search

hustvl / TopFormer

TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation, CVPR2022
Other
373 stars 42 forks source link

Configs for Object Detection #11

Open xyc2690 opened 2 years ago

xyc2690 commented 2 years ago

Would you share the mmdet configs for the object detection training?

mulinmeng commented 2 years ago

Would you share the mmdet configs for the object detection training?

Link: https://pan.baidu.com/s/1lX0FeAWyYWccyLQzmoVCnQ (pwd: topf)

xyc2690 commented 2 years ago

Would you share the mmdet configs for the object detection training?

Link: https://pan.baidu.com/s/1lX0FeAWyYWccyLQzmoVCnQ (pwd: topf)

Many thanks, I use almost the same config (Topformer-T with syncBN enabled) and get a higher mAP(31.2) than reported (27.1).

Could you also kindly share the configs for mobilenetv3/Shuffenet?

mulinmeng commented 2 years ago

Would you share the mmdet configs for the object detection training?

Link: https://pan.baidu.com/s/1lX0FeAWyYWccyLQzmoVCnQ (pwd: topf)

Many thanks, I use almost the same config (Topformer-T with syncBN enabled) and get a higher mAP(31.2) than reported (27.1).

Could you also kindly share the configs for mobilenetv3/Shuffenet?

Congratulations！We use the default config(w/o sync_bn, 2x8 schedular) for fair comparison. If you find it useful in your work or research, welcome to recommend our work to your friends!

As for the configs for mobilenetv3/Shuffenet, we refer to the results of MobileFormer.