在 Google Colab 上构建模型时 TCN 层出现属性错误：“tuple”对象没有属性“as_list”

Question

我正在做一个需要使用时域卷积网络的项目，我找到了一个支持方便构建此网络的包：https://github.com/philipperemy/keras-tcn 下面是我用来定义 TCN 模型架构的代码。

!pip install keras-tcn

from tensorflow.keras import Input, Model
from tensorflow.keras.layers import Dense, Softmax, Lambda
from tcn import TCN

# Create the Input Layer
input_layer = Input(shape=(20, 225))

# First TCN Layer - parameters based on the tcn.py file
tcn_layer_1 = TCN(nb_filters=64,
                  kernel_size=3,
                  nb_stacks=1,
                  dilations=(1, 2, 4, 8),
                  padding='causal',
                  use_skip_connections=True,
                  return_sequences=True, # Important: Return sequences for stacked TCN layers
                  dropout_rate=0.05,
                  activation='relu',
                  use_batch_norm=False,
                  use_layer_norm=False)(input_layer)

# Second TCN Layer - similar parameters as the first layer
tcn_layer_2 = TCN(nb_filters=64,
                  kernel_size=3,
                  nb_stacks=1,
                  dilations=(1, 2, 4, 8),
                  padding='causal',
                  use_skip_connections=True,
                  return_sequences=False, # Final TCN layer, no need to return sequences
                  dropout_rate=0.05,
                  activation='relu',
                  use_batch_norm=False,
                  use_layer_norm=False)(tcn_layer_1)

# Dense Layer to further process the TCN output
dense_layer = Dense(128, activation='relu')(tcn_layer_2)

# Softmax Output Layer for classification
output_layer = Dense(len(gloss_list), activation='softmax')(dense_layer)

# Compile the model
model = Model(inputs=input_layer, outputs=output_layer)
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

# Print the model summary to verify the architecture
model.summary()

运行上面的代码块后会弹出以下错误。

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-7-3a050a142399> in <cell line: 9>()
      7 
      8 # First TCN Layer - parameters based on the tcn.py file
----> 9 tcn_layer_1 = TCN(nb_filters=64,
     10                   kernel_size=3,
     11                   nb_stacks=1,

1 frames
/usr/local/lib/python3.10/dist-packages/tcn/tcn.py in build(self, input_shape)
    314             self.output_slice_index = -1  # causal case.
    315         self.slicer_layer = Lambda(lambda tt: tt[:, self.output_slice_index, :], name='Slice_Output')
--> 316         self.slicer_layer.build(self.build_output_shape.as_list())
    317 
    318     def compute_output_shape(self, input_shape):

AttributeError: 'tuple' object has no attribute 'as_list'

最奇怪的是我实际上可以在我的 Macbook M1 Pro 上运行这段代码。

当我在本地计算机上运行代码时，会打印出模型的摘要。

我尝试查看 keras-tcn 包的代码，但一无所获。该错误来自TCN类的下面的方法，特别是来自最后一行代码

self.slicer_layer.build(self.build_output_shape.as_list())

。据我了解，

self.build_output_shape

在方法开始时设置为元组

input_shape

。为了使代码能够正常运行，我认为（实际上是 GPT-4o）

self.build_output_shape

将在

self.build_output_shape = self.residual_blocks[-1].res_output_shape

行更改为 TensorShape 对象。但对象的类型似乎没有改变，这导致了错误。再说一次，最奇怪的事情是这种情况只发生在 Google Colab 上，而不是我的本地计算机上。

def build(self, input_shape):

        # member to hold current output shape of the layer for building purposes
        self.build_output_shape = input_shape

        # list to hold all the member ResidualBlocks
        self.residual_blocks = []
        total_num_blocks = self.nb_stacks * len(self.dilations)
        if not self.use_skip_connections:
            total_num_blocks += 1  # cheap way to do a false case for below

        for s in range(self.nb_stacks):
            for i, d in enumerate(self.dilations):
                res_block_filters = self.nb_filters[i] if isinstance(self.nb_filters, list) else self.nb_filters
                self.residual_blocks.append(ResidualBlock(dilation_rate=d,
                                                          nb_filters=res_block_filters,
                                                          kernel_size=self.kernel_size,
                                                          padding=self.padding,
                                                          activation=self.activation_name,
                                                          dropout_rate=self.dropout_rate,
                                                          use_batch_norm=self.use_batch_norm,
                                                          use_layer_norm=self.use_layer_norm,
                                                          use_weight_norm=self.use_weight_norm,
                                                          kernel_initializer=self.kernel_initializer,
                                                          name='residual_block_{}'.format(len(self.residual_blocks))))
                # build newest residual block
                self.residual_blocks[-1].build(self.build_output_shape)
                self.build_output_shape = self.residual_blocks[-1].res_output_shape

        # this is done to force keras to add the layers in the list to self._layers
        for layer in self.residual_blocks:
            self.__setattr__(layer.name, layer)

        self.output_slice_index = None
        if self.padding == 'same':
            time = self.build_output_shape.as_list()[1]
            if time is not None:  # if time dimension is defined. e.g. shape = (bs, 500, input_dim).
                self.output_slice_index = int(self.build_output_shape.as_list()[1] / 2)
            else:
                # It will known at call time. c.f. self.call.
                self.padding_same_and_time_dim_unknown = True

        else:
            self.output_slice_index = -1  # causal case.
        self.slicer_layer = Lambda(lambda tt: tt[:, self.output_slice_index, :], name='Slice_Output')
        self.slicer_layer.build(self.build_output_shape.as_list())

Answer 1

我降级了它运行的Colab中的tensorflow版本，Colab通常安装版本2.17.0 我用这个代码来降级它 #!pip install tensorflow==2.12 # 安装tensorflow 2.12 将张量流导入为 tf 打印（tf。版本）