机器学习笔记 - TensorFlow2.0全卷积网络FCN语义分割

主要参考

https://blog.csdn.net/yx123919804/article/details/104811087

训练及数据等代码参考

https://blog.csdn.net/bashendixie5/article/details/115795171

代码及数据集下载

链接：https://pan.baidu.com/s/17s2uCQJ7OOB0ekmOjL3xEA 
提取码：d9eq

原图和预测效果如下，之后在自定义的数据集上测试，效果也不错

 model.py - 模型代码

from keras.layers import *
from keras.optimizers import *
from keras.models import *


project_name = "fcn_segment"

channels = 1
std_shape = (256, 256, channels) # 输入尺寸, std_shape[0]: img_rows, std_shape[1]: img_cols
                                  # 这个尺寸按你的图像来, 如果你的图大小不一, 那 img_rows 和 image_cols
                                  # 都要设置成 None, 如果你在用 Generator 加载数据时有扩展边缘, 那 std_shape
                                  # 就是扩展后的尺寸

img_input = Input(shape = std_shape, name = "input")

conv_1 = Conv2D(32, kernel_size = (3, 3), activation = "relu", padding = "same", name = "conv_1")(img_input)
max_pool_1 = MaxPool2D(pool_size = (2, 2), strides = (2, 2), name = "max_pool_1")(conv_1)

conv_2 = Conv2D(64, kernel_size = (3, 3), activation = "relu", padding = "same", name = "conv_2")(max_pool_1)
max_pool_2 = MaxPool2D(pool_size = (2, 2), strides = (2, 2), name = "max_pool_2")(conv_2)

conv_3 = Conv2D(128, kernel_size = (3, 3), activation = "relu", padding = "same", name = "conv_3")(max_pool_2)
max_pool_3 = MaxPool2D(pool_size = (2, 2), strides = (2, 2), name = "max_pool_3")(conv_3)

conv_4 = Conv2D(256, kernel_size = (3, 3), activation = "relu", padding = "same", name = "conv_4")(max_pool_3)
max_pool_4 = MaxPool2D(pool_size = (2, 2), strides = (2, 2), name = "max_pool_4")(conv_4)

conv_5 = Conv2D(512, kernel_size = (3, 3), activation = "relu", padding = "same", name = "conv_5")(max_pool_4)
max_pool_5 = MaxPool2D(pool_size = (2, 2), strides = (2, 2), name = "max_pool_5")(conv_5)

# max_pool_5 转置卷积上采样 2 倍和 max_pool_4 一样大
up6 = Conv2DTranspose(256, kernel_size = (3, 3), strides = (2, 2), padding = "same", kernel_initializer = "he_normal",
                                   name = "upsamping_6")(max_pool_5)
                
_16s = add([max_pool_4, up6])

# _16s 转置卷积上采样 2 倍和 max_pool_3 一样大
up_16s = Conv2DTranspose(128, kernel_size = (3, 3), strides = (2, 2), padding = "same", kernel_initializer = "he_normal",
                                      name = "Conv2DTranspose_16s")(_16s)
                                 
_8s = add([max_pool_3, up_16s])

# _8s 上采样 8 倍后与输入尺寸相同
up7 = UpSampling2D(size = (8, 8), interpolation = "bilinear", name = "upsamping_7")(_8s)

# 这里 kernel 也是 3 * 3, 也可以同 FCN-32s 那样修改的
conv_7 = Conv2D(1, kernel_size = (3, 3), activation = "sigmoid", padding = "same", name = "conv_7")(up7)

model = Model(img_input, conv_7, name = project_name)

model.compile(optimizer=Adam(lr=1e-4), loss = "binary_crossentropy", metrics = ["accuracy"])

model.summary()

data.py - 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):
        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)



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=(256,256), 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,
        classes=[image_folder],
        class_mode=None,
        color_mode=image_color_mode,
        target_size=target_size,
        batch_size=batch_size,
        save_to_dir=save_to_dir,
        save_prefix=image_save_prefix,
        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:
        img, mask = adjustData(img, mask, flag_multi_class, num_class)
        yield (img, mask)



def testGenerator(test_path, num_image = 30, target_size = (256,256),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)
        yield img


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))
    image_arr = []
    mask_arr = []
    for index, item in enumerate(image_name_arr):
        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)
        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)
    return image_arr, mask_arr


def labelVisualize(num_class, color_dict, img):
    img = img[:, :, 0] if len(img.shape) == 3 else img
    img_out = np.zeros(img.shape + (3,))
    for i in range(num_class):
        img_out[img == i, :] = color_dict[i]
    return img_out / 255



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]
        io.imsave(os.path.join(save_path, "%d_predict.png"%i), img)

main.py - 训练

from model import *
from data import *

import os
os.environ['TF_FORCE_GPU_ALLOW_GROWTH'] = "true"
#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')
myGene = trainGenerator(2,'data/membrane/train','image','label',data_gen_args,save_to_dir = None)

model = unet()
model_checkpoint = ModelCheckpoint('unet_membrane.hdf5', monitor='loss', verbose=1, save_best_only=True)
model.fit_generator(myGene, steps_per_epoch=2000, epochs=5, callbacks=[model_checkpoint])

test.py - 测试

from model import *
from data import *
import matplotlib
import os
from keras.models import load_model
import numpy as np
from PIL import Image
import cv2
import tensorflow as tf
import tensorflow_hub as hub
from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2

def test():
    model = load_model("unet_membrane.hdf5")
    testGene = testGenerator("data/membrane/test", 5)
    results = model.predict_generator(testGene, 5, verbose=1)
    saveResult("data/membrane/result", results)

test()