lightweight-neural-architecture-search
lightweight-neural-architecture-search copied to clipboard
the limit of btn
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
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.