plalexx

Results 2 comments of plalexx

Hi, it seems that you use old style of setting pretrained weights like `pretrained=...` Instead of this try like in the new version of mmdetection https://github.com/open-mmlab/mmdetection/blob/master/configs/_base_/models/faster_rcnn_r50_fpn.py#L13 in backbone like this:...

Noticed same problem while training on custom dataset even after large number of iterations. Have you figured what was the issue?