Post-training quantization references

Papers:

Same, Same But Different - Recovering Neural Network Quantization Error Through Weight Factorization https://arxiv.org/abs/1902.01917
Up or Down? Adaptive Rounding for Post-Training Quantization http://proceedings.mlr.press/v119/nagel20a/nagel20a.pdf
Post training 4-bit quantization of convolutional networks for rapid-deployment https://openreview.net/pdf/513214e98debdadfcc6048cd40ebbd5d9ba81a49.pdf
Data-Free QuantizationThrough Weight Equalization and Bias Correction https://arxiv.org/pdf/1906.04721.pdf
Fighting Quantization Bias With Bias https://arxiv.org/abs/1906.03193
BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction https://arxiv.org/abs/2102.05426
Zero shot adversarial quantization https://arxiv.org/abs/2103.15263
Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming https://arxiv.org/abs/2006.10518
ZeroQ: A Novel Zero Shot Quantization Framework https://arxiv.org/abs/2001.00281
Generative Low-bitwidth Data Free Quantization https://arxiv.org/abs/2003.03603
Improving Neural Network Quantization without Retraining using Outlier Channel Splitting https://arxiv.org/pdf/1901.09504.pdf
The Knowledge Within: Methods for Data-Free Model Compression https://arxiv.org/abs/1912.01274
Low-bit Quantization of Neural Networks for Efficient Inference https://arxiv.org/abs/1902.06822

Xilinx / brevitas