Chrome Extension
WeChat Mini Program
Use on ChatGLM

Searching for Fast Model Families on Datacenter Accelerators.

Computer Vision and Pattern Recognition(2021)

Cited 30|Views160
No score
Key words
FLOPs-latency nonproportionality,DC-accelerator-optimized search space,hybrid fused convolution structures,depthwise convolutions,block-wise activation functions,latency-aware compound scaling,multiobjective compound scaling method,LACS discovers,Efficient-Net,fast model families,neural architecture search,NAS,model scaling,fast convolutional architecture families,hardware architecture details,datacenter accelerators,fast CNN model families,EfficientNet-X,TPUv3,GPUv100
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined