这篇文章将为大家详细讲解有关Keras:Unet网络如何实现多类语义分割，小编觉得挺实用的，因此分享给大家做个参考，希望大家阅读完这篇文章后可以有所收获。 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.h6')
#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.h6')
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。 
关于Keras:Unet网络如何实现多类语义分割？就分享到这里了，希望以上内容可以对大家有一定的帮助，可以学到更多知识。如果觉得文章不错，可以把它分享出去让更多的人看到。
|