Exemple #1
0
def train_model(dataset):
    X = T.tensor4()
    S = T.tensor3()

    layers = []
    layers.append(ConvPoolLayer(
        input=X,
        input_shape=(3, 160, 80),
        filter_shape=(32, 3, 5, 5),
        pool_shape=(2, 2),
        active_func=actfuncs.tanh,
        flatten=False
    ))

    layers.append(ConvPoolLayer(
        input=layers[-1].output,
        input_shape=layers[-1].output_shape,
        filter_shape=(64, 32, 5, 5),
        pool_shape=(2, 2),
        active_func=actfuncs.tanh,
        flatten=False
    ))

    layers.append(FullConnLayer(
        input=layers[-1].output.flatten(2),
        input_shape=np.prod(layers[-1].output_shape),
        output_shape=1024,
        dropout_ratio=0.1,
        active_func=actfuncs.tanh
    ))

    layers.append(FullConnLayer(
        input=layers[-1].output,
        input_shape=layers[-1].output_shape,
        output_shape=37 * 17,
        dropout_input=layers[-1].dropout_output,
        active_func=actfuncs.sigmoid
    ))

    model = NeuralNet(layers, X, layers[-1].output)
    model.target = S

    '''
    model.cost = costfuncs.binxent(layers[-1].dropout_output, S.flatten(2)) + \
        1e-3 * model.get_norm(2)
    model.error = costfuncs.binerr(layers[-1].output, S.flatten(2))
    '''

    model.cost = costfuncs.weighted_norm2(
        layers[-1].dropout_output, S.flatten(2), 1.0) + \
        1e-3 * model.get_norm(2)
    model.error = costfuncs.weighted_norm2(
        layers[-1].output, S.flatten(2), 1.0)

    sgd.train(model, dataset, lr=1e-2, momentum=0.9,
              batch_size=100, n_epochs=300,
              epoch_waiting=10)

    return model
Exemple #2
0
def train_model(dataset):
    X = T.matrix()
    S = T.tensor3()

    layers = []

    layers.append(FullConnLayer(
        input=X,
        input_shape=2784,
        output_shape=1024,
        dropout_ratio=0.1,
        active_func=actfuncs.tanh
    ))

    """
    layers.append(FullConnLayer(
        input=layers[-1].output,
        input_shape=layers[-1].output_shape,
        output_shape=1024,
        dropout_ratio=0.1,
        dropout_input=layers[-1].dropout_output,
        active_func=actfuncs.tanh
    ))
    """

    layers.append(FullConnLayer(
        input=layers[-1].output,
        input_shape=layers[-1].output_shape,
        output_shape=37 * 17,
        dropout_input=layers[-1].dropout_output,
        active_func=actfuncs.sigmoid
    ))

    model = NeuralNet(layers, X, layers[-1].output)
    model.target = S

    '''
    model.cost = costfuncs.binxent(layers[-1].dropout_output, S.flatten(2)) + \
        1e-3 * model.get_norm(2)
    model.error = costfuncs.binerr(layers[-1].output, S.flatten(2))
    '''

    model.cost = costfuncs.weighted_norm2(
        layers[-1].dropout_output, S.flatten(2), 1.0) + \
        1e-3 * model.get_norm(2)
    model.error = costfuncs.weighted_norm2(
        layers[-1].output, S.flatten(2), 1.0)

    sgd.train(model, dataset, lr=1e-2, momentum=0.9,
              batch_size=100, n_epochs=300,
              epoch_waiting=10, never_stop=True)

    return model