[Keras] Learn API by UNet

热身

一、实践学习

Ref: https://arxiv.org/pdf/1505.04597.pdf

Fig. 1. U-net architecture (example for 32x32 pixels in the lowest resolution). Each blue box corresponds to a multi-channel feature map. The number of channels is denoted on top of the box. The x-y-size is provided at the lower left edge of the box. White boxes represent copied feature maps. The arrows denote the different operations.

 

import numpy as np
import os
from os.path import exists, join
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 = (256,256,1)):

    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 = 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 = 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 = 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 = 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)

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

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

    #model.summary()
return model

 

Ref: unet网络结构说明及keras实现详解

网络结构说明

unet网络可以简单看为先下采样，经过不同程度的卷积，学习了深层次的特征，在经过上采样回复为原图大小，上采样用反卷积实现。最后输出类别数量的特征图，如分割是两类（是或不是），典型unet也是输出两张图，最后要说明一下，原网络到此就结束了，其实在最后还要使用激活函数softmax将这两个类别转换为概率图，针对某个像素点，如输出是[0.1，0.9]，则判定这个像素点是第二类的概率更大。
网络结构可以看成3个部分：

• 下采样：网络的红色箭头部分，池化实现
• 上采样：网络的绿色箭头部分，反卷积实现
• 最后层的softmax：在网络结构中，最后输出两张fiture maps后，其实在最后还要做一次softmax，将其转换为概率图。

 

概念理解

Ref: 反卷积（deconvolution）的理解 +上采样(UNSampling)与上池化(UnPooling)

Ref: 上采样、以及反卷积&空洞卷积区别

 

二、学习

Are you an engineer or data scientist? Do you ship real-world machine learning solutions?
Check out our Introduction to Keras for engineers.

Are you a machine learning researcher? Do you publish at NeurIPS and push the state-of-the-art in CV and NLP?
Check out our Introduction to Keras for researchers.

 

 

关键概念 & 相关文档

一、For researchers

In this guide, you will learn about:

• • Tensors, variables, and gradients in TensorFlow
    • tensor不变性，保存计算后的状态
  • Creating layers by subclassing the Layer class
  • Writing low-level training loops
  • Tracking losses created by layers via the add_loss() method
  • Tracking metrics in a low-level training loop
  • Speeding up execution with a compiled tf.function
  • Executing layers in training or inference mode
  • The Keras Functional API

 

二、层 Layer

 

Ref: https://keras-cn.readthedocs.io/en/latest/layers/writting_layer/

 

End.