This is the codebase of searching bit-widths for neural networks based on fractional bit-widths, as proposed in FracBits arXiv AAAI2021.
apps
dir, based on PyTorch.logs
dir and directly run command.test_only
and pretrained
in config file. You will need to manage visible gpus by yourself.python train.py app:{apps/***.yml}
. {apps/***.yml}
is config file. Do not miss app:
prefix.Implementing network quantizing is straightforward:
models/quantizable_ops
.kappa
] in the yml file.q_mobilenetv1_uint8_train_val.yml
] is a good start yml example. For ablation test, please run test_ablation
with the corresponding test ablation yml file.CC 4.0 Attribution-NonCommercial International
The software is for educaitonal and academic research purpose only.
@article{yang2020fracbits,
title={FracBits: Mixed Precision Quantization via Fractional Bit-Widths},
author={Yang, Linjie and Jin, Qing},
journal={arXiv preprint arXiv:2007.02017},
year={2020}
}