Keras 虽然训练图像分割网络的UNET-验证损失在经过一段时间后并没有得到减少，但保持不变
我正在figshare的脑瘤数据集上训练UNET图像分割网络，它训练得很好，训练丢失和训练骰子分数都在相应地改变，或者与验证丢失和验证骰子分数的音调相同。表示没有过度安装的问题。但在大约40个时代之后绩效指标没有改善。它在损失0.58和骰子得分0.47之间切换如何解决这个问题？请推荐我。 下面是我的UNET网络-Keras 虽然训练图像分割网络的UNET-验证损失在经过一段时间后并没有得到减少，但保持不变,keras,image-segmentation,loss,unity3d-unet,Keras,Image Segmentation,Loss,Unity3d Unet,我正在figshare的脑瘤数据集上训练UNET图像分割网络，它训练得很好，训练丢失和训练骰子分数都在相应地改变，或者与验证丢失和验证骰子分数的音调相同。表示没有过度安装的问题。但在大约40个时代之后绩效指标没有改善。它在损失0.58和骰子得分0.47之间切换如何解决这个问题？请推荐我。 下面是我的UNET网络- def unet(pretrained_weights = None,input_size = (512,512,3)): inputs = Input(input_size)
def unet(pretrained_weights = None,input_size = (512,512,3)):
inputs = Input(input_size)
conv1 = Convolution2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(inputs)
conv1 = BatchNormalization()(conv1)
#conv1 = Dropout(0.2)(conv1)
conv1 = Convolution2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv1)
conv1 = BatchNormalization()(conv1)
#conv1 = Dropout(0.2)(conv1)
pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)
conv2 = Convolution2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool1)
conv2 = BatchNormalization()(conv2)
#conv2 = Dropout(0.1)(conv2)
conv2 = Convolution2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv2)
conv2 = BatchNormalization()(conv2)
#conv2 = Dropout(0.1)(conv2)
pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)
conv3 = Convolution2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool2)
conv3 = BatchNormalization()(conv3)
#conv3 = Dropout(0.1)(conv3)
conv3 = Convolution2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv3)
conv3 = BatchNormalization()(conv3)
#conv3 = Dropout(0.1)(conv3)
pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)
conv4 = Convolution2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool3)
conv4 = BatchNormalization()(conv4)
#conv4 = Dropout(0.1)(conv4)
conv4 = Convolution2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv4)
conv4 = BatchNormalization()(conv4)
#conv4 = Dropout(0.5)(conv4)
pool4 = MaxPooling2D(pool_size=(2, 2))(conv4)
conv5 = Convolution2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool4)
conv5 = BatchNormalization()(conv5)
#conv5 = Dropout(0.1)(conv5)
conv5 = Convolution2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv5)
conv5 = BatchNormalization()(conv5)
#conv5 = Dropout(0.5)(conv5)
up6 = Convolution2D(512, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv5))
merge6 = concatenate([conv4,up6], axis = 3)
conv6 = Convolution2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge6)
conv6 = BatchNormalization()(conv6)
#conv6 = Dropout(0.1)(conv6)
conv6 = Convolution2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv6)
conv6 = BatchNormalization()(conv6)
#conv6 = Dropout(0.1)(conv6)
up7 = Convolution2D(256, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv6))
merge7 = concatenate([conv3,up7], axis = 3)
conv7 = Convolution2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge7)
conv7 = BatchNormalization()(conv7)
#conv7 = Dropout(0.1)(conv7)
conv7 = Convolution2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv7)
conv7 = BatchNormalization()(conv7)
#conv7 = Dropout(0.1)(conv7)
up8 = Convolution2D(128, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv7))
merge8 = concatenate([conv2,up8], axis = 3)
conv8 = Convolution2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge8)
conv8 = BatchNormalization()(conv8)
#conv8 = Dropout(0.1)(conv8)
conv8 = Convolution2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv8)
conv8 = BatchNormalization()(conv8)
#conv8 = Dropout(0.1)(conv8)
up9 = Convolution2D(64, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv8))
merge9 = concatenate([conv1,up9], axis = 3)
conv9 = Convolution2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge9)
conv9 = BatchNormalization()(conv9)
#conv9 = Dropout(0.2)(conv9)
conv9 = Convolution2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv9)
conv9 = BatchNormalization()(conv9)
#conv9 = Dropout(0.2)(conv9)
conv9 = Convolution2D(2, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv9)
conv9 = BatchNormalization()(conv9)
#conv9 = Dropout(0.2)(conv9)
conv10 = Convolution2D(1, 1, activation = 'sigmoid')(conv9)
model = Model(input = inputs, output = conv10)
#model.summary()
if(pretrained_weights):
model.load_weights(pretrained_weights)
return model
callbacks = [EarlyStopping(monitor='val_loss',mode="min", patience=30,verbose=1,min_delta=1e-4),
ReduceLROnPlateau(monitor='val_loss',mode="min", factor=0.1,patience=8,verbose=1),
ModelCheckpoint(monitor='val_loss',mode="min",
filepath='weights/anmol/1/UNET_sigmoid_focus_DC_2605_R_B_t-{epoch:03d}-{dice_coef:.6f}--{val_loss:.6f}.hdf5',save_weights_only=True, verbose=1),
CSVLogger('weights/anmol/1/UNET_mixed_loss_monitor_DC_new.csv')]
def dice_coef(y_true, y_pred, smooth=1):
y_true_f = K.flatten(y_true)
y_pred_f = K.flatten(y_pred)
intersection = K.sum(y_true_f * y_pred_f)
return (2. * intersection + smooth) / (K.sum(y_true_f) + K.sum(y_pred_f) + smooth)
def dice_loss(y_true, y_pred):
loss = 1 - dice_coef(y_true, y_pred)
return loss
def dice_coef_loss(y_true, y_pred):
return binary_crossentropy(y_true, y_pred) + dice_loss(y_true, y_pred)
img_size = 512
image_args = dict(seed=seed,
batch_size=2,
shuffle=True,
class_mode=None,
target_size=(img_size, img_size),
color_mode='rgb')
mask_args = dict(seed=seed,
batch_size=2,
class_mode=None,
shuffle=True,
target_size=(img_size, img_size),
color_mode='grayscale')
DIR = 'raw/brain/'
image = 'images'
masks = 'masks'
# combine generators into one which yields image and masks
train_generator = zip(image_datagen.flow_from_directory(**image_args, directory=DIR+'train_'+image),
mask_datagen.flow_from_directory(**mask_args, directory=DIR+'train_'+masks))
validation_generator = zip(image_datagen.flow_from_directory(**image_args, directory=DIR+'validation_'+image),
mask_datagen.flow_from_directory(**mask_args, directory=DIR+'validation_'+masks))
model.fit_generator(train_generator, steps_per_epoch=1302, epochs=100, validation_data=validation_generator,validation_steps=153, callbacks=callbacks)