ValueError: Input 0 of layer conv1d is incompatible with the layer: : expected min_ndim=3, found ndim=2. Full shape received: (None, 19)

0
votes
  1. I am building a prediction model for the sequence data using conv1d layer provided by Keras. This is how I did`
def autoencoder():  
    #autoencoder = Model(inputs=input_layer, outputs=decoder)
    input_dim = x_train_scaled.shape[1]
    input_layer = Input(shape=(input_dim,))
    conv1 = Conv1D(filters = 32, kernel_size=3,activation='relu') (input_layer)
    batch1 = BatchNormalization()(conv1)
    maxp1 = MaxPooling1D(pool_size=2)(batch1)
    dropout1 = Dropout(0.2)(maxp1)
    conv2 = Conv1D(filters = 16, kernel_size=3,activation='relu') (dropout1)
    batch2 = BatchNormalization()(conv2)
    maxp2 = MaxPooling1D(2)(batch2)
    dropout2 = Dropout(0.2)(maxp2)
    conv3 = Conv1D(filters = 8, kernel_size=3,activation='relu') (dropout2)
    batch3 = BatchNormalization()(conv3)
    maxp3 = MaxPooling1D(2)(batch3)
    dropout3 = Dropout(0.2)(maxp3)
    #decoder layers 
    conv4 = Conv1D(filters = 8, kernel_size=3,activation='relu') (dropout3)
    batch4 = BatchNormalization()(conv4)
    dropout4 = Dropout(0.2)(batch4)
    conv5 = Conv1D(filters = 16, kernel_size=3,activation='relu') (dropout4)
    batch5 = BatchNormalization()(conv5)
    unsamp5 = UpSampling1D(2)(batch5)
    dropout5 = Dropout(0.2)(unsamp5)
    conv6 = Conv1D(filters = 32, kernel_size=3,activation='relu') (dropout5)
    batch6 = BatchNormalization()(conv6)
    unsamp6 = UpSampling1D(2)(batch6)
    dropout6 = Dropout(0.2)(unsamp6)
    decoder = Conv1D(filters = 1, kernel_size=3,activation='sigmoid') (dropout6)
    return Model(input_layer, decoder)
  1. Train model to reduce the data dimension using autoencoder

model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

model.fit(x_train_scaled, x_train_scaled, epochs=15, batch_size=32, verbose=verbose, shuffle=True)

  1. However, the debugging information has

ValueError: Input 0 of layer conv1d is incompatible with the layer: : expected min_ndim=3, found ndim=2. Full shape received: (None, 19)

  1. The training data and validation data shape are as follows

x_train_scaled shape (125973, 19)

  1. Dataset use to train model NSL-KDD(https://www.unb.ca/cic/datasets/nsl.html)
pythontensorflow