lightweight-neural-architecture-search icon indicating copy to clipboard operation
lightweight-neural-architecture-search copied to clipboard

the limit of btn

Open ct-wei opened this issue 2 years ago • 1 comments
trafficstars

The constraint limit the btn in https://github.com/alibaba/lightweight-neural-architecture-search/blob/6bf4d6949ed690b8ef59bcb843e2d36d03ebecd1/tinynas/spaces/mutator/super_res_k1kx_mutator.py#L72 https://github.com/alibaba/lightweight-neural-architecture-search/blob/6bf4d6949ed690b8ef59bcb843e2d36d03ebecd1/tinynas/spaces/mutator/super_res_k1kx_mutator.py#L82 but this https://github.com/tinyvision/DAMO-YOLO/blob/master/damo/base_models/backbones/nas_backbones/tinynas_nano_middle.txt seems to have broken the limit May I ask why? thanks

ct-wei avatar May 11 '23 13:05 ct-wei

The constraint limit the btn in

https://github.com/alibaba/lightweight-neural-architecture-search/blob/6bf4d6949ed690b8ef59bcb843e2d36d03ebecd1/tinynas/spaces/mutator/super_res_k1kx_mutator.py#L72

https://github.com/alibaba/lightweight-neural-architecture-search/blob/6bf4d6949ed690b8ef59bcb843e2d36d03ebecd1/tinynas/spaces/mutator/super_res_k1kx_mutator.py#L82

but this https://github.com/tinyvision/DAMO-YOLO/blob/master/damo/base_models/backbones/nas_backbones/tinynas_nano_middle.txt seems to have broken the limit May I ask why? thanks

That's a good question. For small or mobile models, particularly those with depthwise search space, we have observed that the limitation on btn may constrain the final accuracy. The similar observation can be found in mobilenetv3 paper.

xiuyu-sxy avatar May 17 '23 03:05 xiuyu-sxy