DeepLabv3+:Encoder-Decoder with Atrous Separable Convolution语义分割模型在tensorflow2当中的实现

Overview

DeepLabv3+:Encoder-Decoder with Atrous Separable Convolution语义分割模型在tensorflow2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 deeplabv3_mobilenetv2.h5 VOC-Val12 512x512 72.50
VOC12+SBD deeplabv3_xception.h5 VOC-Val12 512x512 87.10

所需环境

tensorflow==2.2.0

注意事项

代码中的deeplabv3_mobilenetv2.h5和deeplabv3_xception.h5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deeplabv3_mobilenetv2.h5和deeplabv3_xception.h5可在百度网盘中下载。
链接: https://pan.baidu.com/s/1zVRshWRkb5C3kmDMwEf89A 提取码: ccq5

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.h5,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/deeplabv3_mobilenetv2.h5',
    #----------------------------------------#
    #   所需要区分的类的个数+1
    #----------------------------------------#
    "num_classes"       : 21,
    #----------------------------------------#
    #   所使用的的主干网络:mobilenet、xception    
    #----------------------------------------#
    "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,
}

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...
Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning (ICLR 2021)

Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning (ICLR 2021) Citation Please cite as: @inproceedings{liu2020understan

《LXMERT: Learning Cross-Modality Encoder Representations from Transformers》(EMNLP 2020)

The Most Important Thing. Our code is developed based on: LXMERT: Learning Cross-Modality Encoder Representations from Transformers

Official implementation for Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder at NeurIPS 2020

Likelihood-Regret Official implementation of Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder at NeurIPS 2020. T

Official Implementation for
Official Implementation for "ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement" https://arxiv.org/abs/2104.02699

ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement Recently, the power of unconditional image synthesis has significantly advanced th

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

A Joint Video and Image Encoder for End-to-End Retrieval
A Joint Video and Image Encoder for End-to-End Retrieval

Frozen️ in Time ❄️ ️️️️ ⏳ A Joint Video and Image Encoder for End-to-End Retrieval project page | arXiv | webvid-data Repository containing the code,

PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.
PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.

VAENAR-TTS - PyTorch Implementation PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.

Code for the paper
Code for the paper "Adversarial Generator-Encoder Networks"

This repository contains code for the paper "Adversarial Generator-Encoder Networks" (AAAI'18) by Dmitry Ulyanov, Andrea Vedaldi, Victor Lempitsky. Pr

PyTorch implementation of SQN based on CloserLook3D's encoder

SQN_pytorch This repo is an implementation of Semantic Query Network (SQN) using CloserLook3D's encoder in Pytorch. For TensorFlow implementation, che

Comments
  • How to reproduce the model deeplabv3_xception.h5?

    How to reproduce the model deeplabv3_xception.h5?

    Hi, I'm trying to train deeplabv3 with xception backbone on voc + SBD dataset. You provided the voc pretrained model deeplabv3_xception.h5. But If I want to reproduce your training result, I should not use it as pretrained model, right? So I comment out the line in train.py to not loading pretrained weights. But after 100 epochs, my model accuracy is poor, compared with your model. Did I miss something, do I need something like an ImageNet pretrained model or COCO pretrained model? Thanks!

    opened by zhimengf 6
  • How to export a .pb file

    How to export a .pb file

    Hi, I have problem exporting a .pb file with the current produced .h5 files. I do not think you have provided the export method in the project file. Could you please give me some advice on that? @bubbliiiing

    opened by 77knight 1
Releases(v3.0)
  • v3.0(Apr 22, 2022)

    重要更新

    • 支持step、cos学习率下降法。
    • 支持adam、sgd优化器选择。
    • 支持学习率根据batch_size自适应调整。
    • 支持不同预测模式的选择,单张图片预测、文件夹预测、视频预测、图片裁剪。
    • 更新summary.py文件,用于观看网络结构。
    • 增加了多GPU训练。
    Source code(tar.gz)
    Source code(zip)
  • v2.0(Mar 4, 2022)

    重要更新

    • 更新train.py文件,增加了大量的注释,增加多个可调整参数。
    • 更新predict.py文件,增加了大量的注释,增加fps、视频预测、批量预测等功能。
    • 更新deeplab.py文件,增加了大量的注释,增加先验框选择、置信度、非极大抑制等参数。
    • 合并get_dr_txt.py、get_gt_txt.py和get_map.py文件,通过一个文件来实现数据集的评估。
    • 更新voc_annotation.py文件,增加多个可调整参数。
    • 更新summary.py文件,用于观看网络结构。
    Source code(tar.gz)
    Source code(zip)
Owner
Bubbliiiing
Bubbliiiing
Azua - build AI algorithms to aid efficient decision-making with minimum data requirements.

