Efficient-AI-Backbones icon indicating copy to clipboard operation
Efficient-AI-Backbones copied to clipboard
verified publisher icon huawei-noah

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

Open PistonY opened this issue 5 years ago • 3 comments

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 avatar Nov 23 '20 07:11 PistonY

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

PistonY avatar Nov 23 '20 09:11 PistonY

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

iamhankai avatar Dec 20 '20 12:12 iamhankai

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?

PistonY avatar Dec 21 '20 06:12 PistonY