Question about the pre-process
AndersonZhangyq opened this issue · 2 comments
In _xywh2cs(self, x, y, w, h), to get the scale, the bounding box is rescaled to match the aspect ratio of the model input.
From the source code, I think the standard workflow is to rescale the bounding box and then crop the image according to the rescaled bounding box, which is inconsistent with the standard workflow mentioned in paper(which is to rescale the cropped image).
And I found this behavior in mmpose, which seems to be a common behavior.
Is there any special reason to do so? In my point of view, this behavior may includes much more context then expected.
Or the input aspect ratio chosen is designed for COCO, based on the statistics of aspect ratio of person bounding boxes?
this function is inherited from the orginal hrnet without modification for fair comparison~
Fair enough