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 Junhuan1,2, XU Ke1,2, WANG Dong1,2
ResNet-20的2比特量化的权重可视化分布