Keras:Unet网络实现多类语义分割方式


Posted in Python onJune 11, 2020

1 介绍

U-Net最初是用来对医学图像的语义分割,后来也有人将其应用于其他领域。但大多还是用来进行二分类,即将原始图像分成两个灰度级或者色度,依次找到图像中感兴趣的目标部分。

本文主要利用U-Net网络结构实现了多类的语义分割,并展示了部分测试效果,希望对你有用!

2 源代码

(1)训练模型

from __future__ import print_function
import os
import datetime
import numpy as np
from keras.models import Model
from keras.layers import Input, concatenate, Conv2D, MaxPooling2D, Conv2DTranspose, AveragePooling2D, Dropout, \
 BatchNormalization
from keras.optimizers import Adam
from keras.layers.convolutional import UpSampling2D, Conv2D
from keras.callbacks import ModelCheckpoint
from keras import backend as K
from keras.layers.advanced_activations import LeakyReLU, ReLU
import cv2
 
PIXEL = 512 #set your image size
BATCH_SIZE = 5
lr = 0.001
EPOCH = 100
X_CHANNEL = 3 # training images channel
Y_CHANNEL = 1 # label iamges channel
X_NUM = 422 # your traning data number
 
pathX = 'I:\\Pascal VOC Dataset\\train1\\images\\' #change your file path
pathY = 'I:\\Pascal VOC Dataset\\train1\\SegmentationObject\\' #change your file path
 
#data processing
def generator(pathX, pathY,BATCH_SIZE):
 while 1:
  X_train_files = os.listdir(pathX)
  Y_train_files = os.listdir(pathY)
  a = (np.arange(1, X_NUM))
  X = []
  Y = []
  for i in range(BATCH_SIZE):
   index = np.random.choice(a)
   # print(index)
   img = cv2.imread(pathX + X_train_files[index], 1)
   img = np.array(img).reshape(PIXEL, PIXEL, X_CHANNEL)
   X.append(img)
   img1 = cv2.imread(pathY + Y_train_files[index], 1)
   img1 = np.array(img1).reshape(PIXEL, PIXEL, Y_CHANNEL)
   Y.append(img1)
 
  X = np.array(X)
  Y = np.array(Y)
  yield X, Y
 
 #creat unet network
inputs = Input((PIXEL, PIXEL, 3))
conv1 = Conv2D(8, 3, activation='relu', padding='same', kernel_initializer='he_normal')(inputs)
pool1 = AveragePooling2D(pool_size=(2, 2))(conv1) # 16
 
conv2 = BatchNormalization(momentum=0.99)(pool1)
conv2 = Conv2D(64, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv2)
conv2 = BatchNormalization(momentum=0.99)(conv2)
conv2 = Conv2D(64, 1, activation='relu', padding='same', kernel_initializer='he_normal')(conv2)
conv2 = Dropout(0.02)(conv2)
pool2 = AveragePooling2D(pool_size=(2, 2))(conv2) # 8
 
conv3 = BatchNormalization(momentum=0.99)(pool2)
conv3 = Conv2D(128, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv3)
conv3 = BatchNormalization(momentum=0.99)(conv3)
conv3 = Conv2D(128, 1, activation='relu', padding='same', kernel_initializer='he_normal')(conv3)
conv3 = Dropout(0.02)(conv3)
pool3 = AveragePooling2D(pool_size=(2, 2))(conv3) # 4
 
conv4 = BatchNormalization(momentum=0.99)(pool3)
conv4 = Conv2D(256, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv4)
conv4 = BatchNormalization(momentum=0.99)(conv4)
conv4 = Conv2D(256, 1, activation='relu', padding='same', kernel_initializer='he_normal')(conv4)
conv4 = Dropout(0.02)(conv4)
pool4 = AveragePooling2D(pool_size=(2, 2))(conv4)
 
conv5 = BatchNormalization(momentum=0.99)(pool4)
conv5 = Conv2D(512, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv5)
conv5 = BatchNormalization(momentum=0.99)(conv5)
conv5 = Conv2D(512, 1, activation='relu', padding='same', kernel_initializer='he_normal')(conv5)
conv5 = Dropout(0.02)(conv5)
pool4 = AveragePooling2D(pool_size=(2, 2))(conv4)
# conv5 = Conv2D(35, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv4)
# drop4 = Dropout(0.02)(conv5)
pool4 = AveragePooling2D(pool_size=(2, 2))(pool3) # 2
pool5 = AveragePooling2D(pool_size=(2, 2))(pool4) # 1
 
