Question

我想使用VGG 16模型作为我的编码器来构建U-net架构，并在Imagenet数据集上预先训练权重。对于上采样，我想将编码器中某些层的输出与解码部分连接在一起。几乎像这样（摘自TernausNet）： TernausNet

到目前为止，我的模型如下：

from keras.applications.vgg16 import VGG16 as VGG16, preprocess_input
encode_model = VGG16(input_shape=(768,768,3), include_top=False, weights='imagenet')
encode_model.trainable = False

from keras import models, layers

input_img = layers.Input((768,768,3), name = 'RGB_Input')

# output and start upsampling
features = encode_model(input_img)
conv_1 = layers.Conv2D(512, (3,3), activation='relu', padding='same')(features)
up_conv = layers.Conv2DTranspose(256, (3,3), strides=(2,2), activation='relu', padding='same')(conv_1)

# first concatenation block
concat_1 = layers.concatenate([encode_model.get_layer('block5_conv3').output, up_conv], axis=-1, name='concat_1')
conv_2 = layers.Conv2D(512, (3,3), activation='relu', padding='same')(concat_1)
up_conv_2 = layers.Conv2DTranspose(256, (3,3), strides=(2,2), activation='relu', padding='same')(conv_2)


# second concatenation block
concat_2 = layers.concatenate([up_conv_2, encode_model.get_layer('block4_conv3').output])
conv_3 = layers.Conv2D(512, (3,3), activation='relu', padding='same')(concat_2)
up_conv_3 = layers.Conv2DTranspose(128, (3,3), strides=(2,2), activation='relu', padding='same')(conv_3)

# third concatenation block
concat_3 = layers.concatenate([up_conv_3, encode_model.get_layer('block3_conv3').output])
conv_4 = layers.Conv2D(256, (3,3), activation='relu', padding='same')(concat_3)
up_conv_4 = layers.Conv2DTranspose(64, (3,3), strides=(2,2), activation='relu', padding='same')(conv_4)

# fourth concatenation block
concat_4 = layers.concatenate([up_conv_4, encode_model.get_layer('block2_conv2').output])
conv_5 = layers.Conv2D(128, (3,3), activation='relu', padding='same')(concat_4)
up_conv_5 = layers.Conv2DTranspose(32, (3,3), strides=(2,2), activation='relu', padding='same')(conv_5)

# fifth concatenation block
concat_4 = layers.concatenate([up_conv_5, encode_model.get_layer('block1_conv2').output])
conv_6 = layers.Conv2D(128, (3,3), activation='sigmoid', padding='same')(concat_4)

final_model = models.Model(inputs=[input_img], outputs=[conv_6])
final_model.summary()

稍后我编译并拟合模型：

import keras.backend as K
from keras.optimizers import Adam
from keras.losses import binary_crossentropy  

def dice_coef(y_true, y_pred, smooth=1):
    intersection = K.sum(y_true * y_pred, axis=[1,2,3])
    union = K.sum(y_true, axis=[1,2,3]) + K.sum(y_pred, axis=[1,2,3])
    return K.mean( (2. * intersection + smooth) / (union + smooth), 
    axis=0)

def dice_p_bce(in_gt, in_pred):
    return 1e-3*binary_crossentropy(in_gt, in_pred) - dice_coef(in_gt, 
    in_pred)

def true_positive_rate(y_true, y_pred):
    return K.sum(K.flatten(y_true)*K.flatten(K.round(y_pred)))/K.sum(y_true)   

final_model.compile(optimizer=Adam(1e-3, decay=1e-6), loss=dice_p_bce, 
    metrics=[dice_coef, 'binary_accuracy', true_positive_rate])

step_count = min(MAX_TRAIN_STEPS, balanced_train_df.shape[0]//BATCH_SIZE)
aug_gen = create_aug_gen(make_image_gen(balanced_train_df))
loss_history = [final_model.fit_generator(aug_gen, 
                         steps_per_epoch=step_count, 
                         epochs=NB_EPOCHS, 
                         validation_data=(valid_x, valid_y),
                         callbacks=callbacks_list,
                        workers=1)]`

然后我得到以下错误：

Graph disconnected: cannot obtain value for tensor Tensor("input_4:0", shape=(?, 768, 768, 3), dtype=float32) at layer "input_4". The following previous layers were accessed without issue: []

我读到，当输入和输出不属于同一图形时，会发生这种情况。我认为与此相关的是两个图形：

input_img = layers.Input((768,768,3), name = 'RGB_Input')

# output and start upsampling
features = encode_model(input_img)
conv_1 = layers.Conv2D(512, (3,3), activation='relu', padding='same')(features)

我怎么了？

Answer 1

我更新了答案，使其与编辑后的问题相对应

我认为问题出在这一行：

features = encode_model(input_img)

encode_model是一个keras模型，您尝试将自定义输入层传递给它。当然这不是必需的。请尝试以下操作：

# necessary imports
encode_model = VGG16(input_shape=(768,768,3), include_top=False, weights='imagenet')
conv_1 = layers.Conv2D(512, (3,3), activation='relu', padding='same')(encode_model.output)  # need to pass the output tensor to the conv_1 layer
# define the rest of your model as you have it

Answer 2

由于VGG16中已经存在输入层，因此在这种情况下无需定义新的输入层。只需使用现有的一个即可：

decode_features = decode_model.output

# ...

final_model = models.Model(inputs=[decode_model.input], outputs=[conv_6])

更新：如果要防止修改VGG16的权重，请使用trainable参数明确冻结其所有层：

for layer in decode_model.layers:
    layer.trainable = False

只需确保在编译最终模型之前执行此操作即可。

具有VGG 16作为特征提取器的类似U-net的体系结构-串联层的问题

2 个答案: