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

The implementation of 'Image synthesis via semantic composition'.

Code for Subgraph Federated Learning with Missing Neighbor Generation (NeurIPS 2021)

ERISHA is a mulitilingual multispeaker expressive speech synthesis framework. It can transfer the expressivity to the speaker's voice for which no expressive speech corpus is available.

DECAF: Deep Extreme Classification with Label Features

BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation

PyTorch implementation of DCT fast weight RNNs

Dynamic hair modeling from monocular videos using deep neural networks

This is the official repository for our paper: ''Pruning Self-attentions into Convolutional Layers in Single Path''.

Pytorch code for "State-only Imitation with Transition Dynamics Mismatch" (ICLR 2020)

[CVPR 2021] Monocular depth estimation using wavelets for efficiency

RITA is a family of autoregressive protein models, developed by LightOn in collaboration with the OATML group at Oxford and the Debora Marks Lab at Harvard.

Tensorflow Implementation for "Pre-trained Deep Convolution Neural Network Model With Attention for Speech Emotion Recognition"

Implementing a simplified copy of Shazam application from scratch using MinHashing and LSH.

Data and analysis code for an MS on SK VOC genomes phenotyping/neutralisation assays

Effective Use of Transformer Networks for Entity Tracking

Differential rendering based motion capture blender project.

Deep Learning Slide Captcha

Official PyTorch Implementation of "AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting".

LocUNet is a deep learning method to localize a UE based solely on the reported signal strengths from a set of BSs.

The 2nd Version Of Slothybot