Bo Chen

Hope to add TrivialAugmentation，https://github.com/automl/trivialaugment

Thank you for your answer, there is another question I would like to ask, in SAM, why need to use two ROI operations to get q_content and q_content_point respectively.

Same issue. My mmdet's version is 2.19.0 and raise error during training the 3rd epoch

try to use python2.7

+1

Thank you for your answer. Looking forward to seeing the extended version

Hi，我也遇到了这个问题，请问你现在解决了吗