python – ValueError：`Concatenate`图层要求输入具有匹配的形状,但concat轴除外

2019年7月28日 347次阅读

我正在尝试为我的项目构建一个Pix2Pix并得到错误：

ValueError：连接层要求输入具有匹配的形状(concat轴除外).得到输入形状：[(无,64,64,128),(无,63,63,128)]

发生器是U-net模型,我的输入高度x宽x通道是256,256,3(X_train)和256,256,1(Y_train).如果错误是由预处理或模型本身引起的,我不是.任何援助将不胜感激.

def build_generator(self):
    """U-Net Generator"""

    def conv2d(layer_input, filters, f_size=3, bn=True):
        """Layers used during downsampling"""
        d = Conv2D(filters, kernel_size=f_size, strides=2, padding='same')(layer_input)
        d = LeakyReLU(alpha=0.2)(d)
        if bn:
            d = BatchNormalization(momentum=0.8)(d)
        return d

    def deconv2d(layer_input, skip_input, filters, f_size=3, dropout_rate=0):
        """Layers used during upsampling"""
        u = UpSampling2D(size=2)(layer_input)
        u = Conv2D(filters, kernel_size=f_size, strides=1, padding='same', activation='relu')(u)
        if dropout_rate:
            u = Dropout(dropout_rate)(u)
        u = BatchNormalization(momentum=0.8)(u)
        u = Concatenate()([u, skip_input])
        return u

    # Image input
    d0 = Input(shape=self.img_shape)

    # Downsampling
    d1 = conv2d(d0, self.gf, bn=False)
    d2 = conv2d(d1, self.gf*2)
    d3 = conv2d(d2, self.gf*4)
    d4 = conv2d(d3, self.gf*8)
    d5 = conv2d(d4, self.gf*8)
    d6 = conv2d(d5, self.gf*8)
    d7 = conv2d(d6, self.gf*8)

    # Upsampling
    u1 = deconv2d(d7, d6, self.gf*8)
    u2 = deconv2d(u1, d5, self.gf*8)
    u3 = deconv2d(u2, d4, self.gf*8)
    u4 = deconv2d(u3, d3, self.gf*4)
    u5 = deconv2d(u4, d2, self.gf*2)
    u6 = deconv2d(u5, d1, self.gf)

    u7 = UpSampling2D(size=2)(u6)
    output_img = Conv2D(self.channels, kernel_size=3, strides=1, padding='same', activation='tanh')(u7)

    return Model(d0, output_img)

跟踪错误如下：

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-58-1a469bc54cde> in <module>()
----> 1 gan = Pix2Pix()
      2 gan.train(epochs=30000, batch_size=1, save_interval=200)

<ipython-input-57-f9ff9b0e4228> in __init__(self)
     48 
     49         # Build and compile the generator
---> 50         self.generator = self.build_generator()
     51         self.generator.compile(loss='binary_crossentropy', optimizer=optimizer)
     52 

<ipython-input-57-f9ff9b0e4228> in build_generator(self)
    107         u3 = deconv2d(u2, d4, self.gf*8)
    108         u4 = deconv2d(u3, d3, self.gf*4)
--> 109         u5 = deconv2d(u4, d2, self.gf*2)
    110         u6 = deconv2d(u5, d1, self.gf)
    111 

<ipython-input-57-f9ff9b0e4228> in deconv2d(layer_input, skip_input, filters, f_size, dropout_rate)
     87                 u = Dropout(dropout_rate)(u)
     88             u = BatchNormalization(momentum=0.8)(u)
---> 89             u = Concatenate()([u, skip_input])
     90             return u
     91 

/usr/local/lib/python3.5/site-packages/keras/engine/topology.py in __call__(self, inputs, **kwargs)
    569                     self.build(input_shapes[0])
    570                 else:
--> 571                     self.build(input_shapes)
    572                 self.built = True
    573 

/usr/local/lib/python3.5/site-packages/keras/layers/merge.py in build(self, input_shape)
    275                              'inputs with matching shapes '
    276                              'except for the concat axis. '
--> 277                              'Got inputs shapes: %s' % (input_shape))
    278 
    279     def call(self, inputs):

ValueError: `Concatenate` layer requires inputs with matching shapes except for the concat axis. Got inputs shapes: [(None, 64, 64, 128), (None, 63, 63, 128)]

最佳答案 尝试定义图像数据格式

from keras import backend as K
K.set_image_data_format('channels_first')

我认为这应该可以解决您的问题.

点赞