conv6 = BatchNormalization(momentum=0.99)(pool5)
conv6 = Conv2D(256, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv6)
 
conv7 = Conv2D(256, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv6)
up7 = (UpSampling2D(size=(2, 2))(conv7)) # 2
conv7 = Conv2D(256, 3, activation='relu', padding='same', kernel_initializer='he_normal')(up7)
merge7 = concatenate([pool4, conv7], axis=3)
 
conv8 = Conv2D(128, 3, activation='relu', padding='same', kernel_initializer='he_normal')(merge7)
up8 = (UpSampling2D(size=(2, 2))(conv8)) # 4
conv8 = Conv2D(128, 3, activation='relu', padding='same', kernel_initializer='he_normal')(up8)
merge8 = concatenate([pool3, conv8], axis=3)
 
conv9 = Conv2D(64, 3, activation='relu', padding='same', kernel_initializer='he_normal')(merge8)
up9 = (UpSampling2D(size=(2, 2))(conv9)) # 8
conv9 = Conv2D(64, 3, activation='relu', padding='same', kernel_initializer='he_normal')(up9)
merge9 = concatenate([pool2, conv9], axis=3)
 
conv10 = Conv2D(32, 3, activation='relu', padding='same', kernel_initializer='he_normal')(merge9)
up10 = (UpSampling2D(size=(2, 2))(conv10)) # 16
conv10 = Conv2D(32, 3, activation='relu', padding='same', kernel_initializer='he_normal')(up10)
 
conv11 = Conv2D(16, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv10)
up11 = (UpSampling2D(size=(2, 2))(conv11)) # 32
conv11 = Conv2D(8, 3, activation='relu', padding='same', kernel_initializer='he_normal')(up11)
 
# conv12 = Conv2D(3, 1, activation='relu', padding='same', kernel_initializer='he_normal')(conv11)
conv12 = Conv2D(3, 1, activation='relu', padding='same', kernel_initializer='he_normal')(conv11)
 
model = Model(input=inputs, output=conv12)
print(model.summary())
model.compile(optimizer=Adam(lr=1e-3), loss='mse', metrics=['accuracy'])
 
history = model.fit_generator(generator(pathX, pathY,BATCH_SIZE),
        steps_per_epoch=600, nb_epoch=EPOCH)
end_time = datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')
 
 #save your training model
model.save(r'V1_828.h5')
 
#save your loss data
mse = np.array((history.history['loss']))
np.save(r'V1_828.npy', mse)

(2)测试模型

from keras.models import load_model
import numpy as np
import matplotlib.pyplot as plt
import os
import cv2
 
model = load_model('V1_828.h5')
test_images_path = 'I:\\Pascal VOC Dataset\\test\\test_images\\'
test_gt_path = 'I:\\Pascal VOC Dataset\\test\\SegmentationObject\\'
pre_path = 'I:\\Pascal VOC Dataset\\test\\pre\\'
 
X = []
for info in os.listdir(test_images_path):
 A = cv2.imread(test_images_path + info)
 X.append(A)
 # i += 1
X = np.array(X)
print(X.shape)
Y = model.predict(X)
 
groudtruth = []
for info in os.listdir(test_gt_path):
 A = cv2.imread(test_gt_path + info)
 groudtruth.append(A)
groudtruth = np.array(groudtruth)
 
i = 0
for info in os.listdir(test_images_path):
 cv2.imwrite(pre_path + info,Y[i])
 i += 1
 
a = range(10)
n = np.random.choice(a)
cv2.imwrite('prediction.png',Y[n])
cv2.imwrite('groudtruth.png',groudtruth[n])
fig, axs = plt.subplots(1, 3)
# cnt = 1
# for j in range(1):
axs[0].imshow(np.abs(X[n]))
axs[0].axis('off')
axs[1].imshow(np.abs(Y[n]))
axs[1].axis('off')
axs[2].imshow(np.abs(groudtruth[n]))
axs[2].axis('off')
 # cnt += 1
fig.savefig("imagestest.png")
plt.close()

