这是一个deeplabv3-plus-pytorch的源码,可以用于训练自己的模型。

Overview

DeepLabv3+:Encoder-Decoder with Atrous Separable Convolution语义分割模型在Pytorch当中的实现


目录

  1. 性能情况 Performance
  2. 所需环境 Environment
  3. 注意事项 Attention
  4. 文件下载 Download
  5. 训练步骤 How2train
  6. 预测步骤 How2predict
  7. 评估步骤 miou
  8. 参考资料 Reference

性能情况

训练数据集 权值文件名称 测试数据集 输入图片大小 mIOU
VOC12+SBD deeplab_mobilenetv2.pth VOC-Val12 512x512 72.59
VOC12+SBD deeplab_xception.pth VOC-Val12 512x512 76.95

所需环境

torch==1.2.0

注意事项

代码中的deeplab_mobilenetv2.pth和deeplab_xception.pth是基于VOC拓展数据集训练的。训练和预测时注意修改backbone。

文件下载

训练所需的deeplab_mobilenetv2.pth和deeplab_xception.pth可在百度网盘中下载。
链接: https://pan.baidu.com/s/1KgLMbprQshlcpKgug9ECFg 提取码: 4ir8

VOC拓展数据集的百度网盘如下:
链接: https://pan.baidu.com/s/1BrR7AUM1XJvPWjKMIy2uEw 提取码: vszf

训练步骤

a、训练voc数据集

1、将我提供的voc数据集放入VOCdevkit中(无需运行voc_annotation.py)。
2、在train.py中设置对应参数,默认参数已经对应voc数据集所需要的参数了,所以只要修改backbone和model_path即可。
3、运行train.py进行训练。

b、训练自己的数据集

1、本文使用VOC格式进行训练。
2、训练前将标签文件放在VOCdevkit文件夹下的VOC2007文件夹下的SegmentationClass中。
3、训练前将图片文件放在VOCdevkit文件夹下的VOC2007文件夹下的JPEGImages中。
4、在训练前利用voc_annotation.py文件生成对应的txt。
5、在train.py文件夹下面,选择自己要使用的主干模型和下采样因子。本文提供的主干模型有mobilenet和xception。下采样因子可以在8和16中选择。需要注意的是,预训练模型需要和主干模型相对应。
6、注意修改train.py的num_classes为分类个数+1。
7、运行train.py即可开始训练。

预测步骤

a、使用预训练权重

1、下载完库后解压,如果想用backbone为mobilenet的进行预测,直接运行predict.py就可以了;如果想要利用backbone为xception的进行预测,在百度网盘下载deeplab_xception.pth,放入model_data,修改deeplab.py的backbone和model_path之后再运行predict.py,输入。

img/street.jpg

可完成预测。
2、在predict.py里面进行设置可以进行fps测试、整个文件夹的测试和video视频检测。

b、使用自己训练的权重

1、按照训练步骤训练。
2、在deeplab.py文件里面,在如下部分修改model_path、num_classes、backbone使其对应训练好的文件;model_path对应logs文件夹下面的权值文件,num_classes代表要预测的类的数量加1,backbone是所使用的主干特征提取网络

_defaults = {
    #----------------------------------------#
    #   model_path指向logs文件夹下的权值文件
    #----------------------------------------#
    "model_path"        : 'model_data/deeplab_mobilenetv2.pth',
    #----------------------------------------#
    #   所需要区分的类的个数+1
    #----------------------------------------#
    "num_classes"       : 21,
    #----------------------------------------#
    #   所使用的的主干网络
    #----------------------------------------#
    "backbone"          : "mobilenet",
    #----------------------------------------#
    #   输入图片的大小
    #----------------------------------------#
    "input_shape"       : [512, 512],
    #----------------------------------------#
    #   下采样的倍数,一般可选的为8和16
    #   与训练时设置的一样即可
    #----------------------------------------#
    "downsample_factor" : 16,
    #--------------------------------#
    #   blend参数用于控制是否
    #   让识别结果和原图混合
    #--------------------------------#
    "blend"             : True,
    #-------------------------------#
    #   是否使用Cuda
    #   没有GPU可以设置成False
    #-------------------------------#
    "cuda"              : True,
}

3、运行predict.py,输入

img/street.jpg

可完成预测。
4、在predict.py里面进行设置可以进行fps测试、整个文件夹的测试和video视频检测。

评估步骤

1、设置get_miou.py里面的num_classes为预测的类的数量加1。
2、设置get_miou.py里面的name_classes为需要去区分的类别。
3、运行get_miou.py即可获得miou大小。

Reference

https://github.com/ggyyzm/pytorch_segmentation
https://github.com/bonlime/keras-deeplab-v3-plus

You might also like...
这是一个yolo3-tf2的源码,可以用于训练自己的模型。

YOLOV3:You Only Look Once目标检测模型在Tensorflow2当中的实现 目录 性能情况 Performance 所需环境 Environment 文件下载 Download 训练步骤 How2train 预测步骤 How2predict 评估步骤 How2eval 参考资料

