Skip to main content

Algorithm


OP frequency

ONNX OP statistics

alphabet order 3 Abs 4325 Add 20 And 2 ArgMax 101 AveragePool 34...

Model Compression

Model compression techniques are mainly classified into quantization (Zafrir et al.,2019), prunin...

Model Quantization

Quantization Granularity Quantization is a magic spell to reduce the memory footprint of a model...

Neural Arch Search

Knowledge Distillation

Pruning

reference

量化技术背景 从CNN量化说起 在传统CNN网络中，为了加速网络的推理速度，一种非常有效的方法是INT8量化 ，即将权重与激活(feature map) 的浮点数值量化成8-bit整型表示...

Data type

data type
Back to top