ProxylessNet-CPU is an image model learnt with the ProxylessNAS neural architecture search algorithm that is optimized for CPU devices. It uses inverted residual blocks (MBConvs) from MobileNetV2 as its basic building block.
Source: ProxylessNAS: Direct Neural Architecture Search on Target Task and HardwarePaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Classification | 2 | 40.00% |
Few-Shot Image Classification | 1 | 20.00% |
General Classification | 1 | 20.00% |
Language Modelling | 1 | 20.00% |
Component | Type |
|
---|---|---|
Convolution
|
Convolutions | |
Global Average Pooling
|
Pooling Operations | |
Inverted Residual Block
|
Skip Connection Blocks |