python类nesterov_momentum()的实例源码-第2页-面圈网

demo.py 文件源码项目：ip-avsr 作者: lzuwei 项目源码文件源码阅读 35 收藏 0 点赞 0 评论 0

def load_dbn(path='models/oulu_ae.mat'):
    """
    load a pretrained dbn from path
    :param path: path to the .mat dbn
    :return: pretrained deep belief network
    """
    # create the network using weights from pretrain_nn.mat
    nn = sio.loadmat(path)
    w1 = nn['w1']
    w2 = nn['w2']
    w3 = nn['w3']
    w4 = nn['w4']
    w5 = nn['w5']
    w6 = nn['w6']
    w7 = nn['w7']
    w8 = nn['w8']
    b1 = nn['b1'][0]
    b2 = nn['b2'][0]
    b3 = nn['b3'][0]
    b4 = nn['b4'][0]
    b5 = nn['b5'][0]
    b6 = nn['b6'][0]
    b7 = nn['b7'][0]
    b8 = nn['b8'][0]

    layers = [
        (InputLayer, {'name': 'input', 'shape': (None, 1144)}),
        (DenseLayer, {'name': 'l1', 'num_units': 2000, 'nonlinearity': sigmoid, 'W': w1, 'b': b1}),
        (DenseLayer, {'name': 'l2', 'num_units': 1000, 'nonlinearity': sigmoid, 'W': w2, 'b': b2}),
        (DenseLayer, {'name': 'l3', 'num_units': 500, 'nonlinearity': sigmoid, 'W': w3, 'b': b3}),
        (DenseLayer, {'name': 'l4', 'num_units': 50, 'nonlinearity': linear, 'W': w4, 'b': b4}),
        (DenseLayer, {'name': 'l5', 'num_units': 500, 'nonlinearity': sigmoid, 'W': w5, 'b': b5}),
        (DenseLayer, {'name': 'l6', 'num_units': 1000, 'nonlinearity': sigmoid, 'W': w6, 'b': b6}),
        (DenseLayer, {'name': 'l7', 'num_units': 2000, 'nonlinearity': sigmoid, 'W': w7, 'b': b7}),
        (DenseLayer, {'name': 'output', 'num_units': 1144, 'nonlinearity': linear, 'W': w8, 'b': b8}),
    ]

    dbn = NeuralNet(
        layers=layers,
        max_epochs=30,
        objective_loss_function=squared_error,
        update=nesterov_momentum,
        regression=True,
        verbose=1,
        update_learning_rate=0.001,
        update_momentum=0.05,
        objective_l2=0.005,
    )
    return dbn

bimodal_diff_image.py 文件源码项目：ip-avsr 作者: lzuwei 项目源码文件源码阅读 21 收藏 0 点赞 0 评论 0

def load_dbn(path='models/avletters_ae.mat'):
    """
    load a pretrained dbn from path
    :param path: path to the .mat dbn
    :return: pretrained deep belief network
    """
    # create the network using weights from pretrain_nn.mat
    nn = sio.loadmat(path)
    w1 = nn['w1']
    w2 = nn['w2']
    w3 = nn['w3']
    w4 = nn['w4']
    w5 = nn['w5']
    w6 = nn['w6']
    w7 = nn['w7']
    w8 = nn['w8']
    b1 = nn['b1'][0]
    b2 = nn['b2'][0]
    b3 = nn['b3'][0]
    b4 = nn['b4'][0]
    b5 = nn['b5'][0]
    b6 = nn['b6'][0]
    b7 = nn['b7'][0]
    b8 = nn['b8'][0]

    layers = [
        (InputLayer, {'name': 'input', 'shape': (None, 1200)}),
        (DenseLayer, {'name': 'l1', 'num_units': 1000, 'nonlinearity': sigmoid, 'W': w1, 'b': b1}),
        (DenseLayer, {'name': 'l2', 'num_units': 1000, 'nonlinearity': sigmoid, 'W': w2, 'b': b2}),
        (DenseLayer, {'name': 'l3', 'num_units': 1000, 'nonlinearity': sigmoid, 'W': w3, 'b': b3}),
        (DenseLayer, {'name': 'l4', 'num_units': 50, 'nonlinearity': linear, 'W': w4, 'b': b4}),
        (DenseLayer, {'name': 'l5', 'num_units': 1000, 'nonlinearity': sigmoid, 'W': w5, 'b': b5}),
        (DenseLayer, {'name': 'l6', 'num_units': 1000, 'nonlinearity': sigmoid, 'W': w6, 'b': b6}),
        (DenseLayer, {'name': 'l7', 'num_units': 1000, 'nonlinearity': sigmoid, 'W': w7, 'b': b7}),
        (DenseLayer, {'name': 'output', 'num_units': 1200, 'nonlinearity': linear, 'W': w8, 'b': b8}),
    ]

