Add coordattention in MobileNetV2?
cc19860606 opened this issue · 7 comments
cc19860606 commented
cc19860606 commented
Anyone reproduct the performance of CoordAttention with MobileNetV2 on VOC2007?
houqb commented
Have you pretrained the model on ImageNet?
cc19860606 commented
I firstly test MobileNetV2,the mAP can achieve 71.7. Then, I try to add CoordAttention as shown above, meanwhile the pretrained model of 'mobilenet_v2-b0353104.pth' is not use. The mAP only can achieve 64.
@Andrew-Qibin
cc19860606 commented
ssdlite-pytorch-mobilenext with CoordAttention need to be trained with ImageNet, then test on VOC?
houqb commented
Exactly. Otherwise, it does not work. Recently, I will release the pretrained models.
cc19860606 commented
I look forward for it, thx.
cc19860606 commented
The ImageNet dataset used for training is ILSVRC2012 or others? And the hyperparameter and code of data augmentation for training?
@Andrew-Qibin