Keras中语义分割的不平衡数据？

Question

我是keras的新手，现在已经学习了大约3个星期。如果我的问题听起来有点愚蠢，我道歉。

我目前正在进行512x512的语义医学图像分割。我正在使用这个链接https://github.com/zhixuhao/unet的UNet。基本上，我想从图像中分割大脑（所以两级分割，背景与前景）

我对网络做了一些修改，我得到了一些我很满意的结果。但我认为我可以通过对前景施加更多权重来改善分割结果，因为大脑的像素数远小于背景像素的数量。在某些情况下，大脑不会出现在图像中，尤其是位于底部切片中的大脑。

我不知道我需要在https://github.com/zhixuhao/unet中修改哪部分代码

如果有人能帮助我，我真的很感激。非常感谢提前！

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=(256, 256, 1)):
  inputs = Input(input_size)
  conv1 = Conv2D(64, 3, activation='relu', padding='same', kernel_initializer='he_normal')(inputs)
  conv1 = BatchNormalization()(conv1)
  conv1 = Conv2D(64, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv1)
  conv1 = BatchNormalization()(conv1)
  pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)

  conv2 = Conv2D(128, 3, activation='relu', padding='same', kernel_initializer='he_normal')(pool1)
  conv2 = BatchNormalization()(conv2)
  conv2 = Conv2D(128, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv2)
  conv2 = BatchNormalization()(conv2)
  pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)

  conv3 = Conv2D(256, 3, activation='relu', padding='same', kernel_initializer='he_normal')(pool2)
  conv3 = BatchNormalization()(conv3)
  conv3 = Conv2D(256, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv3)
  conv3 = BatchNormalization()(conv3)
  pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)

  conv4 = Conv2D(512, 3, activation='relu', padding='same', kernel_initializer='he_normal')(pool3)
  conv4 = BatchNormalization()(conv4)
  conv4 = Conv2D(512, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv4)
  conv4 = BatchNormalization()(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 = BatchNormalization()(conv5)
  conv5 = Conv2D(1024, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv5)
  conv5 = BatchNormalization()(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 = BatchNormalization()(conv6)
  conv6 = Conv2D(512, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv6)
  conv6 = BatchNormalization()(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 = BatchNormalization()(conv7)
  conv7 = Conv2D(256, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv7)
  conv7 = BatchNormalization()(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 = BatchNormalization()(conv8)
  conv8 = Conv2D(128, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv8)
  conv8 = BatchNormalization()(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 = BatchNormalization()(conv9)
  conv9 = Conv2D(64, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv9)
  conv9 = BatchNormalization()(conv9)
  conv9 = Conv2D(2, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv9)
  conv9 = BatchNormalization()(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()

  if (pretrained_weights):
      model.load_weights(pretrained_weights)

  return model

这是main.py

from model2 import *
from data2 import *
from keras.models import load_model

class_weight= {0:0.10, 1:0.90}
myGene = trainGenerator(2,'data/brainTIF/trainNew','image','label',save_to_dir = None)
model = unet()
model_checkpoint = ModelCheckpoint('unet_brainTest_e10_s5.hdf5', 
monitor='loss')
model.fit_generator(myGene,steps_per_epoch=5,epochs=10,callbacks = [model_checkpoint])

testGene = testGenerator("data/brainTIF/test3")
results = model.predict_generator(testGene,18,verbose=1)
saveResult("data/brainTIF/test_results3",results)

Answer 1

作为class_weight用于二进制类的选项，您还可以使用合成过采样技术（SMOTE）处理不平衡类，从而增加少数组的大小：

from imblearn.over_sampling import SMOTE

sm = SMOTE()
x, y = sm.fit_sample(X_train, Y_train)