How can I use it for downstream tasks

[fly_zhu]

If I want to use representation information for downstream tasks, which part of the feature should I use ？

[xyupeng]

For linear classification, please follow README. For object detection and instance segmentation, we use the same code as in MoCo.

[fly_zhu]

I still haven't found how the pre-training model is used for target detection, could you give a specific explanation

[xyupeng]

Transferring to detection is the same as MoCo.

[xyupeng]

To be more specific, you need to first convert the saved model (last.pth) to detectron2's format. Then use detectron2's code to train detection.