基于指数移动平均知识蒸馏的神经网络低比特量化方法
吕君环
1,
2
, 许柯
1,
2
, 王东
1,
2
Low-Bit Quantization of Neural Network Based on Exponential Moving Average Knowledge Distillation
LÜ Junhuan
1,
2
, XU Ke
1,
2
, WANG Dong
1,
2
ResNet-20的2比特量化的权重可视化分布