# image-segmentation-keras

**Repository Path**: bees_huang/image-segmentation-keras

## Basic Information

- **Project Name**: image-segmentation-keras
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: GPL-3.0
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 2
- **Created**: 2020-03-26
- **Last Updated**: 2021-05-13

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# 图像分割Keras：在Keras中实现Segnet、FCN、UNet、PSPNet等模型。

[![PyPI version](https://badge.fury.io/py/keras-segmentation.svg)](https://badge.fury.io/py/keras-segmentation)
[![Downloads](https://pepy.tech/badge/keras-segmentation)](https://pepy.tech/project/keras-segmentation)
[![Build Status](https://travis-ci.org/divamgupta/image-segmentation-keras.png)](https://travis-ci.org/divamgupta/image-segmentation-keras)
[![Say Thanks!](https://img.shields.io/badge/Say%20Thanks-!-1EAEDB.svg)](https://saythanks.io/to/divamgupta)
[![GPLv3 license](https://img.shields.io/badge/License-GPLv3-blue.svg)](http://perso.crans.org/besson/LICENSE.html)
[![Twitter](https://img.shields.io/twitter/url.svg?label=Follow%20%40divamgupta&style=social&url=https%3A%2F%2Ftwitter.com%2Fdivamgupta)](https://twitter.com/divamgupta)



各种深度图像分割模型在keras中的实现

链接到完整的博客文章和教程：https://divamgupta.com/image-segmentation/2019/06/06/deep-learning-semantic-segmentation-keras.html

<p align="center">
  <img src="https://raw.githubusercontent.com/sunshineatnoon/Paper-Collection/master/images/FCN1.png" width="50%" >
</p>

## 我们的其他仓库
- [Attention based Language Translation in Keras](https://github.com/divamgupta/attention-translation-keras)
- [Ladder Network in Keras](https://github.com/divamgupta/ladder_network_keras)  model achives 98% test accuracy on MNIST with just 100 labeled examples

### 贡献者

Divam Gupta : https://divamgupta.com [![Twitter](https://img.shields.io/twitter/url.svg?label=Follow%20%40divamgupta&style=social&url=https%3A%2F%2Ftwitter.com%2Fdivamgupta)](https://twitter.com/divamgupta)


[Rounaq Jhunjhunu wala](https://github.com/rjalfa)



## 模型

支持以下型号：

| model_name       | Base Model        | Segmentation Model |
|------------------|-------------------|--------------------|
| fcn_8            | Vanilla CNN       | FCN8               |
| fcn_32           | Vanilla CNN       | FCN8               |
| fcn_8_vgg        | VGG 16            | FCN8               |
| fcn_32_vgg       | VGG 16            | FCN32              |
| fcn_8_resnet50   | Resnet-50         | FCN32              |
| fcn_32_resnet50  | Resnet-50         | FCN32              |
| fcn_8_mobilenet  | MobileNet         | FCN32              |
| fcn_32_mobilenet | MobileNet         | FCN32              |
| pspnet           | Vanilla CNN       | PSPNet             |
| vgg_pspnet       | VGG 16            | PSPNet             |
| resnet50_pspnet  | Resnet-50         | PSPNet             |
| unet_mini        | Vanilla Mini CNN  | U-Net              |
| unet             | Vanilla CNN       | U-Net              |
| vgg_unet         | VGG 16            | U-Net              |
| resnet50_unet    | Resnet-50         | U-Net              |
| mobilenet_unet   | MobileNet         | U-Net              |
| segnet           | Vanilla CNN       | Segnet             |
| vgg_segnet       | VGG 16            | Segnet             |
| resnet50_segnet  | Resnet-50         | Segnet             |
| mobilenet_segnet | MobileNet         | Segnet             |


提供的预训练模型的示例结果：

输入图像                   |  输出分割图像
:-------------------------:|:-------------------------:
![](sample_images/1_input.jpg)  |  ![](sample_images/1_output.png)
![](sample_images/3_input.jpg)  |  ![](sample_images/3_output.png)


## 入门

### 先决条件

* Keras 2.0
* opencv for python
* Theano / Tensorflow / CNTK

```shell
apt-get install -y libsm6 libxext6 libxrender-dev
pip install opencv-python
```

### 安装

安装模块

```shell
pip install keras-segmentation
```

或

```shell
pip install git+https://github.com/divamgupta/image-segmentation-keras
```

### 或

```shell
git clone https://github.com/divamgupta/image-segmentation-keras
cd image-segmentation-keras
python setup.py install
```


## 预先培训的模型：

```python
from keras_segmentation.pretrained import pspnet_50_ADE_20K , pspnet_101_cityscapes, pspnet_101_voc12

model = pspnet_50_ADE_20K() # load the pretrained model trained on ADE20k dataset

model = pspnet_101_cityscapes() # load the pretrained model trained on Cityscapes dataset

model = pspnet_101_voc12() # load the pretrained model trained on Pascal VOC 2012 dataset

# load any of the 3 pretrained models

out = model.predict_segmentation(
    inp="input_image.jpg",
    out_fname="out.png"
)

```


###准备培训数据

你需要做两个文件夹

*  Images Folder - 所有的训练图像
* Annotations Folder - 对于相应的地面真值分割图像

注释图像的文件名应与RGB图像的文件名相同。

相应RGB图像的注释图像大小应相同。

对于RGB图像中的每个像素，注释图像中该像素的类标签将是蓝色像素的值。

生成注释图像的示例代码：

```python
import cv2
import numpy as np

ann_img = np.zeros((30,30,3)).astype('uint8')
ann_img[ 3 , 4 ] = 1 # this would set the label of pixel 3,4 as 1

cv2.imwrite( "ann_1.png" ,ann_img )
```

仅对批注图像使用bmp或png格式。

## 下载准备好的样本数据集

Download and extract the following:

https://drive.google.com/file/d/0B0d9ZiqAgFkiOHR1NTJhWVJMNEU/view?usp=sharing

您将得到一个名为dataset1的文件夹/


## 使用python模块

可以在python脚本中导入keras_分段并使用API

```python
from keras_segmentation.models.unet import vgg_unet

model = vgg_unet(n_classes=51 ,  input_height=416, input_width=608  )

model.train(
    train_images =  "dataset1/images_prepped_train/",
    train_annotations = "dataset1/annotations_prepped_train/",
    checkpoints_path = "/tmp/vgg_unet_1" , epochs=5
)

out = model.predict_segmentation(
    inp="dataset1/images_prepped_test/0016E5_07965.png",
    out_fname="/tmp/out.png"
)

import matplotlib.pyplot as plt
plt.imshow(out)

# 评估模型
print(model.evaluate_segmentation( inp_images_dir="dataset1/images_prepped_test/"  , annotations_dir="dataset1/annotations_prepped_test/" ) )

```


## 通过命令行使用
也可以仅使用命令行使用该工具

### 将准备好的数据可视化

您还可以将准备好的注释可视化，以验证准备好的数据。


```shell
python -m keras_segmentation verify_dataset \
 --images_path="dataset1/images_prepped_train/" \
 --segs_path="dataset1/annotations_prepped_train/"  \
 --n_classes=50
```

```shell
python -m keras_segmentation visualize_dataset \
 --images_path="dataset1/images_prepped_train/" \
 --segs_path="dataset1/annotations_prepped_train/"  \
 --n_classes=50
```



### 训练模型

要训练模型，请运行以下命令：

```shell
python -m keras_segmentation train \
 --checkpoints_path="path_to_checkpoints" \
 --train_images="dataset1/images_prepped_train/" \
 --train_annotations="dataset1/annotations_prepped_train/" \
 --val_images="dataset1/images_prepped_test/" \
 --val_annotations="dataset1/annotations_prepped_test/" \
 --n_classes=50 \
 --input_height=320 \
 --input_width=640 \
 --model_name="vgg_unet"
```

从上表中选择型号名称



### 得到预测

得到训练模型的预测

```shell
python -m keras_segmentation predict \
 --checkpoints_path="path_to_checkpoints" \
 --input_path="dataset1/images_prepped_test/" \
 --output_path="path_to_predictions"

```

### 模型评估

拿到评估分数

```shell
python -m keras_segmentation evaluate_model \
 --checkpoints_path="path_to_checkpoints" \
 --images_path="dataset1/images_prepped_test/" \
 --segs_path="dataset1/annotations_prepped_test/"
```



## 分割模型微调

下面的示例演示如何使用10个类微调模型。

```python
from keras_segmentation.models.model_utils import transfer_weights
from keras_segmentation.pretrained import pspnet_50_ADE_20K
from keras_segmentation.models.pspnet import pspnet_50

pretrained_model = pspnet_50_ADE_20K()

new_model = pspnet_50( n_classes=51 )

transfer_weights( pretrained_model , new_model  ) # 将重量从预先训练的模型转移到您的模型

new_model.train(
    train_images =  "dataset1/images_prepped_train/",
    train_annotations = "dataset1/annotations_prepped_train/",
    checkpoints_path = "/tmp/vgg_unet_1" , epochs=5
)


```

## 使用keras分段的项目
以下是一些正在使用我们的库的项目：
* https://github.com/SteliosTsop/QF-image-segmentation-keras [paper](https://arxiv.org/pdf/1908.02242.pdf)
* https://github.com/willembressers/bouquet_quality
* https://github.com/jqueguiner/image-segmentation
* https://github.com/theerawatramchuen/Keras_Segmentation
* https://github.com/neheller/labels18
* https://github.com/shsh-a/segmentation-over-web
* https://github.com/chenwe73/deep_active_learning_segmentation
* https://github.com/vigneshrajap/vision-based-navigation-agri-fields
* https://github.com/ronalddas/Pneumonia-Detection
* https://github.com/Aiwiscal/ECG_UNet
* https://github.com/TianzhongSong/Unet-for-Person-Segmentation
* https://github.com/Guyanqi/GMDNN
* https://github.com/kozemzak/prostate-lesion-segmentation
* https://github.com/lixiaoyu12138/fcn-date
* https://github.com/sagarbhokre/LyftChallenge
* https://github.com/TianzhongSong/Person-Segmentation-Keras
* https://github.com/divyanshpuri02/COCO_2018-Stuff-Segmentation-Challenge
* https://github.com/XiangbingJi/Stanford-cs230-final-project
* https://github.com/lsh1994/keras-segmentation
* https://github.com/SpirinEgor/mobile_semantic_segmentation
* https://github.com/LeadingIndiaAI/COCO-DATASET-STUFF-SEGMENTATION-CHALLENGE
* https://github.com/lidongyue12138/Image-Segmentation-by-Keras
* https://github.com/laoj2/segnet_crfasrnn
* https://github.com/rancheng/AirSimProjects
* https://github.com/RadiumScriptTang/cartoon_segmentation
* https://github.com/dquail/NerveSegmentation
* https://github.com/Bhomik/SemanticHumanMatting
* https://github.com/Symefa/FP-Biomedik-Breast-Cancer
* https://github.com/Alpha-Monocerotis/PDF_FigureTable_Extraction
* https://github.com/rusito-23/mobile_unet_segmentation
* https://github.com/Philliec459/ThinSection-image-segmentation-keras

如果您在公共项目中使用我们的代码，请在此处添加链接（通过发布问题或创建PR）