Skip to content

How to start downstream task of object detection on MAE ? #528

Discussion options

You must be logged in to vote

Currently, MMDet does not support ViT for Mask-RCNN, but I have already supported ViT for UpperNet in MMSeg. You can have a try, following this guide. A kind note: There is no need to convert the keys of the weights from MMSelfSup. Thanks!

Replies: 6 comments

Comment options

You must be logged in to vote
0 replies
Comment options

You must be logged in to vote
0 replies
Comment options

You must be logged in to vote
0 replies
Comment options

You must be logged in to vote
0 replies
Answer selected by fangyixiao18
Comment options

You must be logged in to vote
0 replies
Comment options

You must be logged in to vote
0 replies
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
How-to
Labels
None yet
3 participants
Converted from issue

This discussion was converted from issue #465 on October 19, 2022 09:40.