Question

我正在尝试创建CNN + LSTM网络，但是LSTM层不接受输入形状。我有什么可以做的吗？

model = Sequential()
model.add(Conv2D(128, (2,2), padding = 'same', input_shape=(30, 216, 1)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.2))

model.add(Conv2D(256, (2,2), padding = 'same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.2))

model.add(LSTM(512, input_shape = (7, 54, 256,)))
model.add(Flatten())
model.add(Dense(7, activation='softmax'))

ValueError：lstm_21层的输入0与该层不兼容：预期ndim = 3，找到的ndim = 4。收到完整的图形：[None，7，54，256]

Answer 1

Keras的LSTM层希望此格式作为输入：

inputs: A 3D tensor with shape [batch, timesteps, feature].

因此，您不能直接传递非循环图层。首先，Flatten()之前的图层，然后将该图层包装为TimeDistributed图层，如下所示：

model.add(TimeDistributed(Flatten()))
model.add(LSTM(8))

此TimeDistributed层允许将层应用于输入的每个时间切片。这是一个完整的示例：

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, LSTM, \
    Dense, Flatten, Dropout, MaxPooling2D, Activation, TimeDistributed
import numpy as np

X = np.random.rand(100, 30, 216, 1)
y = np.random.randint(0, 7, 100)

model = Sequential()
model.add(Conv2D(16, (2,2), padding = 'same', input_shape=(30, 216, 1)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.2))

model.add(Conv2D(32, (2,2), padding = 'same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.2))
model.add(TimeDistributed(Flatten()))
model.add(LSTM(8))
model.add(Dense(7, activation='softmax'))

model.compile(loss='sparse_categorical_crossentropy', optimizer='adam')
history = model.fit(X, y)

LSTM层不接受CNN层输出的输入形状

1 个答案: