当我尝试训练我的张量流模型时，出现“ValueError”

Question

这是我在调用 model.fit 时在第一个时期遇到的错误：

Exception has occurred: ValueError
Layer "functional" expects 2 input(s), but it received 1 input tensors. Inputs received: [<tf.Tensor 'data:0' shape=(None, 128) dtype=float32>]
  File "D:\workspace\Machine Learning 545\PSU_classes\cs445_group_project\code\Keras Music Genres Classification\encoder_decoder_feature_extractor.py", line 177, in train_encoder_decoder_model
    model.fit(x = X_train,
  File "D:\workspace\Machine Learning 545\PSU_classes\cs445_group_project\code\Keras Music Genres Classification\encoder_decoder_feature_extractor.py", line 217, in <module>
    trained_model = train_encoder_decoder_model(encoder_decoder_model, X_train, y_train, X_test, y_test)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: Layer "functional" expects 2 input(s), but it received 1 input tensors. Inputs received: [<tf.Tensor 'data:0' shape=(None, 128) dtype=float32>]"

这是我的模型：

def define_encoder_decoder_model(num_features):
    # Define the encoder
    encoder_inputs = Input(shape=(None, num_features))
    encoder_hidden1 = Dense(100, activation='relu')(encoder_inputs)
    encoder_hidden2 = Dense(50, activation='relu')(encoder_hidden1)
    encoder_lstm = LSTM(25, return_state=True)
    encoder_outputs, state_h, state_c = encoder_lstm(encoder_hidden2)
    encoder_states = [state_h, state_c]

    # Define the decoder
    decoder_inputs = Input(shape=(None, 25))
    decoder_hidden1 = Dense(50, activation='relu')(decoder_inputs)
    decoder_hidden2 = Dense(100, activation='relu')(decoder_hidden1)
    decoder_lstm = LSTM(num_features, return_sequences=True, return_state=True)
    decoder_outputs, _, _ = decoder_lstm(decoder_hidden2, initial_state=encoder_states)
    decoder_dense = Dense(num_features, activation='softmax')
    decoder_outputs = decoder_dense(decoder_outputs)

    # Define the model that will turn encoder_inputs and decoder_inputs into decoder_outputs
    model = Model([encoder_inputs, decoder_inputs], decoder_outputs)

    # Compile the model
    model.compile(optimizer='adam', loss='categorical_crossentropy', 
                  metrics=['accuracy', 'precision', 'recall', 'f1_score'])

    # Summary of the model
    model.summary()

    return modeltype here

这就是我调用 model.fit 的方式：

def train_encoder_decoder_model(model, X_train, y_train, X_test, y_test):
    """
    Trains an encoder-decoder model using the provided data.

    Args:
        model: The encoder-decoder model to train.
        X_train: The input training data.
        y_train: The target training data.
        X_test: The input test data.
        y_test: The target test data.

    Returns:
        The trained encoder-decoder model.
    """
    print("shapes: X_train:", np.shape(X_train)," y_train: ", np.shape(y_train)," X_test: ", np.shape(X_test)," y_test: ", np.shape(y_test))
    # Train the model
    # append to a file the training log for each epoch
    file_logger = FileLogger('training.log')
    y_train_T = tf.convert_to_tensor(np.array([y_train]).T)
    y_test_T = tf.convert_to_tensor(np.array([y_test]).T)
    #x_train = tf.convert_to_tensor(X_train)
    y_train = X_train
    y_test = X_test
    model.fit(x = X_train,
              y= y_train,
              batch_size=100,
              epochs=100,
              verbose=2,
              validation_data=(X_test, y_test),
              callbacks=[file_logger])
    return model

这是一个编码器-解码器模型，因此 X_train 数据集等于 y_train，X_test、y_test 也相同。在第一种情况下，训练集的形状是 (799,128)，测试数据集是 (299,128)。这些特征表示为“float64”值。

我正在 Visual Studio Code 下运行代码。我将数据预处理为标准化和缩放的数据集，然后将其分为训练数据集和测试数据集，构建我的编码器-解码器模型（请参阅上面的方法），然后尝试训练模型。我得到的是 model.fit“Epoch 1/100”的输出以及上面显示的错误消息。

这个错误是什么以及如何解决？

Answer 1

您的模型是一种编码器-解码器架构，需要两个输入：一个用于编码器，一个用于解码器。

具体：

encoder_inputs (shape (None, num_features))
decoder_inputs (shape (None, 25))

但是，在 model.fit() 调用中，您只提供单个输入 (X_train)，这就是模型抛出错误的原因 ->

expects 2 input(s), but it received 1

要解决此问题，您需要确保将两个输入传递给 model.fit() 函数：一个用于编码器，一个用于解码器。以下是如何做到这一点的示例：

1- 确保 X_train 和 y_train 的形状正确以匹配模型的预期：

X_train 应该是编码器的输入。 y_train 应该是解码器的输入。

既然您提到编码器和解码器使用相同的数据，您可以调整 train_encoder_decoder_model 函数来处理此问题：

def train_encoder_decoder_model(model, X_train, y_train, X_test, y_test):
    # Create decoder inputs which is the same as y_train but shifted by one timestep
    decoder_input_data = np.zeros_like(X_train)
    decoder_input_data[:, 1:] = X_train[:, :-1]
    
    # Now, y_train should be the actual outputs you expect from the decoder.
    y_train_T = np.array([y_train]).T

    # The same logic applies for the test data
    decoder_input_test = np.zeros_like(X_test)
    decoder_input_test[:, 1:] = X_test[:, :-1]
    
    y_test_T = np.array([y_test]).T

    model.fit(x=[X_train, decoder_input_data],
              y=y_train_T,
              batch_size=100,
              epochs=100,
              verbose=2,
              validation_data=([X_test, decoder_input_test], y_test_T),
              callbacks=[file_logger])
    return model

您还需要更新 model.fit() 中的模型输入：

model.fit(x=[X_train, decoder_input_data],  # Two inputs
          y=y_train_T,  # Target output
          batch_size=100,
          epochs=100,
          verbose=2,
          validation_data=([X_test, decoder_input_test], y_test_T),  # Two inputs for validation
          callbacks=[file_logger])