Convolutional Neural Networks
DenseNAS-B
Introduced by Fang et al. in Densely Connected Search Space for More Flexible Neural Architecture SearchDenseNAS-B is a mobile convolutional neural network discovered through the DenseNAS neural architecture search method. The basic building block is MBConvs, or inverted bottleneck residuals, from the MobileNet architectures.
Source: Densely Connected Search Space for More Flexible Neural Architecture Search
Papers
| Paper | Code | Results | Date | Stars |
|---|
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
Convolution
|
Convolutions | |
Dense Connections
|
Feedforward Networks | |
Global Average Pooling
|
Pooling Operations | |
Inverted Residual Block
|
Skip Connection Blocks | |
Softmax
|
Output Functions |
