ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
Datasets, Transforms and Models specific to Computer Vision
PDF Abstract ECCV 2018 PDF ECCV 2018 AbstractCode
Methods
1x1 Convolution •
Average Pooling •
Batch Normalization •
Channel Shuffle •
Convolution •
Dense Connections •
Depthwise Convolution •
Global Average Pooling •
ReLU •
Residual Connection •
ShuffleNet v2 •
ShuffleNet V2 Block •
ShuffleNet V2 Downsampling Block •
Sigmoid Activation •
Softmax •
Squeeze-and-Excitation Block •
Step Decay •
Weight Decay