COCO pre-trained models

zehuichen123 / DDOD

[ACM MM 2021, TMM 2023] Disentangle your Dense Object Detector

Apache License 2.0

61 stars 7 forks source link

COCO pre-trained models #4

Closed shinya7y closed 3 years ago

shinya7y commented 3 years ago

Hi! Awesome work! Do you have any plans to upload COCO weights?

Especially,

ATSS(IoU) R-50 1x
DDOD R-50 1x
DDOD R2-101-DCN 2x
DDOD-X R2-101-DCN 2x

It would be great if you also could provide configs for DDOD-X because the arXiv v1 seems to lack the explanation of DDOD-X and the details of multi-scale testing and stronger data augmentation.

zehuichen123 commented 3 years ago

Currently, we don't have plans for that (the checkpoints are missing due to personal reasons), but you can run them on your own. For detailed settings about DDOD-X, you may refer to https://github.com/hyz-xmaster/VarifocalNet/blob/master/configs/vfnet/vfnetx_r2_101_fpn_mdconv_c3-c5_mstrain_59e_coco.py. We adopt a similar setting in this config.

shinya7y commented 3 years ago

Thank you for the information!