如何确保 con1D 的output_shape与 keras 自动编码器中具有时间序列input_shape相同？

Question

运行自动编码器拟合时，keras 自动编码器模型中的 Conv1D 输出形状不正确。

我尝试使用 keras 自动编码器模型来压缩和解压缩我的时间序列数据。 但是当我用Conv1D更改图层时，输出形状不正确。

我有一些形状为 (4000， 689) 的时间序列数据，其中代表 4000 个样本，每个样本有 689 个特征。我想使用Conv1D来压缩数据，但Upsampling层和最后Conv1D层的输出形状 (？， 688， 1) 不等于输入形状 (， 689， 1)。

我应该如何设置这些图层的参数？提前谢谢。

x_train = data[0:4000].values
x_test = data[4000:].values
print('x_train shape:', x_train.shape)
print('x_test shape:', x_test.shape)

x_train形状： (4000， 689)
x_test 形状： (202， 689)

我重新塑造了x_train，x_test到3dim，如下所示。

x_tr = x_train.reshape(4000,689,1)
x_te = x_test.reshape(202,689,1)
print('x_tr shape:', x_tr.shape)
print('x_te shape:', x_te.shape)

x_tr形状： (4000， 689， 1)
x_te 形状： (202， 689， 1)

input_img = Input(shape=(689,1))
x = Conv1D(16, 3, activation='relu', padding='same')(input_img)
print(x)
x = MaxPooling1D(2, padding='same')(x)
print(x)
x = Conv1D(8, 3, activation='relu', padding='same')(x)
print(x)
x = MaxPooling1D(2, padding='same')(x)
print(x)
x = Conv1D(8, 3, activation='relu', padding='same')(x)
print(x)
encoded = MaxPooling1D(2)(x)
print(encoded)
print('--------------')


x = Conv1D(8, 3, activation='relu', padding='same')(encoded)
print(x)
x = UpSampling1D(2)(x)
print(x)
x = Conv1D(8, 3, activation='relu', padding='same')(x)
print(x)
x = UpSampling1D(2)(x)
print(x)
x = Conv1D(16, 3, activation='relu', padding='same')(x)
print(x)
x = UpSampling1D(2)(x)
print(x)
decoded = Conv1D(1, 3, activation='sigmoid', padding='same')(x)
print(decoded)
autoencoder = Model(input_img, decoded)
autoencoder.compile(optimizer='adam', loss='mse')

当我导入这些模型并在 Jupyter 中运行上面的单元格时，似乎还可以。或。但是我在运行autoencoder.fit时在下一个代码中出现错误。

autoencoder.fit(x_tr, x_tr, epochs=50, batch_size=128, shuffle=True, validation_data=(x_te, x_te)) 

所以我print每一层。

每个图层的print结果如下。

Tensor("conv1d_166/Relu:0", shape=(?, 689, 16), dtype=float32)
Tensor("max_pooling1d_71/Squeeze:0", shape=(?, 345, 16), dtype=float32)
Tensor("conv1d_167/Relu:0", shape=(?, 345, 8), dtype=float32)
Tensor("max_pooling1d_72/Squeeze:0", shape=(?, 173, 8), dtype=float32)
Tensor("conv1d_168/Relu:0", shape=(?, 173, 8), dtype=float32)
Tensor("max_pooling1d_73/Squeeze:0", shape=(?, 86, 8), dtype=float32)
Tensor("conv1d_169/Relu:0", shape=(?, 86, 8), dtype=float32)
Tensor("up_sampling1d_67/concat:0", shape=(?, 172, 8), dtype=float32)
Tensor("conv1d_170/Relu:0", shape=(?, 172, 8), dtype=float32)
Tensor("up_sampling1d_68/concat:0", shape=(?, 344, 8), dtype=float32)
Tensor("conv1d_171/Relu:0", shape=(?, 344, 16), dtype=float32)
Tensor("up_sampling1d_69/concat:0", shape=(?, 688, 16), dtype=float32)
Tensor("conv1d_172/Sigmoid:0", shape=(?, 688, 1), dtype=float32) 

值错误波纹管：

ValueError                                Traceback (most recent call last)
<ipython-input-74-56836006a800> in <module>
3                 batch_size=128,
4                 shuffle=True,
----> 5                 validation_data=(x_te, x_te)
6                 )
~/anaconda3/envs/keras/lib/python3.6/site-packages/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, **kwargs)
950             sample_weight=sample_weight,
951             class_weight=class_weight,
--> 952             batch_size=batch_size)
953         # Prepare validation data.
954         do_validation = False
~/anaconda3/envs/keras/lib/python3.6/site-packages/keras/engine/training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, check_array_lengths, batch_size)
787                 feed_output_shapes,
788                 check_batch_axis=False,  # Don't enforce the batch size.
--> 789                 exception_prefix='target')
790 
791             # Generate sample-wise weight values given the `sample_weight` and
~/anaconda3/envs/keras/lib/python3.6/site-packages/keras/engine/training_utils.py in standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
136                             ': expected ' + names[i] + ' to have shape ' +
137                             str(shape) + ' but got array with shape ' +
--> 138                             str(data_shape))
139     return data
140 
ValueError: Error when checking target: expected conv1d_172 to have shape (688, 1) but got array with shape (689, 1)

floor函数是否使这种情况发生？
如何正确修复错误和autoencoder.fit？
提前感谢。

Answer 1

使用卷积层，您需要根据输入大小、内核大小和其他参数推断输出大小。最简单的方法是通过网络馈送数据样本，并查看最后一个卷积层之后的最终向量大小。然后，您可以根据该大小定义更多图层。

这是我的pytorch项目中的一个例子：

def _infer_flat_size(self):
encoder_output = self.encoder(torch.ones(1, *self.input_size))
return int(np.prod(encoder_output.size()[1:])), encoder_output.size()[1:]