这是一个yolox-keras的源码,可以用于训练自己的模型。

YOLOX:You Only Look Once目标检测模型在Keras当中的实现 目录 性能情况 Performance 实现的内容 Achievement 所需环境 Environment 小技巧的设置 TricksSet 文件下载 Download 训练步骤 How2train 预测步骤 Ho

A cross platform package to do curses-like operations, plus higher level APIs and widgets to create text UIs and ASCII art animations
A cross platform package to do curses-like operations, plus higher level APIs and widgets to create text UIs and ASCII art animations

ASCIIMATICS Asciimatics is a package to help people create full-screen text UIs (from interactive forms to ASCII animations) on any platform. It is li

CUDA integration for Python, plus shiny features

PyCUDA lets you access Nvidia's CUDA parallel computation API from Python. Several wrappers of the CUDA API already exist-so what's so special about P

It is a personal assistant chatbot, capable to perform many tasks same as Google Assistant plus more extra features...
It is a personal assistant chatbot, capable to perform many tasks same as Google Assistant plus more extra features...

PersonalAssistant It is an Personal Assistant, capable to perform many tasks with some unique features, that you haven'e seen yet.... Features / Tasks

A3C LSTM  Atari with Pytorch plus A3G design
A3C LSTM Atari with Pytorch plus A3G design

NEWLY ADDED A3G A NEW GPU/CPU ARCHITECTURE OF A3C FOR SUBSTANTIALLY ACCELERATED TRAINING!! RL A3C Pytorch NEWLY ADDED A3G!! New implementation of A3C

Face Recognition plus identification simply and fast | Python
Face Recognition plus identification simply and fast | Python

PyFaceDetection Face Recognition plus identification simply and fast Ubuntu Setup sudo pip3 install numpy sudo pip3 install cmake sudo pip3 install dl

Proof of Concept Exploit for ManageEngine ServiceDesk Plus CVE-2021-44077
Proof of Concept Exploit for ManageEngine ServiceDesk Plus CVE-2021-44077

CVE-2021-44077 Proof of Concept Exploit for CVE-2021-44077: PreAuth RCE in ManageEngine ServiceDesk Plus 11306 Based on: https://xz.aliyun.com/t/106

Enigma-Plus - Python based Enigma machine simulator with some extra features

Enigma-Plus Python based Enigma machine simulator with some extra features Examp

Plone Interface contracts, plus basic features and utilities

plone.base This package is the base package of the CMS Plone https://plone.org. It contains only interface contracts and basic features and utilitie

Strawberry-django-plus - Enhanced Strawberry GraphQL integration with Django

strawberry-django-plus Enhanced Strawberry integration with Django. Built on top

Comments
  • 输出坐标

    输出坐标

    image if self.mix_type == 0: seg_img = np.zeros((np.shape(pr)[0], np.shape(pr)[1], 3)) for c in range(self.num_classes): seg_img[:, :, 0] += ((pr[:, :] == c ) * self.colors[c][0]).astype('uint8') seg_img[:, :, 1] += ((pr[:, :] == c ) * self.colors[c][1]).astype('uint8') seg_img[:, :, 2] += ((pr[:, :] == c ) * self.colors[c][2]).astype('uint8')

    请问如果我想得到这个猫的左上方坐标和右下方坐标该怎么print呢

    opened by SSTato 3
  • TF/Keras 版和 PyTorch 版的性能差异

    TF/Keras 版和 PyTorch 版的性能差异

    首先感谢提供多种版本的代码。 我注意到同样是VOC12数据集,deeplabv3-plus-tf2/deeplabv3-plus-keras在测试集上的结果显著优于deeplabv3-plus-pytorch版本。 是否因为前者使用的是dice_loss_with_CE而后者只使用DiceLoss进行训练?还是有其它别的原因?

    opened by fyang93 3
  • 关于替换为我自己的数据集训练的问题

    关于替换为我自己的数据集训练的问题

    我替换为自己的数据集进行训练,但是一直遇到ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 256, 1, 1]),这个报错,百度了都说是batch_size可能多出来了,把drop_last设置为true就好了。可是我看你的代码里是设置的true啊,请问up怎么解决呢,我这边cuda:10.1 pytorch:1.2.0

    opened by Codingaworld 1
  • 模型输出问题

    模型输出问题

    老师好,想请问一下,默认导出onnx之后,模型输出是三通道的RGB图像,怎么将输出改为0或1的标签呀,比如我就对两个类进行分割(背景和目标),然后我希望输出二值图(背景为0,目标为1),就好像训练的数据集的标签一样 模型转onnx格式之后,输出是3通道的float图,仔细观察后通道1和通道2都有点奇怪,通道3是我想要的(需要格式转换),怎么控制网络直接输出灰度标签呢

    opened by YuriGao 4
Releases(v3.0)
Owner
Bubbliiiing
Bubbliiiing
URIE: Universal Image Enhancementfor Visual Recognition in the Wild

