XYD

The checkpoint models might be corrupted.

2

Hi, when I used your pre-training model to test, I encountered a problem "RuntimeError: unexpected of. The file might be corrupted." Traceback (most recent call last): File "test.py", line 20,...

The AP with_fp and removed_fp is very close

1

I have try to execute bash run_pipeline_universal_patch.sh as your steps,but the AP for train with_fp is 0.8548 and the AP for train removed_fp is 0.8618.Why is the AP so close?Can...