Keras:Unet网络实现多类语义分割方式
更新时间：2020年06月11日 10:39:44 作者：Robin Long 2018
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！
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。
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脚本之家。
相关文章
Apache Flink是一个流处理框架,用于实时处理和分析数据流,PyFlink是Apache Flink的Python API,它允许用户使用Python语言来编写Flink作业,进行实时数据处理,以下是如何使用Flink与Python进行实时数据处理的基本步骤,需要的朋友可以参考下2024-09-09
这篇文章主要介绍了Python中使用PyQt把网页转换成PDF操作代码实例,本文直接给出实现代码,需要的朋友可以参考下2015-04-04
这篇文章主要介绍了pycharm新建Vue项目的方法步骤，文中通过示例代码介绍的非常详细，对大家的学习或者工作具有一定的参考学习价值，需要的朋友们下面随着小编来一起学习学习吧2020-03-03
Bokeh 是一个流行的 Python 数据可视化库，可以生成高质量的交互式图表，这篇文章主要就介绍了Python如何使用Bokeh实现交互式图表的创建，需要的可以参考一下2023-06-06
A/B测试，通过分析两种不同的营销策略，以此来选择最佳的营销策略，可以高效地将流量转化为销售额。本文主要介绍了如何通过Python实现一个A/B测试，感兴趣的可以了解一下2023-01-01
这篇文章主要介绍了python使用7z解压apk包的方法,涉及Python的shell命令调用技巧,非常具有实用价值,需要的朋友可以参考下2015-04-04
这篇文章主要介绍了Python编程中如何通过鼠标事件及坐标获取窗口坐标和屏幕坐标的示例解析，有需要的朋友可以借鉴参考下，希望能够有所帮助2021-10-10
这篇文章主要介绍了Python中字典创建、遍历、添加等实用操作技巧合集,本文讲解了字典中常见方法列表、创建字典的五种方法、字典中键值遍历方法等内容,需要的朋友可以参考下2015-06-06
这篇文章主要介绍了pandas数据处理之绘图的实现，文中通过示例代码介绍的非常详细，对大家的学习或者工作具有一定的参考学习价值，需要的朋友们下面随着小编来一起学习学习吧2020-06-06
global关键字用来在函数或其他局部作用域中使用全局变量， nonlocal声明的变量不是局部变量,也不是全局变量,而是外部嵌套函数内的变量。这篇文章主要介绍了Python中 Global和Nonlocal的用法,需要的朋友可以参考下2020-01-01
最新评论