Project Azua 0. Overview Many modern AI algorithms are known to be data-hungry, whereas human decision-making is much more efficient. The human can re

Microsoft 197 Jan 06, 2023
Mix3D: Out-of-Context Data Augmentation for 3D Scenes (3DV 2021)

Mix3D: Out-of-Context Data Augmentation for 3D Scenes (3DV 2021) Alexey Nekrasov*, Jonas Schult*, Or Litany, Bastian Leibe, Francis Engelmann Mix3D is

Alexey Nekrasov 189 Dec 26, 2022
A small tool to joint picture including gif

README 做设计的时候遇到拼接长图的情况,但是发现没有什么好用的能拼接gif的工具。 于是自己写了个gif拼接小工具。 可以自动拼接gif、png和jpg等常见格式。 效果 从上至下 从下至上 从左至右 从右至左 使用 克隆仓库 git clone https://github.com/Dels

3 Dec 15, 2021
Tutorials, assignments, and competitions for MIT Deep Learning related courses.

MIT Deep Learning This repository is a collection of tutorials for MIT Deep Learning courses. More added as courses progress. Tutorial: Deep Learning

Lex Fridman 9.5k Jan 07, 2023
The implementation our EMNLP 2021 paper "Enhanced Language Representation with Label Knowledge for Span Extraction".

LEAR The implementation our EMNLP 2021 paper "Enhanced Language Representation with Label Knowledge for Span Extraction". **The code is in the "master

杨攀 93 Jan 07, 2023
DiSECt: Differentiable Simulator for Robotic Cutting

DiSECt: Differentiable Simulator for Robotic Cutting Website | Paper | Dataset | Video | Blog post DiSECt is a simulator for the cutting of deformable

NVIDIA Research Projects 73 Oct 29, 2022
PyTorch implementation of UNet++ (Nested U-Net).

PyTorch implementation of UNet++ (Nested U-Net) This repository contains code for a image segmentation model based on UNet++: A Nested U-Net Architect

4ui_iurz1 642 Jan 04, 2023
Chunkmogrify: Real image inversion via Segments

Chunkmogrify: Real image inversion via Segments Teaser video with live editing sessions can be found here This code demonstrates the ideas discussed i

David Futschik 112 Jan 04, 2023
Code base for the paper "Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation"

This repository contains code for the paper Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiati

8 Aug 28, 2022
Official repository for "Restormer: Efficient Transformer for High-Resolution Image Restoration". SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.

Restormer: Efficient Transformer for High-Resolution Image Restoration Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan,

Syed Waqas Zamir 906 Dec 30, 2022
face2comics by Sxela (Alex Spirin) - face2comics datasets

This is a paired face to comics dataset, which can be used to train pix2pix or similar networks.

Alex 164 Nov 13, 2022
Intel® Nervana™ reference deep learning framework committed to best performance on all hardware

DISCONTINUATION OF PROJECT. This project will no longer be maintained by Intel. Intel will not provide or guarantee development of or support for this

Nervana 3.9k Dec 20, 2022
The aim of this project is to build an AI bot that can play the Wordle game, or more generally Squabble

Wordle RL The aim of this project is to build an AI bot that can play the Wordle game, or more generally Squabble I know there are more deterministic

Aditya Arora 3 Feb 22, 2022
The codes and related files to reproduce the results for Image Similarity Challenge Track 1.

ISC-Track1-Submission The codes and related files to reproduce the results for Image Similarity Challenge Track 1. Required dependencies To begin with

Wenhao Wang 115 Jan 02, 2023
ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction

ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction. NeurIPS 2021.

Gengshan Yang 59 Nov 25, 2022
Memory-Augmented Model Predictive Control

Memory-Augmented Model Predictive Control This repository hosts the source code for the journal article "Composing MPC with LQR and Neural Networks fo

Fangyu Wu 1 Jun 19, 2022
True per-item rarity for Loot

True-Rarity True per-item rarity for Loot (For Adventurers) and More Loot A.K.A mLoot each out/true_rarity_{item_type}.json file contains probabilitie

Dan R. 3 Jul 26, 2022
Author's PyTorch implementation of TD3 for OpenAI gym tasks

Addressing Function Approximation Error in Actor-Critic Methods PyTorch implementation of Twin Delayed Deep Deterministic Policy Gradients (TD3). If y

Scott Fujimoto 1.3k Dec 25, 2022
This is the official pytorch implementation of Student Helping Teacher: Teacher Evolution via Self-Knowledge Distillation(TESKD)

Student Helping Teacher: Teacher Evolution via Self-Knowledge Distillation (TESKD) By Zheng Li[1,4], Xiang Li[2], Lingfeng Yang[2,4], Jian Yang[2], Zh

Zheng Li 9 Sep 26, 2022
Remote sensing change detection using PaddlePaddle

Change Detection Laboratory Developing and benchmarking deep learning-based remo

Lin Manhui 15 Sep 23, 2022