QAT(quantize aware training) for classification with MQBench

Ling Zhang

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%

Comments

run error

stty: 标准输入: 对设备不适当的 ioctl 操作 Traceback (most recent call last): File "/home/chenxin/disk1/github/MQBench_Quantize/main.py", line 21, in from utils import progress_bar, choose_model, choose_backend File "/home/chenxin/disk1/github/MQBench_Quantize/utils.py", line 49, in _, term_width = os.popen('stty size', 'r').read().split() ValueError: not enough values to unpack (expected 2, got 0)

opened by mathpopo 2
quanitze model to 4 bits

Hello, Have you ever tried to quanitze model to 4 bits with MQbench in ImageNet. I found that it would have a gradient explosion in the second epoch. Do you know why?

opened by haoxuanwang37 0

Image Classification - A research on image classification and auto insurance claim prediction, a systematic experiments on modeling techniques and approaches

A research on image classification and auto insurance claim prediction, a systematic experiments on modeling techniques and approaches

0 Jan 23, 2022

Hl classification bc - A Network-Based High-Level Data Classification Algorithm Using Betweenness Centrality

A Network-Based High-Level Data Classification Algorithm Using Betweenness Centr

3 Dec 1, 2022

Scripts for training an AI to play the endless runner Subway Surfers using a supervised machine learning approach by imitation and a convolutional neural network (CNN) for image classification

About subwAI subwAI - a project for training an AI to play the endless runner Subway Surfers using a supervised machine learning approach by imitation

82 Jan 1, 2023

Ultra-Data-Efficient GAN Training: Drawing A Lottery Ticket First, Then Training It Toughly

Ultra-Data-Efficient GAN Training: Drawing A Lottery Ticket First, Then Training It Toughly Code for this paper Ultra-Data-Efficient GAN Tra

77 Oct 5, 2022

Learning recognition/segmentation models without end-to-end training. 40%-60% less GPU memory footprint. Same training time. Better performance.

InfoPro-Pytorch The Information Propagation algorithm for training deep networks with local supervision. (ICLR 2021) Revisiting Locally Supervised Lea

78 Dec 27, 2022

ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training

ActNN : Activation Compressed Training This is the official project repository for ActNN: Reducing Training Memory Footprint via 2-Bit Activation Comp

178 Jan 5, 2023

This is the code for our KILT leaderboard submission to the T-REx and zsRE tasks. It includes code for training a DPR model then continuing training with RAG.

KGI (Knowledge Graph Induction) for slot filling This is the code for our KILT leaderboard submission to the T-REx and zsRE tasks. It includes code fo

72 Jan 6, 2023

BERT model training impelmentation using 1024 A100 GPUs for MLPerf Training v1.1

Pre-trained checkpoint and bert config json file Location of checkpoint and bert config json file This MLCommons members Google Drive location contain

SAIT (Samsung Advanced Institute of Technology)

12 Apr 27, 2022

FuseDream: Training-Free Text-to-Image Generationwith Improved CLIP+GAN Space OptimizationFuseDream: Training-Free Text-to-Image Generationwith Improved CLIP+GAN Space Optimization

FuseDream This repo contains code for our paper (paper link): FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimizat

191 Dec 31, 2022

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

You might also like...

Image Classification - A research on image classification and auto insurance claim prediction, a systematic experiments on modeling techniques and approaches

Hl classification bc - A Network-Based High-Level Data Classification Algorithm Using Betweenness Centrality

Scripts for training an AI to play the endless runner Subway Surfers using a supervised machine learning approach by imitation and a convolutional neural network (CNN) for image classification

Ultra-Data-Efficient GAN Training: Drawing A Lottery Ticket First, Then Training It Toughly

Learning recognition/segmentation models without end-to-end training. 40%-60% less GPU memory footprint. Same training time. Better performance.

ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training

This is the code for our KILT leaderboard submission to the T-REx and zsRE tasks. It includes code for training a DPR model then continuing training with RAG.

BERT model training impelmentation using 1024 A100 GPUs for MLPerf Training v1.1

FuseDream: Training-Free Text-to-Image Generationwith Improved CLIP+GAN Space OptimizationFuseDream: Training-Free Text-to-Image Generationwith Improved CLIP+GAN Space Optimization

Comments

run error

quanitze model to 4 bits

Owner

Ling Zhang

MQBench Quantization Aware Training with PyTorch

MQBench: Towards Reproducible and Deployable Model Quantization Benchmark

Official implementation for the paper: "Multi-label Classification with Partial Annotations using Class-aware Selective Loss"

Based on the paper "Geometry-aware Instance-reweighted Adversarial Training" ICLR 2021 oral

Physics-Aware Training (PAT) is a method to train real physical systems with backpropagation.

Degree-Quant: Quantization-Aware Training for Graph Neural Networks.

TAP: Text-Aware Pre-training for Text-VQA and Text-Caption, CVPR 2021 (Oral)

Implement face detection, and age and gender classification, and emotion classification.

Simple-Image-Classification - Simple Image Classification Code (PyTorch)