EfficientNetv2 TensorRT int8

Overview

EfficientNetv2_TensorRT_int8

EfficientNetv2模型实现来自https://github.com/d-li14/efficientnetv2.pytorch

环境配置

ubuntu:18.04

cuda:11.0

cudnn:8.0

tensorrt:7.2.16

OpenCV:3.4.2

cuda,cudnn,tensorrt和OpenCV安装包可以从如下链接下载:

链接: https://pan.baidu.com/s/1XSzHJ1kPXO0PrAMAF6uNyA 密码: b88e

cuda安装

如果系统有安装驱动,运行如下命令卸载

sudo apt-get purge nvidia*

禁用nouveau,运行如下命令

sudo vim /etc/modprobe.d/blacklist.conf

在末尾添加

blacklist nouveau

然后执行

sudo update-initramfs -u

chmod +x cuda_11.0.2_450.51.05_linux.run

sudo ./cuda_11.0.2_450.51.05_linux.run

是否接受协议: accept

然后选择Install

最后回车

vim ~/.bashrc 添加如下内容:

export PATH=/usr/local/cuda-11.0/bin:$PATH

export LD_LIBRARY_PATH=/usr/local/cuda-11.0/lib64:$LD_LIBRARY_PATH

source .bashrc 激活环境

cudnn 安装

tar -xzvf cudnn-11.0-linux-x64-v8.0.4.30.tgz

cd cuda/include

sudo cp *.h /usr/local/cuda-11.0/include

cd cuda/lib64

sudo cp libcudnn* /usr/local/cuda-11.0/lib64

tensorrt及OpenCV安装

定位到用户根目录

tar -xzvf TensorRT-7.2.1.6.Ubuntu-18.04.x86_64-gnu.cuda-11.0.cudnn8.0.tar.gz

cd TensorRT-7.2.1.6/python,该目录有4个python版本的tensorrt安装包

sudo pip3 install tensorrt-7.2.1.6-cp37-none-linux_x86_64.whl(根据自己的python版本安装)

pip install pycuda 安装python版本的cuda

定位到用户根目录

tar -xzvf opencv-3.4.2.zip 以备推理调用

efficientnetv2模型训练以及转换onnx

定位到用户根目录

git clone https://github.com/Wulingtian/EfficientNetv2_TensorRT_int8.git

cd EfficientNetv2_TensorRT_int8

vim train.py 修改IMAGENET_TRAINSET_SIZE参数 指定训练图片的数量

根据自己的训练数据及配置设置data(数据集路径),epochs,lr,batch-size等参数

python train.py,开始训练,模型保存在当前目录,名为model_best.pth.tar

vim export_onnx.py

设置weights_file(训练得到的模型),output_file(输出模型名称),img_size(图片输入大小),batch_size(推理的batch)

python export_onnx.py 得到onnx模型

onnx模型转换为 int8 tensorrt引擎

cd EfficientNetv2_TensorRT_int8/effnetv2_tensorrt_int8_tools

vim convert_trt_quant.py 修改如下参数

BATCH_SIZE 模型量化一次输入多少张图片

BATCH 模型量化次数

height width 输入图片宽和高

CALIB_IMG_DIR 量化图片路径(把训练的图片放到一个文件夹下,然后把这个文件夹设置为此参数,注意BATCH_SIZE*BATCH要小于或等于训练图片数量)

onnx_model_path onnx模型路径(上面运行export_onnx.py得到的onnx模型)

python convert_trt_quant.py 量化后的模型存到models_save目录下

TensorRT模型推理

cd EfficientNetv2_TensorRT_int8/effnetv2_tensorrt_int8

vim CMakeLists.txt

修改USER_DIR参数为自己的用户根目录

vim effnetv2_infer.cc修改如下参数

output_name effnetv2模型有1个输出

我们可以通过netron查看模型输出名

pip install netron 安装netron

vim netron_effnetv2.py 把如下内容粘贴

    import netron

    netron.start('此处填充简化后的onnx模型路径', port=3344)

python netron_effnetv2.py 即可查看 模型输出名

trt_model_path 量化的tensorrt推理引擎(models_save目录下trt后缀的文件)

test_img 测试图片路径

INPUT_W INPUT_H 输入图片宽高

NUM_CLASS 训练的模型有多少类

参数配置完毕

mkdir build

cd build

cmake ..

make

./Effnetv2sEngine 输出平均推理时间,实测1070显卡平均推理时间3.8ms一帧;至此,部署完成!

分享一下我的训练集(猫狗二分类数据)及量化数据,链接如下:

链接: https://pan.baidu.com/s/1Mh6GxTLoXRTCRQh-TPUc3Q 密码: 3dt3
[CVPR'20] TTSR: Learning Texture Transformer Network for Image Super-Resolution

TTSR Official PyTorch implementation of the paper Learning Texture Transformer Network for Image Super-Resolution accepted in CVPR 2020. Contents Intr

Multimedia Research 689 Dec 28, 2022
Drone Task1 - Drone Task1 With Python

Drone_Task1 Matching Results 3.mp4 1.mp4

MLV Lab (Machine Learning and Vision Lab at Korea University) 11 Nov 14, 2022
PyTorch EO aims to make Deep Learning for Earth Observation data easy and accessible to real-world cases and research alike.

Pytorch EO Deep Learning for Earth Observation applications and research. 🚧 This project is in early development, so bugs and breaking changes are ex

earthpulse 28 Aug 25, 2022
Yolov5+SlowFast: Realtime Action Detection Based on PytorchVideo

Yolov5+SlowFast: Realtime Action Detection A realtime action detection frame work based on PytorchVideo. Here are some details about our modification:

WuFan 181 Dec 30, 2022
A simple version for graphfpn

GraphFPN: Graph Feature Pyramid Network for Object Detection Download graph-FPN-main.zip For training , run: python train.py For test with Graph_fpn

WorldGame 67 Dec 25, 2022
Code of the paper "Deep Human Dynamics Prior" in ACM MM 2021.

Code of the paper "Deep Human Dynamics Prior" in ACM MM 2021. Figure 1: In the process of motion capture (mocap), some joints or even the whole human

Shinny cui 3 Oct 31, 2022
The code of "Dependency Learning for Legal Judgment Prediction with a Unified Text-to-Text Transformer".

Code data_preprocess.py: preprocess data for Dependent-T5. parameters.py: define parameters of Dependent-T5. train_tools.py: traning and evaluation co

1 Apr 21, 2022
AttGAN: Facial Attribute Editing by Only Changing What You Want (IEEE TIP 2019)

News 11 Jan 2020: We clean up the code to make it more readable! The old version is here: v1. AttGAN TIP Nov. 2019, arXiv Nov. 2017 TensorFlow impleme

Zhenliang He 568 Dec 14, 2022
Mercury: easily convert Python notebook to web app and share with others

Mercury Share your Python notebooks with others Easily convert your Python notebooks into interactive web apps by adding parameters in YAML. Simply ad

MLJAR 2.2k Dec 27, 2022
Hierarchical Metadata-Aware Document Categorization under Weak Supervision (WSDM'21)

Hierarchical Metadata-Aware Document Categorization under Weak Supervision This project provides a weakly supervised framework for hierarchical metada

Yu Zhang 53 Sep 17, 2022
NeuroLKH: Combining Deep Learning Model with Lin-Kernighan-Helsgaun Heuristic for Solving the Traveling Salesman Problem

NeuroLKH: Combining Deep Learning Model with Lin-Kernighan-Helsgaun Heuristic for Solving the Traveling Salesman Problem Liang Xin, Wen Song, Zhiguang

xinliangedu 33 Dec 27, 2022
Can we learn gradients by Hamiltonian Neural Networks?

Can we learn gradients by Hamiltonian Neural Networks? This project was carried out as part of the Optimization for Machine Learning course (CS-439) a

2 Aug 22, 2022
AugLy is a data augmentations library that currently supports four modalities (audio, image, text & video) and over 100 augmentations

AugLy is a data augmentations library that currently supports four modalities (audio, image, text & video) and over 100 augmentations. Each modality’s augmentations are contained within its own sub-l

Facebook Research 4.6k Jan 09, 2023
A strongly-typed genetic programming framework for Python

monkeys "If an army of monkeys were strumming on typewriters they might write all the books in the British Museum." monkeys is a framework designed to

H. Chase Stevens 115 Nov 27, 2022
Catch-all collection of generative art made using processing

Generative art with Processing.py Some art I have created for fun. Dependencies Processing for Python, see how to download/use here Packages contained

2 Mar 12, 2022
Repository for the paper "PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation", CVPR 2021.

PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation Code repository for the paper: PoseAug: A Differentiable Pose Augme

Pyjcsx 328 Dec 17, 2022
The easiest tool for extracting radiomics features and training ML models on them.

Simple pipeline for experimenting with radiomics features Installation git clone https://github.com/piotrekwoznicki/ClassyRadiomics.git cd classrad pi

Piotr Woźnicki 17 Aug 04, 2022
FlowTorch is a PyTorch library for learning and sampling from complex probability distributions using a class of methods called Normalizing Flows

FlowTorch is a PyTorch library for learning and sampling from complex probability distributions using a class of methods called Normalizing Flows.

Meta Incubator 272 Jan 02, 2023
The project page of paper: Architecture disentanglement for deep neural networks [ICCV 2021, oral]

This is the project page for the paper: Architecture Disentanglement for Deep Neural Networks, Jie Hu, Liujuan Cao, Tong Tong, Ye Qixiang, ShengChuan

Jie Hu 15 Aug 30, 2022
Learning kernels to maximize the power of MMD tests

Code for the paper "Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy" (arXiv:1611.04488; published at ICLR 2017), by Douga

Danica J. Sutherland 201 Dec 17, 2022