我正在使用 TensorFlow 在时间序列回归问题上试验有状态 LSTM。我很抱歉无法共享数据集。下面是我的代码。
train_feature = train_feature.reshape((train_feature.shape[0], 1, train_feature.shape[1]))
val_feature = val_feature.reshape((val_feature.shape[0], 1, val_feature.shape[1]))
batch_size = 64
model = tf.keras.Sequential()
model.add(tf.keras.layers.LSTM(50, batch_input_shape=(batch_size, train_feature.shape[1], train_feature.shape[2]), stateful=True))
model.add(tf.keras.layers.Dense(1))
model.compile(optimizer='adam',
loss='mse',
metrics=[tf.keras.metrics.RootMeanSquaredError()])
model.fit(train_feature, train_label,
epochs=10,
batch_size=batch_size)
Run Code Online (Sandbox Code Playgroud)
当我运行上面的代码时,在第一个 epoch 结束后,我会得到如下错误。
InvalidArgumentError: [_Derived_] Invalid input_h shape: [1,64,50] [1,49,50]
[[{{node CudnnRNN}}]]
[[sequential_1/lstm_1/StatefulPartitionedCall]] [Op:__inference_train_function_1152847]
Function call stack:
train_function -> train_function -> train_function
Run Code Online (Sandbox Code Playgroud)
但是,如果我将batch_size更改为 1,并将模型训练的代码更改为以下代码,则模型将成功训练。
total_epochs = 10
for i in range(total_epochs):
model.fit(train_feature, train_label,
epochs=1,
validation_data=(val_feature, val_label),
batch_size=batch_size,
shuffle=False)
model.reset_states()
Run Code Online (Sandbox Code Playgroud)
尽管如此,对于非常大的数据(100 万行),由于batch_size 为1,模型训练将花费很长时间。
所以,我想知道,如何训练批量大小大于 …