tensorflow/keras lstm 输入形状

Question

我正在尝试通过 Keras 的 tutorials 学习 keras 功能 API，当我尝试修改示例时，我似乎得到了形状不匹配的问题。教程代码和下面的唯一区别是我删除了嵌入层，因为我的是回归问题。

首先，我知道 LSTM 需要 3 个维度。在我的示例中，我有：

TRAIN_BATCH_SIZE=32
MODEL_INPUT_BATCH_SIZE=128

headline_data = np.random.uniform(low=1, high=9000, size=(MODEL_INPUT_BATCH_SIZE, 100)).astype(np.float32)
additional_data = np.random.uniform(low=1, high=9000, size=(MODEL_INPUT_BATCH_SIZE, 5)).astype(np.float32)
labels = np.random.randint(0, 1 + 1, size=(MODEL_INPUT_BATCH_SIZE, 1))

main_input = Input(shape=(100,), dtype='float32', name='main_input')

lstm_out = LSTM(32)(main_input)

auxiliary_output = Dense(1, activation='sigmoid', name='aux_output')(lstm_out)

auxiliary_input = Input(shape=(5,), name='aux_input')
x = keras.layers.concatenate([lstm_out, auxiliary_input])

# We stack a deep densely-connected network on top
x = Dense(64, activation='relu')(x)
x = Dense(64, activation='relu')(x)
x = Dense(64, activation='relu')(x)

# And finally we add the main logistic regression layer
main_output = Dense(1, activation='sigmoid', name='main_output')(x)

# This defines a model with two inputs and two outputs:
model = Model(inputs=[main_input, auxiliary_input], outputs=[main_output, auxiliary_output])

model.compile(optimizer='rmsprop',
                loss={'main_output': 'binary_crossentropy', 'aux_output': 'binary_crossentropy'},
                loss_weights={'main_output': 1., 'aux_output': 0.2})

# And trained it via:
model.fit({'main_input': headline_data, 'aux_input': additional_data},
                {'main_output': labels, 'aux_output': labels},
                epochs=2, batch_size=TRAIN_BATCH_SIZE)

当我运行上述内容时，我得到：

ValueError: Input 0 is incompatible with layer lstm_1: expected ndim=3, found ndim=2

所以，我尝试像这样改变我的输入形状：

main_input = Input(shape=(100,1), dtype='float64', name='main_input')

当我运行它时，我得到：

ValueError: Error when checking input: expected main_input to have 3 dimensions, but got array with shape (128, 100)

我对错误的来源感到困惑和迷茫。非常感谢您对此提供一些指导。

编辑

我也试过设置：

headline_data = np.expand_dims(headline_data, axis=2)

然后使用，

main_input = Input(shape=headline_data.shape, dtype='float64', name='main_input')

然后，我得到：

ValueError: Input 0 is incompatible with layer lstm_1: expected ndim=3, found ndim=4

看起来真的很奇怪！

Answer 1

ValueError: Input 0 is incompatible with layer lstm_1: expected ndim=3, found ndim=2

您的问题在于数据的形状。

headline_data = np.random.uniform(low=1, high=9000, size=(MODEL_INPUT_BATCH_SIZE, 100))
headline_data.shape

返回

(128,100)

但是这应该具有三个维度。

如果不仔细检查，您可能需要执行以下操作：

headline_data.reshape(128,1,100)

看看这篇文章，它应该清楚一切。

Link

* 更新 *

执行以下操作：

headling_data = healdine_data.reshape(128,1,100)
main_input = Input(shape=(1,100), dtype='float32', name='main_input')

我测试了它并且它有效，所以如果它不适合你，请告诉我 =)

---- 完整代码：----

import numpy as np

from tensorflow import keras
from tensorflow.keras import Model
from tensorflow.keras.layers import Input, LSTM, Dense


TRAIN_BATCH_SIZE=32
MODEL_INPUT_BATCH_SIZE=128

headline_data = np.random.uniform(low=1, high=9000, size=(MODEL_INPUT_BATCH_SIZE, 100)).astype(np.float32)
headline_data.shape
lstm_data = headline_data.reshape(MODEL_INPUT_BATCH_SIZE,1,100)
additional_data = np.random.uniform(low=1, high=9000, size=(MODEL_INPUT_BATCH_SIZE, 5)).astype(np.float32)
labels = np.random.randint(0, 1 + 1, size=(MODEL_INPUT_BATCH_SIZE, 1))

main_input = Input(shape=(1,100), dtype='float32', name='main_input')

lstm_out = LSTM(32)(main_input)

auxiliary_output = Dense(1, activation='sigmoid', name='aux_output')(lstm_out)

auxiliary_input = Input(shape=(5,), name='aux_input')
x = keras.layers.concatenate([lstm_out, auxiliary_input])

# We stack a deep densely-connected network on top
x = Dense(64, activation='relu')(x)
x = Dense(64, activation='relu')(x)
x = Dense(64, activation='relu')(x)

# And finally we add the main logistic regression layer
main_output = Dense(1, activation='sigmoid', name='main_output')(x)

# This defines a model with two inputs and two outputs:
model = Model(inputs=[main_input, auxiliary_input], outputs=[main_output, auxiliary_output])

model.compile(optimizer='rmsprop',
                loss={'main_output': 'binary_crossentropy', 'aux_output': 'binary_crossentropy'},
                loss_weights={'main_output': 1., 'aux_output': 0.2})

# And trained it via:
model.fit({'main_input': lstm_data, 'aux_input': additional_data},
                {'main_output': labels, 'aux_output': labels},
                epochs=1000, batch_size=TRAIN_BATCH_SIZE)