TAGS

Insights and Thoughts
Nets-Compression

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

XNOR Net: ImageNet Classification Using Binary Convolutional Neural Networks

MobileNets Analysis: From V1 to V3

Binarization

XNOR Net: ImageNet Classification Using Binary Convolutional Neural Networks

Quantization

DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients

QAT: Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference