keras 中的本地连接一维自动编码器

Question

我正在尝试通过重新利用 this tutorial 中的 'simplest possible' 密集自动编码器，在 Keras 中创建一个 LocallyConnected1D 自动编码器。

我不断收到以下错误消息，我认为这是由 input_shape.

的尺寸引起的

Traceback (most recent call last):
File "localdendritic.py", line 38, in <module>
kernel_size=6)
File "localdendritic.py", line 15, in __init__
activation='relu')(input_placeholder)
File "/Users/me/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py", line 573, in __call__
self.assert_input_compatibility(inputs)
File "/Users/me/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py", line 472, in assert_input_compatibility
str(K.ndim(x)))
ValueError: Input 0 is incompatible with layer encoded_layer: expected ndim=3, found ndim=2

我的代码如下。我已经尝试将 input_shape 数组更改为 [None, 1, input_size]、[1, 1, input_size]、[1, input_size] 和 [None, input_size]，但它似乎没有任何改变。我想我缺少一些关于输入形状的见解。

import numpy as np
from keras.models import Model, Sequential
from keras.layers import Input, LocallyConnected1D


class Localautoencoder:

  def __init__(self, input_size, encoded_size, kernel_size, **kwargs):

    input_shape = np.array([input_size])
    input_placeholder = Input(shape=(input_size, 1))
    encoded = LocallyConnected1D(encoded_size, kernel_size,
                                 input_shape=input_shape,
                                 name='encoded_layer',
                                 activation='relu')(input_placeholder)
    decoded = LocallyConnected1D(input_size, kernel_size,
                                activation='sigmoid',
                                name='decoded_layer')(encoded)
    self.localae = Model(input_placeholder, decoded)
    self.encoder = Model(input_placeholder, encoded)
    encoded_input = Input(shape=(1, encoded_size))
    decoded_layer = self.localae.layers[-1]
    self.decoder = Model(encoded_input, decoded_layer(encoded_input))
    self.localae.compile(optimizer='adam', loss='binary_crossentropy')


from keras.datasets import mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.astype('float32')/255.
x_test = x_test.astype('float32')/255.
x_train = x_train.reshape((len(x_train), np.prod(x_train.shape[1:])))
x_test = x_test.reshape((len(x_test), np.prod(x_test.shape[1:])))
print(x_train.shape)
print(x_test.shape)

lae = Localautoencoder(input_size=x_train.shape[1],
                   encoded_size=100,
                   kernel_size=6)

Answer 1

一个LocallyConnected1D层接受一个three-dimensional输入，但是input_placeholder只有两个维度。解决此问题的方法是添加一个 Reshape 层，将您的 2D 输入转换为 3D 输入。

keras 中的本地连接一维自动编码器

locallyconnected1D autoencoder in keras

python

autoencoder

keras