Could you please tell us some details about GhostNet-BCD settings?

huawei-noah / Efficient-AI-Backbones

Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

4.05k stars 707 forks source link

Could you please tell us some details about GhostNet-BCD settings? #48

Open PistonY opened 3 years ago

PistonY commented 3 years ago

I read the paper Model Rubik’s Cube: Twisting Resolution, Depth and Width for TinyNets I have interest to reproduce this on GhostNet-(X), could you please share us the details of r,d,c setting compare to GhostNet-A?

PistonY commented 3 years ago

And you not specify dw_kernel_size for GhostNet in paper Table 7, are you using dw_kernel_size=3 by default?

iamhankai commented 3 years ago

Sorry for late reply. Please refer to TinyNet code: https://gitee.com/mindspore/mindspore/tree/master/model_zoo/research/cv/tinynet

PistonY commented 3 years ago

Hi @iamhankai, thanks for reply and open source. But I still confuse about how to get TinyGhostNet-X(B/C/D/E) from TinyGhostNet-A, are using using same param with EfficientNet?