    dbn = NeuralNet(
        layers=layers,
        max_epochs=30,
        objective_loss_function=squared_error,
        update=nesterov_momentum,
        regression=True,
        verbose=1,
        update_learning_rate=0.001,
        update_momentum=0.05,
        objective_l2=0.005,
    )
    return dbn

bimodal.py 文件源码项目：ip-avsr 作者: lzuwei 项目源码文件源码阅读 26 收藏 0 点赞 0 评论 0

def load_dbn(path='models/avletters_ae.mat'):
    """
    load a pretrained dbn from path
    :param path: path to the .mat dbn
    :return: pretrained deep belief network
    """
    # create the network using weights from pretrain_nn.mat
    nn = sio.loadmat(path)
    w1 = nn['w1']
    w2 = nn['w2']
    w3 = nn['w3']
    w4 = nn['w4']
    w5 = nn['w5']
    w6 = nn['w6']
    w7 = nn['w7']
    w8 = nn['w8']
    b1 = nn['b1'][0]
    b2 = nn['b2'][0]
    b3 = nn['b3'][0]
    b4 = nn['b4'][0]
    b5 = nn['b5'][0]
    b6 = nn['b6'][0]
    b7 = nn['b7'][0]
    b8 = nn['b8'][0]

    layers = [
        (InputLayer, {'name': 'input', 'shape': (None, 1200)}),
        (DenseLayer, {'name': 'l1', 'num_units': 2000, 'nonlinearity': rectify, 'W': w1, 'b': b1}),
        (DenseLayer, {'name': 'l2', 'num_units': 1000, 'nonlinearity': rectify, 'W': w2, 'b': b2}),
        (DenseLayer, {'name': 'l3', 'num_units': 500, 'nonlinearity': rectify, 'W': w3, 'b': b3}),
        (DenseLayer, {'name': 'l4', 'num_units': 50, 'nonlinearity': linear, 'W': w4, 'b': b4}),
        (DenseLayer, {'name': 'l5', 'num_units': 500, 'nonlinearity': rectify, 'W': w5, 'b': b5}),
        (DenseLayer, {'name': 'l6', 'num_units': 1000, 'nonlinearity': rectify, 'W': w6, 'b': b6}),
        (DenseLayer, {'name': 'l7', 'num_units': 2000, 'nonlinearity': rectify, 'W': w7, 'b': b7}),
        (DenseLayer, {'name': 'output', 'num_units': 1200, 'nonlinearity': linear, 'W': w8, 'b': b8}),
    ]

    dbn = NeuralNet(
        layers=layers,
        max_epochs=30,
        objective_loss_function=squared_error,
        update=nesterov_momentum,
        regression=True,
        verbose=1,
        update_learning_rate=0.001,
        update_momentum=0.05,
        objective_l2=0.005,
    )
    return dbn

confusion_visualizer.py 文件源码项目：ip-avsr 作者: lzuwei 项目源码文件源码阅读 22 收藏 0 点赞 0 评论 0

def load_dbn(path='models/avletters_ae.mat'):
    """
    load a pretrained dbn from path
    :param path: path to the .mat dbn
    :return: pretrained deep belief network
    """
    # create the network using weights from pretrain_nn.mat
    nn = sio.loadmat(path)
    w1 = nn['w1']
    w2 = nn['w2']
    w3 = nn['w3']
    w4 = nn['w4']
    w5 = nn['w5']
    w6 = nn['w6']
    w7 = nn['w7']
    w8 = nn['w8']
    b1 = nn['b1'][0]
    b2 = nn['b2'][0]
    b3 = nn['b3'][0]
    b4 = nn['b4'][0]
    b5 = nn['b5'][0]
    b6 = nn['b6'][0]
    b7 = nn['b7'][0]
    b8 = nn['b8'][0]

    layers = [
        (InputLayer, {'name': 'input', 'shape': (None, 1200)}),
        (DenseLayer, {'name': 'l1', 'num_units': 1000, 'nonlinearity': sigmoid, 'W': w1, 'b': b1}),
        (DenseLayer, {'name': 'l2', 'num_units': 1000, 'nonlinearity': sigmoid, 'W': w2, 'b': b2}),
        (DenseLayer, {'name': 'l3', 'num_units': 1000, 'nonlinearity': sigmoid, 'W': w3, 'b': b3}),
        (DenseLayer, {'name': 'l4', 'num_units': 50, 'nonlinearity': linear, 'W': w4, 'b': b4}),
        (DenseLayer, {'name': 'l5', 'num_units': 1000, 'nonlinearity': sigmoid, 'W': w5, 'b': b5}),
        (DenseLayer, {'name': 'l6', 'num_units': 1000, 'nonlinearity': sigmoid, 'W': w6, 'b': b6}),
        (DenseLayer, {'name': 'l7', 'num_units': 1000, 'nonlinearity': sigmoid, 'W': w7, 'b': b7}),
        (DenseLayer, {'name': 'output', 'num_units': 1200, 'nonlinearity': linear, 'W': w8, 'b': b8}),
    ]

