Open David-Ttao opened 4 months ago
They can also set 8 layers, but they did not either. Man!
They can also set 8 layers, but they did not either. Man!
its worth discussing and i think its necessary to reproduce the code and change the layers to test result.
It will be a meaningful work!
就你这个issue显得格格不入。伟大无需多言!
《changed the title 什么罐头我说? Why the Gated CNN Blocks are not 24 layers?》hhhhhh
Thank you so much for your suggestion. We released MambaOut-Kobe model, a Kobe Memorial version with 24 Gated CNN blocks. MambaOut-Kobe achieves really competitive performance, surpassing ResNet-50 and ViT-S with much fewer parameters and FLOPs. For example, MambaOut-Kobe outperforms ViT-S by 0.2% accuracy with only 41% parameters and 33% FLOPs.
Model | Resolution | Params | MACs | Top1 Acc |
---|---|---|---|---|
ResNet-50 (ResNet strikes back) |
224 | 25.5M | 4.1G | 79.8 |
ViT-S | 224 | 22.1M | 4.6G | 79.8 |
MambaOut-Kobe | 224 | 9.1M | 1.5G | 80.0 |
Thank you so much for your suggestion. We released MambaOut-Kobe model, a Kobe Memorial version with 24 Gated CNN blocks. MambaOut-Kobe achieves really competitive performance, surpassing ResNet-50 and ViT-S with much fewer parameters and FLOPs. For example, MambaOut-Kobe outperforms ResNet-50 by 0.2% accuracy with only 36% parameters and MACs.
Model Resolution Params MACs Top1 Acc ResNet-50 224 25.5M 4.1G 79.8* ViT-S 224 22.1M 4.6G 79.8 MambaOut-Kobe 224 9.1M 1.5G 80.0
- The result is cited from "ResNet strikes back" paper, a very strong version of ResNet trained for 300 epochs.
Man! Hahahaha
Thank you so much for your suggestion. We released MambaOut-Kobe model, a Kobe Memorial version with 24 Gated CNN blocks. MambaOut-Kobe achieves really competitive performance, surpassing ResNet-50 and ViT-S with much fewer parameters and FLOPs. For example, MambaOut-Kobe outperforms ResNet-50 by 0.2% accuracy with only 36% parameters and MACs.
Model Resolution Params MACs Top1 Acc ResNet-50 224 25.5M 4.1G 79.8* ViT-S 224 22.1M 4.6G 79.8 MambaOut-Kobe 224 9.1M 1.5G 80.0
- The result is cited from "ResNet strikes back" paper, a very strong version of ResNet trained for 300 epochs.
its a meaningful work, what can i say?
What a great suggestion!
I think its necessary to set 24 layers of MambaOut in memory of Kobe Bryant.