我目前正在使用基本的LSTM进行回归预测，并且我想实现因果的CNN，因为它应该在计算上更加有效。
我正在努力弄清楚如何重塑当前数据以适应因果CNN单元并表示相同的数据/时间步长关系以及应设置的扩展率。
我当前的数据是这样的:(number of examples, lookback, features)，这是我现在正在使用的LSTM NN的基本示例。
lookback = 20 # height -- timeseries
n_features = 5 # width -- features at each timestep
# Build an LSTM to perform regression on time series input/output data
model = Sequential()
model.add(LSTM(units=256, return_sequences=True, input_shape=(lookback, n_features)))
model.add(Activation('elu'))
model.add(LSTM(units=256, return_sequences=True))
model.add(Activation('elu'))
model.add(LSTM(units=256))
model.add(Activation('elu'))
model.add(Dense(units=1, activation='linear'))
model.compile(optimizer='adam', loss='mean_squared_error')
model.fit(X_train, y_train,
epochs=50, batch_size=64,
validation_data=(X_val, y_val),
verbose=1, shuffle=True)
prediction = model.predict(X_test)
然后，我创建了一个新的CNN模型(尽管不是因果关系，因为根据Keras文档，
'causal'填充仅是Conv1D而非Conv2D的选项。如果我正确理解，具有多个功能，则需要使用Conv2D，而不是Conv1D，但是如果我设置Conv2D(padding='causal')，则会出现以下错误-Invalid padding: causal)无论如何，我还能够使用新的形状
(number of examples, lookback, features, 1)拟合数据，并使用Conv2D层运行以下模型:lookback = 20 # height -- timeseries
n_features = 5 # width -- features at each timestep
model = Sequential()
model.add(Conv2D(128, 3, activation='elu', input_shape=(lookback, n_features, 1)))
model.add(MaxPool2D())
model.add(Conv2D(128, 3, activation='elu'))
model.add(MaxPool2D())
model.add(Flatten())
model.add(Dense(1, activation='linear'))
model.compile(optimizer='adam', loss='mean_squared_error')
model.fit(X_train, y_train,
epochs=50, batch_size=64,
validation_data=(X_val, y_val),
verbose=1, shuffle=True)
prediction = model.predict(X_test)
但是，根据我的理解，这不会将数据作为因果关系传播，而只会将整个
(lookback, features, 1)传播为图像。是否可以通过多种功能重塑我的数据以使其适合
Conv1D(padding='causal')图层，或者以某种方式运行与Conv2D相同的数据和输入形状，并使用'causal'填充？ 最佳答案
我相信您可以为任意数量的输入功能使用因果填充和扩展。这是我建议的解决方案。
TimeDistributed layer对此很关键。
来自Keras文档:“此包装器将层应用于输入的每个时间切片。输入应至少为3D，并且索引一的维将被视为时间维。”
出于我们的目的，我们希望该层对每个要素应用“内容”，因此我们将要素移至时间索引(即1)。
另一个相关的是Conv1D documentation。
专门关于 channel 的信息:“输入中维的顺序。“channels_last”对应于具有形状(批处理，步骤， channel )的输入(Keras中时间数据的默认格式)”
from tensorflow.python.keras import Sequential, backend
from tensorflow.python.keras.layers import GlobalMaxPool1D, Activation, MaxPool1D, Flatten, Conv1D, Reshape, TimeDistributed, InputLayer
backend.clear_session()
lookback = 20
n_features = 5
filters = 128
model = Sequential()
model.add(InputLayer(input_shape=(lookback, n_features, 1)))
# Causal layers are first applied to the features independently
model.add(Reshape(target_shape=(n_features, lookback, 1)))
# After reshape 5 input features are now treated as the temporal layer
# for the TimeDistributed layer
# When Conv1D is applied to each input feature, it thinks the shape of the layer is (20, 1)
# with the default "channels_last", therefore...
# 20 times steps is the temporal dimension
# 1 is the "channel", the new location for the feature maps
model.add(TimeDistributed(Conv1D(filters, 3, activation="elu", padding="causal", dilation_rate=2**0)))
# You could add pooling here if you want.
# If you want interaction between features AND causal/dilation, then apply later
model.add(TimeDistributed(Conv1D(filters, 3, activation="elu", padding="causal", dilation_rate=2**1)))
model.add(TimeDistributed(Conv1D(filters, 3, activation="elu", padding="causal", dilation_rate=2**2)))
# Stack feature maps on top of each other so each time step can look at
# all features produce earlier
model.add(Reshape(target_shape=(lookback, n_features * filters))) # (20 time steps, 5 features * 128 filters)
# Causal layers are applied to the 5 input features dependently
model.add(Conv1D(filters, 3, activation="elu", padding="causal", dilation_rate=2**0))
model.add(MaxPool1D())
model.add(Conv1D(filters, 3, activation="elu", padding="causal", dilation_rate=2**1))
model.add(MaxPool1D())
model.add(Conv1D(filters, 3, activation="elu", padding="causal", dilation_rate=2**2))
model.add(GlobalMaxPool1D())
model.add(Dense(units=1, activation='linear'))
model.compile(optimizer='adam', loss='mean_squared_error')
model.summary()
最终模型摘要
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
reshape (Reshape) (None, 5, 20, 1) 0
_________________________________________________________________
time_distributed (TimeDistri (None, 5, 20, 128) 512
_________________________________________________________________
time_distributed_1 (TimeDist (None, 5, 20, 128) 49280
_________________________________________________________________
time_distributed_2 (TimeDist (None, 5, 20, 128) 49280
_________________________________________________________________
reshape_1 (Reshape) (None, 20, 640) 0
_________________________________________________________________
conv1d_3 (Conv1D) (None, 20, 128) 245888
_________________________________________________________________
max_pooling1d (MaxPooling1D) (None, 10, 128) 0
_________________________________________________________________
conv1d_4 (Conv1D) (None, 10, 128) 49280
_________________________________________________________________
max_pooling1d_1 (MaxPooling1 (None, 5, 128) 0
_________________________________________________________________
conv1d_5 (Conv1D) (None, 5, 128) 49280
_________________________________________________________________
global_max_pooling1d (Global (None, 128) 0
_________________________________________________________________
dense (Dense) (None, 1) 129
=================================================================
Total params: 443,649
Trainable params: 443,649
Non-trainable params: 0
_________________________________________________________________
编辑:
“为什么需要重塑形状并将n_features用作时间层”
最初需要将n_features置于时间层的原因是，具有扩张和因果填充的Conv1D一次仅适用于一个特征，并且还涉及到如何实现TimeDistributed层。
从他们的文档“考虑一批32个样本，其中每个样本是一个由16个维度的10个向量组成的序列。该层的批次输入形状为(32，10，16)，input_shape不包括样本维度，是(10，16)。
然后，您可以使用TimeDistributed独立地将Dense图层应用于10个时间步长中的每个时间步长:”
通过将TimeDistributed层独立地应用于每个要素，它可以减小问题的范围，就好像只有一个要素一样(这很容易允许膨胀和因果填充)。具有5个功能，它们首先需要分别处理。
关于python - 因果关系的多特征CNN-Keras实现，我们在Stack Overflow上找到一个类似的问题：https://stackoverflow.com/questions/55850797/