QAT(quantize aware training) for classification with MQBench

Last update: Nov 18, 2022

Overview

MQBench Quantization Aware Training with PyTorch

I am using MQBench(Model Quantization Benchmark)(http://mqbench.tech/) to quantize the model for deployment.

MQBench is a benchmark and framework for evluating the quantization algorithms under real world hardware deployments.

Prerequisites

Python 3.7+
PyTorch 1.8.1+

Install MQBench Lib

Before run this repository, you should install MQBench:

git clone https://github.com/ModelTC/MQBench.git
cd MQBench
python setup.py build
python setup.py install

Training Fp32 Model

# Start training fp32 model with: 
# model_name can be ResNet18, MobileNet, ...
python main.py model_name

# You can manually config the training with: 
python main.py --resume --lr=0.01

Training Quantize Model

# Start training quantize model with: 
# model_name can be ResNet18, MobileNet, ...
python main.py model_name --quantize

# You can manually config the training with: 
python main.py --resume --parallel DP --BackendType Tensorrt --quantize
python -m torch.distributed.launch main.py --local_rank 0 --parallel DDP --resume  --BackendType Tensorrt --quantize

Fp32 Accuracy

Model	Acc.
VGG16	92.64%
ResNet18	93.02%
ResNet50	93.62%
ResNet101	93.75%
RegNetX_200MF	94.24%
RegNetY_400MF	94.29%
MobileNetV2	94.43%
ResNeXt29(32x4d)	94.73%
ResNeXt29(2x64d)	94.82%
SimpleDLA	94.89%
DenseNet121	95.04%
PreActResNet18	95.11%
DPN92	95.16%
DLA	95.47%

QAT(quantize aware training) for classification with MQBench

Related tags

Overview

MQBench Quantization Aware Training with PyTorch

Prerequisites

Install MQBench Lib

Training Fp32 Model

Training Quantize Model

Fp32 Accuracy

Owner

Ling Zhang

Super-Fast-Adversarial-Training - A PyTorch Implementation code for developing super fast adversarial training

PyTorch and Tensorflow functional model definitions

A light-weight image labelling tool for Python designed for creating segmentation data sets.

Create images and texts with the First Order Generative Adversarial Networks

Code for the Population-Based Bandits Algorithm, presented at NeurIPS 2020.

Bayesian Meta-Learning Through Variational Gaussian Processes

This project uses Template Matching technique for object detecting by detection of template image over base image.

A Kaggle competition: discriminate gender based on handwriting

Implementation of ConvMixer for "Patches Are All You Need? 🤷"

A mini library for Policy Gradients with Parameter-based Exploration, with reference implementation of the ClipUp optimizer from NNAISENSE.

Self-Learned Video Rain Streak Removal: When Cyclic Consistency Meets Temporal Correspondence

Implementation for Panoptic-PolarNet (CVPR 2021)

Image Matching Evaluation

Vehicle direction identification consists of three module detection , tracking and direction recognization.

An MQA (Studio, originalSampleRate) identifier for lossless flac files written in Python.

A PyTorch toolkit for 2D Human Pose Estimation.

PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

Pre-trained Deep Learning models and demos (high quality and extremely fast)

End-to-end Temporal Action Detection with Transformer. [Under review]

[NeurIPS 2021] Source code for the paper "Qu-ANTI-zation: Exploiting Neural Network Quantization for Achieving Adversarial Outcomes"