Question

我正在训练UNET，从一开始我的准确性和val_accuracy很高。我怀疑我在文件夹中弄错了

。

可能是什么原因？

分割文件夹的方式对我来说不正确，但是如果我没有创建具有相同名称的文件夹（例如，图像文件夹中的图像），则找不到图像

这是我的代码：

def unet(input_size):
    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 

seed = 100

width=512



def my_image_mask_generator(image_data_generator, mask_data_generator):
    train_generator = zip(image_data_generator, mask_data_generator)
    for (img, mask) in train_generator:
        yield (img, mask)



################################################################################### Image Datagenerator

train_datagen = ImageDataGenerator(
        rescale=1./255,
        shear_range=0.2,
        zoom_range=0.2,
        horizontal_flip=True)


################################ train

image_train_generator = train_datagen.flow_from_directory('/content/drive/My Drive/Datasets/Indian DR_flow_from_dir/Training/images',target_size=(512,512),class_mode=None,batch_size=1,seed=seed)

mask_train_generator = train_datagen.flow_from_directory(
    '/content/drive/My Drive/Datasets/Indian DR_flow_from_dir/Training/masks',
    target_size=(512,512),color_mode='grayscale',class_mode=None,batch_size=1,
    seed=seed)

train_generator = my_image_mask_generator(image_train_generator, mask_train_generator)

################# test

test_datagen = ImageDataGenerator(rescale=1./255)

image_test_generator = test_datagen.flow_from_directory('/content/drive/My Drive/Datasets/Indian DR_flow_from_dir/Testing/images ',target_size=(512,512),class_mode=None,batch_size=1,seed=seed)

mask_test_generator =test_datagen.flow_from_directory(
    '/content/drive/My Drive/Datasets/Indian DR_flow_from_dir/Testing/masks',
    target_size=(512,512),color_mode='grayscale',class_mode=None,batch_size=1,
    seed=seed)

test_generator = my_image_mask_generator(image_test_generator, mask_test_generator)


################################################################################ MODEL TRAINING
model=unet((width,width,3))

print("There are :",len(model.layers),"layers in model!!")
from keras import optimizers
adam=optimizers.Adam(lr=0.0001, beta_1=0.9, beta_2=0.999, amsgrad=False)

model.compile(loss='binary_crossentropy',optimizer=adam,metrics=['accuracy'])



earlystopper = EarlyStopping(patience=10, verbose=1)
checkpointer = ModelCheckpoint('unet.{epoch:02d}-{val_loss:.2f}.h5',monitor='accuracy', verbose=1, save_best_only=True)
history=model.fit_generator(train_generator,
                         steps_per_epoch  = 250,
                         nb_epoch = 100,callbacks=[earlystopper,checkpointer],
                         validation_data = test_generator,
                         nb_val_samples = 250)


path_dir='/content/drive/My Drive/Datasets/Indian DR'
os.chdir(path_dir)
os.mkdir(os.path.join(path_dir,'Folder with Unet Results'))
os.chdir(os.path.join(path_dir,'Folder with Unet Results'))

model.save('Custom_Unet.h5')



# summarize history for accuracy
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('model accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()
plt.savefig('Custom_Unet_acc.png')
# summarize history for loss
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()
plt.savefig('Custom_Unet_loss.png')

高精度和val_accuracy

0 个答案: