mvits_for_class_agnostic_od icon indicating copy to clipboard operation
mvits_for_class_agnostic_od copied to clipboard

Loading checkpoints for inference

Open KaleemW opened this issue 2 years ago • 4 comments

Which checkpoints in drive link you provided will load correctly in default MDefDETR model without any errors? Im getting missing/unexpected keys errors.

KaleemW avatar Aug 24 '22 09:08 KaleemW

Hi @KaleemW,

Please try loading MDef_DETR_r101_epoch20.pth checkpoints. If you will still get an error then please post the full error message along with the process you are following for loading the weights here. I hope it will be helpful. Thank you

mmaaz60 avatar Aug 24 '22 13:08 mmaaz60

Thanks a lot. It worked. Just wanted to know one last thing that is there a cpu implementation available for this project. I ran successfully with cuda but without cuda it doesnt compile MSDA...

KaleemW avatar Aug 25 '22 07:08 KaleemW

Thanks a lot. It worked. Just wanted to know one last thing that is there a cpu implementation available for this project. I ran successfully with cuda but without cuda it doesnt compile MSDA...

Hi @KaleemW,

Unfortunately, only GPU implementation is available at the moment.

mmaaz60 avatar Aug 25 '22 11:08 mmaaz60

Ok Sir! Thank You for your help.

KaleemW avatar Aug 30 '22 07:08 KaleemW

@mmaaz60 hi could you tell me what is the inference speed of your model? and how to do batch inference to improve the efficiency? Thanks.

Edwardmark avatar Aug 31 '23 02:08 Edwardmark

Hi @Edwardmark,

Thank you for your interest in our work. Please refer to the Table 10 of our paper for inference speed. Further, the batch inference implementation is available at modulated_detection.py.

I hope it will help. Thank You.

mmaaz60 avatar Sep 01 '23 05:09 mmaaz60