我在处理一个多类分类问题，为了好玩，我想尝试不同的模型。我找到了一篇博客，它使用LSTM进行分类，我试图调整我的模型以使其工作。
这是我的模型：
from tensorflow import keras from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Dense, Dropout, Activation, Bidirectional, LSTM from tensorflow.keras.optimizers import SGD, Adam x_train_shape = X_train.shape[1] model = Sequential() model.add(Dense(x_train_shape, activation='tanh', input_dim=x_train_shape)) # model.add(Dropout(0.2)) model.add(Bidirectional(LSTM(32))) # model.add(Dense(x_train_shape, activation='tanh')) # model.add(Dense(x_train_shape, activation='tanh')) model.add(Dense(len(labels), activation='softmax')) model.compile(loss='categorical_crossentropy', optimizer="adam", metrics=['accuracy', 'TopKCategoricalAccuracy', 'FalsePositives']) model.fit(X_train, y_train, epochs=500, batch_size=200)它返回以下错误：
ValueError: Input 0 of layer bidirectional_5 is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: [None, 109]如果我取消注释LSTM下的Dense层并注释掉LSTM，模型就能工作，所以这肯定与LSTM行有关。
如何将LSTM层连接到Dense层以进行多类分类？
回答：
尝试在Dense层周围添加一个TimeDistributed层。这里有一个使用虚假数据的例子：
from tensorflow import kerasimport numpy as npfrom tensorflow.keras.models import Sequentialfrom tensorflow.keras.layers import *X_train = np.random.rand(100, 1, 10)y_train = np.random.randint(0, 10, 100)y_train = keras.utils.to_categorical(y_train)assert X_train.ndim == 3model = Sequential()model.add(TimeDistributed(Dense(10), input_shape=(X_train.shape[1:])))model.add(Bidirectional(LSTM(8)))model.add(Dense(8, activation='tanh'))model.add(Dense(8, activation='tanh'))model.add(Dense(y_train.shape[-1], activation='softmax'))model.compile(loss='categorical_crossentropy', optimizer="adam")history = model.fit(X_train, y_train, epochs=1, batch_size=8)Train on 100 samples 8/100 [=>............................] - ETA: 0s - loss: 2.2984 80/100 [=======================>......] - ETA: 0s - loss: 2.2863100/100 [==============================] - 0s 950us/sample - loss: 2.2984