tranferred as percent of the image. So the resize operation will not change the gt
During inference, I notice that you first resize the picture as input, but the annotations used in counting mAP doesn't change, is it right, or do I miss something?