0

I am trying to optimze hyperparamter for 1D CNN model using keras-tuner. Everything looks perfect while trying to get the best parameter. But when I try to print tuner.get_best_models()[0].summary(), it gives me the following error:

raise ValueError("Shapes %s and %s are incompatible" % (self, other)) ValueError: Shapes (78400, 10) and (235680, 10) are incompatible

def build_model(hp):  # random search passes this hyperparameter() object
    nSNP = X_train.shape[1]
    kernel_size = 3  # stride between convolutions

    model = keras.models.Sequential()

    model.add(Conv1D(hp.Int('input_units',
                            min_value=32,
                            max_value=256,
                            step=32), kernel_size, input_shape=(nSNP, 1)))

    model.add(Activation('relu'))
    model.add(MaxPooling1D(pool_size=2))

    for i in range(hp.Int('n_layers', 1, 4)):  # adding variation of layers.
        model.add(Conv1D(hp.Int(f'conv_{i}_units',
                                min_value=32,
                                max_value=256,
                                step=32), kernel_size))
        model.add(Activation('relu'))

    model.add(Flatten())
    model.add(Dense(10, activation='linear'))
    model.add(Dense(1))
    # model.add(Activation(hp.Choice('Activation', values=['relu', 'sigmoid', 'linear'])))

    # Tune the learning rate for the optimizer
    # Choose an optimal value from 0.01, 0.001, or 0.0001
    hp_learning_rate = hp.Choice('learning_rate', values=[1e-2, 1e-3, 1e-4, 1e-5,
                                                          1e-6, 1e-7])
    # hp_optimizer = hp.Choice('optimizer', values=['SGD', 'Adam'])
    adm = keras.optimizers.Adam(learning_rate=hp_learning_rate)
    model.compile(optimizer=adm, loss='mse')

    return model

tuner = keras_tuner.Hyperband(build_model,
                             objective='val_loss',
                             max_epochs=10,
                             factor=3)
stop_early = tensorflow.keras.callbacks.EarlyStopping(monitor='val_loss', patience=10)
    tuner.search(x=X2_train,
                 y=y_train,
                 verbose=2,     
                 epochs=50,
                 batch_size=64,
                 validation_data=(X2_valid, y_valid),
                 callbacks=[stop_early])
    
    # Get the optimal hyperparameters
    best_hps = tuner.get_best_hyperparameters(num_trials=1)[0]
    
    print(f"""
    The hyper-parameter search is complete.
    The optimal number of units in the first densely-connected
    layer is {best_hps.get('input_units')} and the optimal learning rate for the optimizer
    is {best_hps.get('learning_rate')}.
    """)
    
    print(tuner.get_best_hyperparameters()[0].values)
    tuner.get_best_models()[0].summary()

The input shape, training data shape is below:

X shape (195, 4915)
Y shape (195, 3)
X_train.shape (156, 4915) 
y_train.shape (156,)
X_valid.shape (39, 4915) 
y_valid.shape (39,)

tuner.get_best_models()[0].summary() supposed to print the following model summary:

keras-tuner model summary

How can I solve this error? If anyone helps me to solve this problem, it is appreciated.

Edy Ashton
  • 45
  • 3

1 Answers1

1

Don't know if you've managed to resolve this already but,

  1. Make sure you reset the Keras tuner as it remembers detailed logs and check points of every trial by passing the argument below when you're running the tuner.

    overwrite = True

  2. The model requires a three dimensional input in the following format: [n_samples, variables, features] where features = 1 in your case. Your X_train shape should look like (156, 4915, 1) and your X_test shape should look like (39, 4915, 1). To reshape your data use:

    X_train = np.array(X_train).reshape(X_train.shape[0], X_train.shape[1], 1)
X_test = np.array(X_test).reshape(X_test.shape[0], X_test.shape[1], 1)

Hope this helps.

Jinhee Kim
  • 11
  • 2