FOTS.PyTorch icon indicating copy to clipboard operation
FOTS.PyTorch copied to clipboard

self.roirotate.apply(feature_map, rois, self.pooled_height, pooled_width, self.spatial_scale) return tensor with all element is 0

Open tranducanhbk opened this issue 3 years ago • 1 comments

Hi, Can u show some result of recognize part. I train with my custom data and the detection part work well but when i try to get recognize result it is not as expected. I found the rroiallign retrun a tensor with all element is 0. Can u help me find the rootcause of this issue, Many Thanks

tranducanhbk avatar Dec 30 '21 05:12 tranducanhbk

this bug is fixed now.

jiangxiluning avatar May 14 '22 14:05 jiangxiluning