深度学习之unet深度网络用于煤岩裂缝提取

本文为github上开源的unet神经网络，用于复习和记录
1.环境配置情况：

h5py                   2.10.0
html5lib               0.9999999
Keras                  2.0.6
Keras-Applications     1.0.8
Keras-Preprocessing    1.1.2
matplotlib             3.3.2
numpy                  1.19.2
opencv-contrib-python  4.4.0.44
opencv-python          4.4.0.44
pandas                 1.1.3
requests               2.25.1
scikit-image           0.17.2
scipy                  1.5.2
tensorflow-gpu         1.3.0
tensorflow-tensorboard 0.1.8

2.训练集数据处理：

from __future__ import print_function
from keras.preprocessing.image import ImageDataGenerator
import numpy as np 
import os
import glob
import skimage.io as io
import skimage.transform as trans

Sky = [128,128,128]
Building = [128,0,0]
Pole = [192,192,128]
Road = [128,64,128]
Pavement = [60,40,222]
Tree = [128,128,0]
SignSymbol = [192,128,128]
Fence = [64,64,128]
Car = [64,0,128]
Pedestrian = [64,64,0]
Bicyclist = [0,128,192]
Unlabelled = [0,0,0]

COLOR_DICT = np.array([Sky, Building, Pole, Road, Pavement,
                          Tree, SignSymbol, Fence, Car, Pedestrian, Bicyclist, Unlabelled])


def adjustData(img,mask,flag_multi_class,num_class):
    if(flag_multi_class):#此程序中不是多类情况，所以不考虑这个
        img = img / 255
        mask = mask[:,:,:,0] if(len(mask.shape) == 4) else mask[:,:,0]
        new_mask = np.zeros(mask.shape + (num_class,))
        for i in range(num_class):
            #for one pixel in the image, find the class in mask and convert it into one-hot vector
            #index = np.where(mask == i)
            #index_mask = (index[0],index[1],index[2],np.zeros(len(index[0]),dtype = np.int64) + i) if (len(mask.shape) == 4) else (index[0],index[1],np.zeros(len(index[0]),dtype = np.int64) + i)
            #new_mask[index_mask] = 1
            new_mask[mask == i,i] = 1
        new_mask = np.reshape(new_mask,(new_mask.shape[0],new_mask.shape[1]*new_mask.shape[2],new_mask.shape[3])) if flag_multi_class else np.reshape(new_mask,(new_mask.shape[0]*new_mask.shape[1],new_mask.shape[2]))
        mask = new_mask
    elif(np.max(img) > 1):
        img = img / 255
        mask = mask /255
        mask[mask > 0.5] = 1
        mask[mask <= 0.5] = 0
    return (img,mask)
#上面这个函数主要是对训练集的数据和标签的像素值进行归一化


def trainGenerator(batch_size,train_path,image_folder,mask_folder,aug_dict,image_color_mode = "grayscale",
                    mask_color_mode = "grayscale",image_save_prefix  = "image",mask_save_prefix  = "mask",
                    flag_multi_class = False,num_class = 2,save_to_dir = None,target_size = (512,512),seed = 1):
    '''
    can generate image and mask at the same time
    use the same seed for image_datagen and mask_datagen to ensure the transformation for image and mask is the same
    if you want to visualize the results of generator, set save_to_dir = "your path"
    '''
    image_datagen = ImageDataGenerator(**aug_dict)
    mask_datagen = ImageDataGenerator(**aug_dict)
    image_generator = image_datagen.flow_from_directory(
        train_path,#训练数据文件夹路径
        classes = [image_folder],#类别文件夹,对哪一个类进行增强
        class_mode = None,#不返回标签
        color_mode = image_color_mode,#灰度，单通道模式
        target_size = target_size,#转换后的目标图片大小
        batch_size = batch_size,#每次产生的（进行转换的）图片张数
        save_to_dir = save_to_dir,#保存的图片路径
        save_prefix  = image_save_prefix,#生成图片的前缀，仅当提供save_to_dir时有效
        seed = seed)
    mask_generator = mask_datagen.flow_from_directory(
        train_path,
        classes = [mask_folder],
        class_mode = None,
        color_mode = mask_color_mode,
        target_size = target_size,
        batch_size = batch_size,
        save_to_dir = save_to_dir,
        save_prefix  = mask_save_prefix,
        seed = seed)
    train_generator = zip(image_generator, mask_generator)
    for (img,mask) in train_generator:
        # 由于batch是2，所以一次返回两张，即img是一个2张灰度图片的数组，[2,256,256]
        img,mask = adjustData(img,mask,flag_multi_class,num_class)
        yield (img,mask)
        #每次分别产出两张图片和标签
#上面这个函数主要是产生一个数据增强的图片生成器，方便后面使用这个生成器不断生成图片


