keras：ValueError：检查模型目标时出错：预期activation_1具有形状（无，60），但数组的形状为（10，100）

Question

我正在尝试将RocAlphaGo移植到“亚马逊游戏”中，并且在尝试实施监督策略培训师时会遇到问题。

from keras.models import Sequential, Model
from keras.layers.core import Activation, Flatten
from keras.layers import convolutional

defaults = {
            "board": 10,
            "filters_per_layer": 128,
            "layers": 12,
            "filter_width_1": 5
}
# copy defaults, but override with anything in kwargs
params = defaults
network = Sequential()
# create first layer
network.add(convolutional.Convolution2D(
      input_shape=(6, 10, 10),
      nb_filter=128,
      nb_row=5,
      nb_col=5,
      init='uniform',
      activation='relu',
      border_mode='same'))

# create all other layers
for i in range(2, 13):
     # use filter_width_K if it is there, otherwise use 3
     filter_key = "filter_width_%d" % i
     filter_width = params.get(filter_key, 3)

     # use filters_per_layer_K if it is there, otherwise use default value
     filter_count_key = "filters_per_layer_%d" % i
     filter_nb = params.get(filter_count_key, 128)

     network.add(convolutional.Convolution2D(
         nb_filter=filter_nb,
         nb_row=filter_width,
         nb_col=filter_width,
         init='uniform',
         activation='relu',
         border_mode='same'))

# the last layer maps each <filters_per_layer> feature to a number
network.add(convolutional.Convolution2D(
    nb_filter=1,
    nb_row=1,
    nb_col=1,
    init='uniform',
    border_mode='same'))
# reshape output to be board x board
network.add(Flatten())
# softmax makes it into a probability distribution
network.add(Activation('softmax'))

• keras 1.2.0
• python 2.7

给出以下异常：

ValueError：检查模型目标时出错：预期activation_1的形状为（无，60），但数组的形状为（10，100）

训练数据集是一个（10、6、10、10）数组，每层10 x 6层，每层是10x10数组（棋盘），为什么需要模型（无，60）？ 如果chagne input_shape=(6, 10, 10)到input_shape=(10, 10, 10) ，将得到：

ValueError：检查模型输入时出错：预期convolution2d_input_1具有形状（None，10，10，10）但具有形状（10，6，10，10）的数组

所有代码都在这里

Answer 1

正如Matias在评论中所说，如果您添加

network.summary() 

您可能会注意到，将卷积应用于输入数据的前两个维度（即（6,10,10））。 您的功能在第一个维度。 默认情况下，当您使用tensorflow时，Keras将假定要素将要放置的尺寸是第三个尺寸，而不是第一个尺寸。 出于这个原因，当您在（6,10,10）数组上应用128个过滤器时，输出将是（6,10,128），如果我理解的话，这不是您想要的。

因此，在最后一个卷积层的输出处，您将获得一个（6,10,1）数组，该数组将展平为（，60）而不是您期望的（100）。

有两种修复网络的方法。 您可以将输入数据更改为（10,10,6）格式。 或者，您可以使用Convolution2D()层的data_format="channels_first"参数。

这是第二个选项的代码：

from keras.models import Sequential, Model
from keras.layers.core import Activation, Flatten
from keras.layers import convolutional

defaults = {
            "board": 10,
            "filters_per_layer": 128,
            "layers": 12,
            "filter_width_1": 5
}
# copy defaults, but override with anything in kwargs
params = defaults
network = Sequential()
# create first layer
network.add(convolutional.Convolution2D(
      input_shape=(6, 10, 10),
      nb_filter=128,
      nb_row=5,
      nb_col=5,
      init='uniform',
      activation='relu',
      border_mode='same',
      data_format='channels_first'
      ))

# create all other layers
for i in range(2, 13):
     # use filter_width_K if it is there, otherwise use 3
     filter_key = "filter_width_%d" % i
     filter_width = params.get(filter_key, 3)

     # use filters_per_layer_K if it is there, otherwise use default value
     filter_count_key = "filters_per_layer_%d" % i
     filter_nb = params.get(filter_count_key, 128)

     network.add(convolutional.Convolution2D(
         nb_filter=filter_nb,
         nb_row=filter_width,
         nb_col=filter_width,
         init='uniform',
         activation='relu',
         border_mode='same',
         data_format='channels_first'))

# the last layer maps each <filters_per_layer> feature to a number
network.add(convolutional.Convolution2D(
    nb_filter=1,
    nb_row=1,
    nb_col=1,
    init='uniform',
    border_mode='same',
    data_format='channels_first'))
# reshape output to be board x board
network.add(Flatten())
# softmax makes it into a probability distribution
network.add(Activation('softmax'))
# display your network summary
network.summary()

编辑

考虑到您的keras版本，您应该使用参数“ dim_ordering”并将其设置为“ th”。

我在keras文档中找到了此信息

from keras.models import Sequential, Model
from keras.layers.core import Activation, Flatten
from keras.layers import convolutional

defaults = {
            "board": 10,
            "filters_per_layer": 128,
            "layers": 12,
            "filter_width_1": 5
}
# copy defaults, but override with anything in kwargs
params = defaults
network = Sequential()
# create first layer
network.add(convolutional.Convolution2D(
      input_shape=(6, 10, 10),
      nb_filter=128,
      nb_row=5,
      nb_col=5,
      init='uniform',
      activation='relu',
      border_mode='same',
      dim_ordering='th'
      ))

# create all other layers
for i in range(2, 13):
     # use filter_width_K if it is there, otherwise use 3
     filter_key = "filter_width_%d" % i
     filter_width = params.get(filter_key, 3)

     # use filters_per_layer_K if it is there, otherwise use default value
     filter_count_key = "filters_per_layer_%d" % i
     filter_nb = params.get(filter_count_key, 128)

     network.add(convolutional.Convolution2D(
         nb_filter=filter_nb,
         nb_row=filter_width,
         nb_col=filter_width,
         init='uniform',
         activation='relu',
         border_mode='same',
         dim_ordering='th'))

# the last layer maps each <filters_per_layer> feature to a number
network.add(convolutional.Convolution2D(
    nb_filter=1,
    nb_row=1,
    nb_col=1,
    init='uniform',
    border_mode='same',
    dim_ordering='th'))
# reshape output to be board x board
network.add(Flatten())
# softmax makes it into a probability distribution
network.add(Activation('softmax'))
# display your network summary
network.summary()