代码之家 › 专栏 › 技术社区 › Karim Mohamed Hasebou

keras'NoneType'对象没有属性'u inbound'u nodes'

conv-neural-network deep-learning keras machine-learning python

Karim Mohamed Hasebou · 技术社区 · 6 年前

我正试图写一个鉴别器,评估一个图像的补丁。

我使用时间分布层的原因是,在最后,鉴别器应该判断整个图像是真是假。因此,我尝试分别对每个补丁执行前向传递,然后通过lambda层平均每个补丁的鉴别器输出:

def my_average(x):
    x = K.mean(x, axis=1)
    return x

def my_average_shape(input_shape):
    shape = list(input_shape)
    del shape[1]
    return tuple(shape)


def defineD(input_shape):
    a = Input(shape=(256, 256, 1))

    cropping_list = []

    n_patches = 256/32
    for x in range(256/32):
        for y in  range(256/32):

            cropping_list += [
             K.expand_dims(
                Cropping2D((( x * 32,  256 - (x+1) * 32), ( y * 32,  256 - (y+1) * 32)))(a)
                , axis=1)
            ]

    x = Concatenate(1)(cropping_list)

    x = TimeDistributed(Conv2D(4 * 8, 3, padding='same'))(x) # 
    x = TimeDistributed(MaxPooling2D())(x)
    x = TimeDistributed(LeakyReLU())(x)                  # 16

    x = TimeDistributed(Conv2D(4 * 16, 3, padding='same'))(x)
    x = TimeDistributed(MaxPooling2D())(x)
    x = TimeDistributed(LeakyReLU())(x)                  # 8

    x = TimeDistributed(Conv2D(4 * 32, 3, padding='same'))(x)
    x = TimeDistributed(MaxPooling2D())(x)
    x = TimeDistributed(LeakyReLU())(x)                  # 4


    x = TimeDistributed(Flatten())(x)
    x = TimeDistributed(Dense(2, activation='sigmoid'))(x)
    x = Lambda(my_average, my_average_shape)(x)

    return keras.models.Model(inputs=a, outputs=x)

出于某种原因,我得到以下错误:

File "testing.py", line 41, in <module>
    defineD((256,256,1) )
  File "testing.py", line 38, in defineD
    return keras.models.Model(inputs=a, outputs=x)
  File "/usr/local/lib/python2.7/dist-packages/keras/legacy/interfaces.py", line 91, in wrapper
    return func(*args, **kwargs)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/network.py", line 93, in __init__
    self._init_graph_network(*args, **kwargs)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/network.py", line 237, in _init_graph_network
    self.inputs, self.outputs)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/network.py", line 1353, in _map_graph_network
    tensor_index=tensor_index)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/network.py", line 1340, in build_map
    node_index, tensor_index)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/network.py", line 1340, in build_map
    node_index, tensor_index)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/network.py", line 1340, in build_map
    node_index, tensor_index)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/network.py", line 1340, in build_map
    node_index, tensor_index)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/network.py", line 1340, in build_map
    node_index, tensor_index)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/network.py", line 1340, in build_map
    node_index, tensor_index)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/network.py", line 1340, in build_map
    node_index, tensor_index)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/network.py", line 1340, in build_map
    node_index, tensor_index)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/network.py", line 1340, in build_map
    node_index, tensor_index)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/network.py", line 1340, in build_map
    node_index, tensor_index)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/network.py", line 1340, in build_map
    node_index, tensor_index)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/network.py", line 1340, in build_map
    node_index, tensor_index)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/network.py", line 1312, in build_map
    node = layer._inbound_nodes[node_index]
AttributeError: 'NoneType' object has no attribute '_inbound_nodes'

2 回复 | 直到 6 年前

today 6 年前

您需要将裁剪操作放在函数中,然后在 Lambda

def my_cropping(a):
    cropping_list = []
    n_patches = 256/32
    for x in range(256//32):
        for y in  range(256//32):

            cropping_list += [
             K.expand_dims(
                Cropping2D((( x * 32,  256 - (x+1) * 32), ( y * 32,  256 - (y+1) * 32)))(a)
                , axis=1)
            ]
    return cropping_list

使用它:

cropping_list = Lambda(my_cropping)(a)

Julian 6 年前

我遇到了同样的问题,它确实通过在张量周围包裹一层Lambda层来解决,正如@today建议的那样。

我想把一个向量和一个正方形的图像连接起来,然后把这个向量转换成一个对角矩阵。它使用了以下代码片段:

def diagonalize(vector):
  diagonalized = tf.matrix_diag(vector) # make diagonal matrix from vector
  out_singlechan = tf.expand_dims(diagonalized, -1) # append 1 channel to get compatible to the multichannel image dim
  return out_singlechan

lstm_out = Lambda(diagonalize, output_shape=(self.img_shape[0],self.img_shape[1],1))(lstm_out)