URIE: Universal Image Enhancementfor Visual Recognition in the Wild This is the implementation of the paper "URIE: Universal Image Enhancement for Vis

Taeyoung Son 43 Sep 12, 2022
Bytedance Inc. 2.5k Jan 06, 2023
NaijaSenti is an open-source sentiment and emotion corpora for four major Nigerian languages

NaijaSenti is an open-source sentiment and emotion corpora for four major Nigerian languages. This project was supported by lacuna-fund initiatives. Jump straight to one of the sections below, or jus

Hausa Natural Language Processing 14 Dec 20, 2022
Python package for multiple object tracking research with focus on laboratory animals tracking.

motutils is a Python package for multiple object tracking research with focus on laboratory animals tracking. Features loads: MOTChallenge CSV, sleap

Matěj Šmíd 2 Sep 05, 2022
This is a Pytorch implementation of the paper: Self-Supervised Graph Transformer on Large-Scale Molecular Data.

This is a Pytorch implementation of the paper: Self-Supervised Graph Transformer on Large-Scale Molecular Data.

212 Dec 25, 2022
Hub is a dataset format with a simple API for creating, storing, and collaborating on AI datasets of any size.

Hub is a dataset format with a simple API for creating, storing, and collaborating on AI datasets of any size. The hub data layout enables rapid transformations and streaming of data while training m

Activeloop 5.1k Jan 08, 2023
CVPR 2021

Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-image Translation [Paper] | [Poster] | [Codes] Yahui Liu1,3, Enver Sangineto1,

Yahui Liu 37 Sep 12, 2022
iBOT: Image BERT Pre-Training with Online Tokenizer

Image BERT Pre-Training with iBOT Official PyTorch implementation and pretrained models for paper iBOT: Image BERT Pre-Training with Online Tokenizer.

Bytedance Inc. 435 Jan 06, 2023
Layered Neural Atlases for Consistent Video Editing

Layered Neural Atlases for Consistent Video Editing Project Page | Paper This repository contains an implementation for the SIGGRAPH Asia 2021 paper L

Yoni Kasten 353 Dec 27, 2022
On the model-based stochastic value gradient for continuous reinforcement learning

On the model-based stochastic value gradient for continuous reinforcement learning This repository is by Brandon Amos, Samuel Stanton, Denis Yarats, a

Facebook Research 46 Dec 15, 2022
(Python, R, C/C++) Isolation Forest and variations such as SCiForest and EIF, with some additions (outlier detection + similarity + NA imputation)

IsoTree Fast and multi-threaded implementation of Extended Isolation Forest, Fair-Cut Forest, SCiForest (a.k.a. Split-Criterion iForest), and regular

141 Dec 29, 2022
Artificial Neural network regression model to predict the energy output in a combined cycle power plant.

Energy_Output_Predictor Artificial Neural network regression model to predict the energy output in a combined cycle power plant. Abstract Energy outpu

1 Feb 11, 2022
Gym for multi-agent reinforcement learning

PettingZoo is a Python library for conducting research in multi-agent reinforcement learning, akin to a multi-agent version of Gym. Our website, with

Farama Foundation 1.6k Jan 09, 2023
Official codes: Self-Supervised Learning by Estimating Twin Class Distribution

TWIST: Self-Supervised Learning by Estimating Twin Class Distributions Codes and pretrained models for TWIST: @article{wang2021self, title={Self-Sup

Bytedance Inc. 85 Dec 15, 2022
PyTorch code for training MM-DistillNet for multimodal knowledge distillation

There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge MM-DistillNet is a

51 Dec 20, 2022
Code for the paper titled "Prabhupadavani: A Code-mixed Speech Translation Data for 25 languages"

Prabhupadavani: A Code-mixed Speech Translation Data for 25 languages Code for the paper titled "Prabhupadavani: A Code-mixed Speech Translation Data

Ayush Daksh 12 Dec 01, 2022
ObjectDetNet is an easy, flexible, open-source object detection framework

Getting started with the ObjectDetNet ObjectDetNet is an easy, flexible, open-source object detection framework which allows you to easily train, resu

5 Aug 25, 2020
Official code for "On the Frequency Bias of Generative Models", NeurIPS 2021

Frequency Bias of Generative Models Generator Testbed Discriminator Testbed This repository contains official code for the paper On the Frequency Bias

35 Nov 01, 2022
ParaGen is a PyTorch deep learning framework for parallel sequence generation

ParaGen is a PyTorch deep learning framework for parallel sequence generation. Apart from sequence generation, ParaGen also enhances various NLP tasks, including sequence-level classification, extrac

Bytedance Inc. 169 Dec 22, 2022
Computer Vision Paper Reviews with Key Summary of paper, End to End Code Practice and Jupyter Notebook converted papers

Computer-Vision-Paper-Reviews Computer Vision Paper Reviews with Key Summary along Papers & Codes. Jonathan Choi 2021 The repository provides 100+ Pap

Jonathan Choi 2 Mar 17, 2022