python - model.fit() Keras 分类多输入-单输出给出错误 : AttributeError: 'NoneType' object has no attribute 'fit'

Question

我正在构建一个具有多个输入(实际上是 3 个)的 Keras 分类模型来预测一个输出。具体来说，我的 3 个输入是:

1. Actor
2. 剧情简介
3. 相关电影特色

输出:

1. 类型标签

以上所有输入和单个输出均与 10,000 部 IMDB 电影相关。

即使模型的创建成功，当我尝试将模型适合我的三个不同的 X_train 时，我收到属性错误。我有一个用于 Actor 的 X_train 和 X_test，另一个用于情节摘要的 X_train 和 X_test，以及另一个用于电影功能的 X_train 和 X_test。我的 y_train 和 y_test 对于所有输入都是相同的。

Python代码(创建多个输入keras)

def kera_multy_classification_model():

    sentenceLength_actors = 15
    vocab_size_frequent_words_actors = 20001

    sentenceLength_plot = 23
    vocab_size_frequent_words_plot = 17501

    sentenceLength_features = 69
    vocab_size_frequent_words_features = 20001

    model = keras.Sequential(name='Multy-Input Keras Classification model')

    actors = keras.Input(shape=(sentenceLength_actors,), name='actors_input')
    plot = keras.Input(shape=(sentenceLength_plot,), name='plot_input')
    features = keras.Input(shape=(sentenceLength_features,), name='features_input')

    emb1 = layers.Embedding(input_dim = vocab_size_frequent_words_actors + 1,
                            # based on keras documentation input_dim: int > 0. Size of the vocabulary, i.e. maximum integer index + 1.
                            output_dim = Keras_Configurations_model1.EMB_DIMENSIONS,
                            # int >= 0. Dimension of the dense embedding
                            embeddings_initializer = 'uniform', 
                            # Initializer for the embeddings matrix.
                            mask_zero = False,
                            input_length = sentenceLength_actors,
                            name="actors_embedding_layer")(actors)
    encoded_layer1 = layers.LSTM(100)(emb1)

    emb2 = layers.Embedding(input_dim = vocab_size_frequent_words_plot + 1,
                            output_dim = Keras_Configurations_model2.EMB_DIMENSIONS,
                            embeddings_initializer = 'uniform',
                            mask_zero = False,
                            input_length = sentenceLength_plot,
                            name="plot_embedding_layer")(plot)
    encoded_layer2 = layers.LSTM(100)(emb2)

    emb3 = layers.Embedding(input_dim = vocab_size_frequent_words_features + 1,
                            output_dim = Keras_Configurations_model3.EMB_DIMENSIONS,
                            embeddings_initializer = 'uniform',
                            mask_zero = False,
                            input_length = sentenceLength_features,
                            name="features_embedding_layer")(features)
    encoded_layer3 = layers.LSTM(100)(emb3)

    merged = layers.concatenate([encoded_layer1, encoded_layer2, encoded_layer3])

    layer_1 = layers.Dense(Keras_Configurations_model1.BATCH_SIZE, activation='relu')(merged)

    output_layer = layers.Dense(Keras_Configurations_model1.TARGET_LABELS, activation='softmax')(layer_1)

    model = keras.Model(inputs=[actors, plot, features], outputs=output_layer)

    print(model.output_shape)

    print(model.summary())

    model.compile(optimizer='adam',
                  loss='sparse_categorical_crossentropy',
                  metrics=['sparse_categorical_accuracy'])

Python 代码(适合我的输入的多个输入 keras)

def fit_keras_multy_input(model, x_train_seq_actors, x_train_seq_plot, x_train_seq_features, x_test_seq_actors, x_test_seq_plot, x_test_seq_features, y_train, y_test):

    s = time()

    fit_model = model.fit([x_train_seq_actors, x_train_seq_plot, x_train_seq_features], y_train, 
                          epochs=Keras_Configurations_model1.NB_EPOCHS,
                          verbose = Keras_Configurations_model1.VERBOSE,
                          batch_size=Keras_Configurations_model1.BATCH_SIZE,
                          validation_data=([x_test_seq_actors, x_test_seq_plot, x_test_seq_features], y_test),
                          callbacks=callbacks)

    duration = time() - s
    print("\nTraining time finished. Duration {} secs".format(duration))

模型的结构

产生错误

注意:请注意 X_train 和 X_test 都是数字序列。 (已标记化的文本)

经过一些研究，问题开始于 model.compile() 函数。虽然，我不确定应该在我的模型的编译函数中更改什么来解决这个问题。

预先感谢您就此事提供的任何建议或帮助。请随时在评论中询问我可能错过的任何其他信息，以使这个问题更加完整。

Answer 1

您的函数kera_multy_classification_model()不会返回任何内容，因此在model = kera_multy_classification_model()之后，您会得到model == None为你的函数什么也不返回。 None 的类型是 NoneType 并且它确实没有名为 fit() 的方法。

只需在kera_multy_classification_model()末尾添加返回模型即可。