3 效果展示

说明:从左到右依次是预测图像,真实图像,标注图像。可以看出,对于部分数据的分割效果还有待改进,主要原因还是数据集相对复杂,模型难于找到其中的规律。

Keras:Unet网络实现多类语义分割方式

以上这篇Keras:Unet网络实现多类语义分割方式就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持三水点靠木。

Python 相关文章推荐
各个系统下的Python解释器相关安装方法
Oct 12 Python
浅析Python中MySQLdb的事务处理功能
Sep 21 Python
python去掉行尾的换行符方法
Jan 04 Python
Python生成任意范围任意精度的随机数方法
Apr 09 Python
opencv3/C++图像像素操作详解
Dec 10 Python
Python 实现数组相减示例
Dec 27 Python
解析pip安装第三方库但PyCharm中却无法识别的问题及PyCharm安装第三方库的方法教程
Mar 10 Python
python 安装impala包步骤
Mar 28 Python
jupyter notebook的安装与使用详解
May 18 Python
Python实现一个优先级队列的方法
Jul 31 Python
django下创建多个app并设置urls方法
Aug 02 Python
Python3中的tuple函数知识点讲解
Jan 03 Python
Pycharm中配置远程Docker运行环境的教程图解
Jun 11 #Python
Keras 快速解决OOM超内存的问题
Jun 11 #Python
python3.6.8 + pycharm + PyQt5 环境搭建的图文教程
Jun 11 #Python
使用keras实现孪生网络中的权值共享教程
Jun 11 #Python
查看keras各种网络结构各层的名字方式
Jun 11 #Python
python datetime时间格式的相互转换问题
Jun 11 #Python
完美解决keras保存好的model不能成功加载问题
Jun 11 #Python
You might like
php 删除数组元素
2009/01/16 PHP
php array_walk() 数组函数
2011/07/12 PHP
php mysql实现mysql_select_db选择数据库
2016/12/30 PHP
Thinkphp5结合layer弹窗定制操作结果页面
2017/07/07 PHP
Thinkphp自定义生成缩略图尺寸的方法
2019/08/05 PHP
使用js判断控件是否获得焦点
2014/01/03 Javascript
Blocksit插件实现瀑布流数据无限( 异步)加载
2014/06/20 Javascript
javascript的几种写法总结
2016/09/30 Javascript
js判断价格,必须为数字且不能为负数的实现方法
2016/10/07 Javascript
javascript self对象使用详解
2016/10/18 Javascript
通过jsonp获取json数据实现AJAX跨域请求
2017/01/22 Javascript
Vue 进阶教程之v-model详解
2017/05/06 Javascript
JavaScript基础之流程控制语句的用法
2017/08/31 Javascript
Node.js Express安装与使用教程
2018/05/11 Javascript
使用proxy实现一个更优雅的vue【推荐】
2018/06/19 Javascript
发布一款npm包帮助理解npm的使用
2019/01/03 Javascript
JavaScript冒泡算法原理与实现方法深入理解
2020/06/04 Javascript
python将人民币转换大写的脚本代码
2013/02/10 Python
python实现2014火车票查询代码分享
2014/01/10 Python
Python中请使用isinstance()判断变量类型
2014/08/25 Python
Python中Django框架利用url来控制登录的方法
2015/07/25 Python
python urllib urlopen()对象方法/代理的补充说明
2017/06/29 Python
python利用ffmpeg进行录制屏幕的方法
2019/01/10 Python
在python中利用numpy求解多项式以及多项式拟合的方法
2019/07/03 Python
Python K最近邻从原理到实现的方法
2019/08/15 Python
解决python中import文件夹下面py文件报错问题
2020/06/01 Python
python Matplotlib模块的使用
2020/09/16 Python
世界上最大的艺术和工艺用品商店:MisterArt.com
2018/07/13 全球购物
全球异乡人的跨境社交电商平台:Kouhigh口嗨网
2020/07/24 全球购物
中文教师求职信
2014/02/22 职场文书
技术总监管理职责范本
2014/03/06 职场文书
领导干部学习“三严三实”思想汇报
2014/09/15 职场文书
法定代表人授权委托书
2014/09/19 职场文书
Mysql 性能监控及调优
2021/04/06 MySQL
SSM VUE Axios详解
2021/10/05 Vue.js
如何解决php-fpm启动不了问题
2021/11/17 PHP