def testGenerator(test_path,num_image = 30,target_size = (512,512),flag_multi_class = False,as_gray = True):
    for i in range(num_image):
        img = io.imread(os.path.join(test_path,"%d.png"%i),as_gray = as_gray)
        img = img / 255
        img = trans.resize(img,target_size)
        img = np.reshape(img,img.shape+(1,)) if (not flag_multi_class) else img
        img = np.reshape(img,(1,)+img.shape)
        # 将测试图片扩展一个维度，与训练时的输入[2,256,256]保持一致
        yield img
#上面这个函数主要是对测试图片进行规范，使其尺寸和维度上和训练图片保持一致


def geneTrainNpy(image_path,mask_path,flag_multi_class = False,num_class = 2,image_prefix = "image",mask_prefix = "mask",image_as_gray = True,mask_as_gray = True):
    image_name_arr = glob.glob(os.path.join(image_path,"%s*.png"%image_prefix))
    # 相当于文件搜索，搜索某路径下与字符匹配的文件
    image_arr = []
    mask_arr = []
    for index,item in enumerate(image_name_arr):#enumerate是枚举，输出[(0,item0),(1,item1),(2,item2)]
        img = io.imread(item,as_gray = image_as_gray)
        img = np.reshape(img,img.shape + (1,)) if image_as_gray else img
        mask = io.imread(item.replace(image_path,mask_path).replace(image_prefix,mask_prefix),as_gray = mask_as_gray)
        # 重新在mask_path文件夹下搜索带有mask字符的图片（标签图片）
        mask = np.reshape(mask,mask.shape + (1,)) if mask_as_gray else mask
        img,mask = adjustData(img,mask,flag_multi_class,num_class)
        image_arr.append(img)
        mask_arr.append(mask)
    image_arr = np.array(image_arr)
    mask_arr = np.array(mask_arr)#转换成array
    return image_arr,mask_arr
#该函数主要是分别在训练集文件夹下和标签文件夹下搜索图片，然后扩展一个维度后以array的形式返回，是为了在没用数据增强时的读取文件夹内自带的数据

def labelVisualize(num_class,color_dict,img):
    img = img[:,:,0] if len(img.shape) == 3 else img
    img_out = np.zeros(img.shape + (3,))
    # 变成RGB空间，因为其他颜色只能再RGB空间才会显示
    for i in range(num_class):
        img_out[img == i,:] = color_dict[i]
        # 为不同类别涂上不同的颜色，color_dict[i]是与类别数有关的颜色，img_out[img == i,:]是img_out在img中等于i类的位置上的点
    return img_out / 255
#上面函数是给出测试后的输出之后，为输出涂上不同的颜色，多类情况下才起作用，两类的话无用


def saveResult(save_path,npyfile,flag_multi_class = False,num_class = 2):
    for i,item in enumerate(npyfile):
        img = labelVisualize(num_class,COLOR_DICT,item) if flag_multi_class else item[:,:,0]
        # 多类的话就图成彩色，非多类（两类）的话就是黑白色
        io.imsave(os.path.join(save_path,"%d_predict.png"%i),img)

