← Search

Yinghan Li

1 accepted papers

2021

Distribution Adaptive INT8 Quantization for Training CNNs

AAAI 2021technical

Researches have demonstrated that low bit-width (e.g., INT8) quantization can be employed to accelerate the inference process. It makes the gradient quantization very promising since the backward propagation requires approximately twice more computation than forward one. Due to the variability and u…

Cited by 72SourcePDFScholar