mixed-precision topic

BitPack is a practical tool to efficiently save ultra-low precision/mixed-precision quantized models.

Zhen-Dong

Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.

Zhen-Dong

Toolkit for efficient experimentation with Speech Recognition, Text2Speech and NLP

NVIDIA

Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation

hellojialee

[CVPR 2019, Oral] HAQ: Hardware-Aware Automated Quantization with Mixed Precision

mit-han-lab

Training with FP16 weights in PyTorch

suvojit-0x55aa

A tool for debugging and assessing floating point precision and reproducibility.

verificarlo

High Resolution Style Transfer in PyTorch with Color Control and Mixed Precision :art:

moritztng

基于tensorflow1.x的预训练模型调用，支持单机多卡、梯度累积，XLA加速，混合精度。可灵活训练、验证、预测。

huanghuidmml

CMix-NN: Mixed Low-Precision CNN Library for Memory-Constrained Edge Devices

EEESlab