3.unet模型建立：

import numpy as np 
import os
import skimage.io as io
import skimage.transform as trans
import numpy as np
from keras.models import *
from keras.layers import *
from keras.optimizers import *
from keras.callbacks import ModelCheckpoint, LearningRateScheduler
from keras import backend as keras


def unet(pretrained_weights = None,input_size = (512,512,1)):
    inputs = Input(input_size)
    conv1 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(inputs)
    conv1 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv1)
    pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)
    conv2 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool1)
    conv2 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv2)
    pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)
    conv3 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool2)
    conv3 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv3)
    pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)
    conv4 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool3)
    conv4 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv4)
    drop4 = Dropout(0.5)(conv4)
    pool4 = MaxPooling2D(pool_size=(2, 2))(drop4)

    conv5 = Conv2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool4)
    conv5 = Conv2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv5)
    drop5 = Dropout(0.5)(conv5)

    up6 = Conv2D(512, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(drop5))
    # merge6 = merge([drop4,up6], mode = 'concat', concat_axis = 3)
    merge6 = concatenate([drop4, up6], axis=3)

    conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge6)
    conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv6)

    up7 = Conv2D(256, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv6))
    # merge7 = merge([conv3,up7], mode = 'concat', concat_axis = 3)
    merge7 = concatenate([conv3, up7], axis=3)

    conv7 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge7)
    conv7 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv7)

    up8 = Conv2D(128, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv7))
    # merge8 = merge([conv2,up8], mode = 'concat', concat_axis = 3)
    merge8 = concatenate([conv2, up8], axis=3)

    conv8 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge8)
    conv8 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv8)

    up9 = Conv2D(64, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv8))
    # merge9 = merge([conv1,up9], mode = 'concat', concat_axis = 3)
    merge9 = concatenate([conv1, up9], axis=3)

    conv9 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge9)
    conv9 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv9)
    conv9 = Conv2D(2, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv9)
    conv10 = Conv2D(1, 1, activation = 'sigmoid')(conv9)#我怀疑这个sigmoid激活函数是多余的，因为在后面的loss中用到的就是二进制交叉熵，包含了sigmoid

    # model = Model(input = inputs, output = conv10)
    model = Model(inputs=inputs, outputs=conv10)

    model.compile(optimizer = Adam(lr = 1e-4), loss = 'binary_crossentropy', metrics = ['accuracy'])#模型执行之前必须要编译
    # 利用二进制交叉熵，也就是sigmoid交叉熵，metrics一般选用准确率，它会使准确率往高处发展
    #model.summary()

    if(pretrained_weights):
    	model.load_weights(pretrained_weights)

    return model

3.main主函数：

from model import *
from data import *

#os.environ["CUDA_VISIBLE_DEVICES"] = "0"


data_gen_args = dict(rotation_range=0.2,
                    width_shift_range=0.05,
                    height_shift_range=0.05,
                    shear_range=0.05,
                    zoom_range=0.05,
                    horizontal_flip=True,
                    fill_mode='nearest')#数据增强时的变换方式的字典
myGene = trainGenerator(2,'/home/lab/lfl/u-net/data/membrane/train','image1','label1',data_gen_args,save_to_dir = None)
#得到一个生成器，以batch=2的速率无限生成增强后的数据
model = unet()
model_checkpoint = ModelCheckpoint('unet_membrane.hdf6', monitor='loss',verbose=1, save_best_only=True)
#回调函数，第一个是保存模型路径，第二个是检测的值，检测Loss是使它最小，第三个是只保存在验证集上性能最好的模型
model.fit_generator(myGene,steps_per_epoch=1000,epochs=3,callbacks=[model_checkpoint])
#steps_per_epoch指的是每个epoch有多少个batch_size，也就是训练集总样本数除以batch_size的值
#上面一行是利用生成器进行batch_size数量的训练，样本和标签通过myGene传入
testGene = testGenerator("/home/lab/lfl/u-net/data/membrane/test1")
results = model.predict_generator(testGene,30,verbose=1)
#30是step,steps: 在停止之前，来自 generator 的总步数 (样本批次)。 可选参数 Sequence：如果未指定，将使用len(generator) 作为步数。
#上面的返回值是：预测值的 Numpy 数组。
saveResult("/home/lab/lfl/u-net/data/membrane/test1",results)#保存结果