    dbn = NeuralNet(
        layers=layers,
        max_epochs=30,
        objective_loss_function=squared_error,
        update=nesterov_momentum,
        regression=True,
        verbose=1,
        update_learning_rate=0.001,
        update_momentum=0.05,
        objective_l2=0.005,
    )
    return dbn

ae_finetuner.py 文件源码项目：ip-avsr 作者: lzuwei 项目源码文件源码阅读 24 收藏 0 点赞 0 评论 0

def load_ae_encoder(path, nonlinearity=sigmoid):
    nn = sio.loadmat(path)
    w1 = nn['w1']
    w2 = nn['w2']
    w3 = nn['w3']
    w4 = nn['w4']
    b1 = nn['b1'][0]
    b2 = nn['b2'][0]
    b3 = nn['b3'][0]
    b4 = nn['b4'][0]

    layers = [
        (InputLayer, {'name': 'input', 'shape': (None, 1500)}),
        (DenseLayer, {'name': 'l1', 'num_units': 2000, 'nonlinearity': nonlinearity, 'W': w1, 'b': b1}),
        (DenseLayer, {'name': 'l2', 'num_units': 1000, 'nonlinearity': nonlinearity, 'W': w2, 'b': b2}),
        (DenseLayer, {'name': 'l3', 'num_units': 500, 'nonlinearity': nonlinearity, 'W': w3, 'b': b3}),
        (DenseLayer, {'name': 'l4', 'num_units': 50, 'nonlinearity': linear, 'W': w4, 'b': b4})
    ]

    '''
    dbn = NeuralNet(
        layers=layers,
        max_epochs=30,
        objective_loss_function=squared_error,
        update=nesterov_momentum,
        regression=True,
        verbose=1,
        update_learning_rate=0.001,
        update_momentum=0.05,
        objective_l2=0.005,
    )
    '''

    dbn = NeuralNet(
        layers=layers,
        max_epochs=10,
        objective_loss_function=squared_error,
        update=adadelta,
        regression=True,
        verbose=1,
        update_learning_rate=0.01,
        # update_learning_rate=0.001,
        # update_momentum=0.05,
        objective_l2=0.005,
    )
    return dbn

trimodal_with_val.py 文件源码项目：ip-avsr 作者: lzuwei 项目源码文件源码阅读 19 收藏 0 点赞 0 评论 0

def load_dbn(path='models/cuave_ae.mat'):
    """
    load a pretrained dbn from path
    :param path: path to the .mat dbn
    :return: pretrained deep belief network
    """
    # create the network using weights from pretrain_nn.mat
    nn = sio.loadmat(path)
    w1 = nn['w1']
    w2 = nn['w2']
    w3 = nn['w3']
    w4 = nn['w4']
    w5 = nn['w5']
    w6 = nn['w6']
    w7 = nn['w7']
    w8 = nn['w8']
    b1 = nn['b1'][0]
    b2 = nn['b2'][0]
    b3 = nn['b3'][0]
    b4 = nn['b4'][0]
    b5 = nn['b5'][0]
    b6 = nn['b6'][0]
    b7 = nn['b7'][0]
    b8 = nn['b8'][0]

    layers = [
        (InputLayer, {'name': 'input', 'shape': (None, 1500)}),
        (DenseLayer, {'name': 'l1', 'num_units': 2000, 'nonlinearity': sigmoid, 'W': w1, 'b': b1}),
        (DenseLayer, {'name': 'l2', 'num_units': 1000, 'nonlinearity': sigmoid, 'W': w2, 'b': b2}),
        (DenseLayer, {'name': 'l3', 'num_units': 500, 'nonlinearity': sigmoid, 'W': w3, 'b': b3}),
        (DenseLayer, {'name': 'l4', 'num_units': 50, 'nonlinearity': linear, 'W': w4, 'b': b4}),
        (DenseLayer, {'name': 'l5', 'num_units': 500, 'nonlinearity': sigmoid, 'W': w5, 'b': b5}),
        (DenseLayer, {'name': 'l6', 'num_units': 1000, 'nonlinearity': sigmoid, 'W': w6, 'b': b6}),
        (DenseLayer, {'name': 'l7', 'num_units': 2000, 'nonlinearity': sigmoid, 'W': w7, 'b': b7}),
        (DenseLayer, {'name': 'output', 'num_units': 1500, 'nonlinearity': linear, 'W': w8, 'b': b8}),
    ]

    dbn = NeuralNet(
        layers=layers,
        max_epochs=30,
        objective_loss_function=squared_error,
        update=nesterov_momentum,
        regression=True,
        verbose=1,
        update_learning_rate=0.001,
        update_momentum=0.05,
        objective_l2=0.005,
    )
    return dbn