Python keras.initializers.Orthogonal() Examples

The following are 9 code examples of keras.initializers.Orthogonal(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module keras.initializers , or try the search function .
Example #1
Source File: va-rnn.py    From View-Adaptive-Neural-Networks-for-Skeleton-based-Human-Action-Recognition with MIT License 5 votes vote down vote up 
def creat_model(input_shape, num_class):

    init = initializers.Orthogonal(gain=args.norm)
    sequence_input =Input(shape=input_shape)
    mask = Masking(mask_value=0.)(sequence_input)
    if args.aug:
        mask = augmentaion()(mask)
    X = Noise(0.075)(mask)
    if args.model[0:2]=='VA':
        # VA
        trans = LSTM(args.nhid,recurrent_activation='sigmoid',return_sequences=True,implementation=2,recurrent_initializer=init)(X)
        trans = Dropout(0.5)(trans)
        trans = TimeDistributed(Dense(3,kernel_initializer='zeros'))(trans)
        rot = LSTM(args.nhid,recurrent_activation='sigmoid',return_sequences=True,implementation=2,recurrent_initializer=init)(X)
        rot = Dropout(0.5)(rot)
        rot = TimeDistributed(Dense(3,kernel_initializer='zeros'))(rot)
        transform = Concatenate()([rot,trans])
        X = VA()([mask,transform])

    X = LSTM(args.nhid,recurrent_activation='sigmoid',return_sequences=True,implementation=2,recurrent_initializer=init)(X)
    X = Dropout(0.5)(X)
    X = LSTM(args.nhid,recurrent_activation='sigmoid',return_sequences=True,implementation=2,recurrent_initializer=init)(X)
    X = Dropout(0.5)(X)
    X = LSTM(args.nhid,recurrent_activation='sigmoid',return_sequences=True,implementation=2,recurrent_initializer=init)(X)
    X = Dropout(0.5)(X)
    X = TimeDistributed(Dense(num_class))(X)
    X = MeanOverTime()(X)
    X = Activation('softmax')(X)

    model=Model(sequence_input,X)
    return model
Example #2
Source File: convaware.py    From keras-contrib with MIT License 5 votes vote down vote up 
def __init__(self, eps_std=0.05, seed=None):
        self.eps_std = eps_std
        self.seed = seed
        self.orthogonal = Orthogonal()
Example #3
Source File: initializers.py    From faceswap with GNU General Public License v3.0 5 votes vote down vote up 
def __init__(self, eps_std=0.05, seed=None, init=False):
        self._init = init
        self.eps_std = eps_std
        self.seed = seed
        self.orthogonal = initializers.Orthogonal()
        self.he_uniform = initializers.he_uniform()
Example #4
Source File: test_keras.py    From hyperparameter_hunter with MIT License 5 votes vote down vote up 
def _build_fn_orthogonal_e_1(input_shape):  # `Orthogonal(gain=Real(0.3, 0.9))`
    model = Sequential(
        [
            Dense(Integer(50, 100), input_shape=input_shape),
            Dense(1, kernel_initializer=Orthogonal(gain=Real(0.3, 0.9))),
        ]
    )
    model.compile(optimizer="adam", loss="binary_crossentropy", metrics=["accuracy"])
    return model
Example #5
Source File: test_keras.py    From hyperparameter_hunter with MIT License 5 votes vote down vote up 
def _build_fn_orthogonal_e_3(input_shape):  # `Orthogonal(gain=0.5)`
    model = Sequential(
        [
            Dense(Integer(50, 100), input_shape=input_shape),
            Dense(1, kernel_initializer=Orthogonal(gain=0.5)),
        ]
    )
    model.compile(optimizer="adam", loss="binary_crossentropy", metrics=["accuracy"])
    return model


#################### `orthogonal` - Including default (`Initializer`) ####################
Example #6
Source File: test_keras.py    From hyperparameter_hunter with MIT License 5 votes vote down vote up 
def _build_fn_orthogonal_i_2(input_shape):  # `Orthogonal()`
    model = Sequential(
        [
            Dense(Integer(50, 100), input_shape=input_shape),
            Dense(1, kernel_initializer=Orthogonal()),
        ]
    )
    model.compile(optimizer="adam", loss="binary_crossentropy", metrics=["accuracy"])
    return model
Example #7
Source File: test_keras.py    From hyperparameter_hunter with MIT License 5 votes vote down vote up 
def _build_fn_orthogonal_i_4(input_shape):  # `Orthogonal(gain=1.0)`
    model = Sequential(
        [
            Dense(Integer(50, 100), input_shape=input_shape),
            Dense(1, kernel_initializer=Orthogonal(gain=1.0)),
        ]
    )
    model.compile(optimizer="adam", loss="binary_crossentropy", metrics=["accuracy"])
    return model
Example #8
Source File: test_keras.py    From hyperparameter_hunter with MIT License 5 votes vote down vote up 
def _build_fn_orthogonal_i_6(input_shape):  # `Orthogonal(gain=Real(0.6, 1.6))`
    model = Sequential(
        [
            Dense(Integer(50, 100), input_shape=input_shape),
            Dense(1, kernel_initializer=Orthogonal(gain=Real(0.6, 1.6))),
        ]
    )
    model.compile(optimizer="adam", loss="binary_crossentropy", metrics=["accuracy"])
    return model


#################### Categorical Initializers ####################
Example #9
Source File: test_keras.py    From hyperparameter_hunter with MIT License 5 votes vote down vote up 
def _build_fn_categorical_4(input_shape):  # `Categorical(["glorot_normal", Orthogonal(gain=1)])`
    model = Sequential(
        [
            Dense(Integer(50, 100), input_shape=input_shape),
            Dense(1, kernel_initializer=Categorical(["glorot_normal", Orthogonal(gain=1)])),
        ]
    )
    model.compile(optimizer="adam", loss="binary_crossentropy", metrics=["accuracy"])
    return model