Open sisrfeng opened 4 years ago
I try it but result is not good with ResNest compared to DLA34
I try it but result is not good with DLA34
Thank you for your reply. Do you know the reason? Recently I have met several problems but can not find reasonable explanation. Just doing experiment is a little frustrating
https://github.com/zhanghang1989/ResNeSt Split-Attention Network, A New ResNet Variant. It significantly boosts the performance of downstream models such as Mask R-CNN, Cascade R-CNN and DeepLabV3.