liming-ai / AlignDet

Official code for ICCV 2023 Paper: AlignDet: Aligning Pre-training and Fine-tuning in Object Detection.
https://liming-ai.github.io/AlignDet/
Apache License 2.0
142 stars 13 forks source link

Hello, here I want to test the effect of Faster-R CNN fine tuning, but do not see the weight parameter? #10

Closed luoyq6 closed 1 year ago

luoyq6 commented 1 year ago

Hello, here I want to test the effect of Faster-R CNN fine tuning, but do not see the weight parameter? Is it this final model.pth file? What is the meaning of selfsup_mask-rcnn_mstrain-soft-teacher_sampler-4096_temp0.5 image

liming-ai commented 1 year ago

Hello, here I want to test the effect of Faster-R CNN fine tuning, but do not see the weight parameter? Is it this final model.pth file? What is the meaning of selfsup_mask-rcnn_mstrain-soft-teacher_sampler-4096_temp0.5 image

Hi, the Faster R-CNN and Mask R-CNN have the same pre-train weights. The only difference between them is weather adding a mask_head during fine-tuning.

luoyq6 commented 1 year ago

ok, Thank you