Python keras.layers.advanced_activations 模块，SReLU() 实例源码

def test_srelu():
    from keras.layers.advanced_activations import SReLU
    layer_test(SReLU, kwargs={},
               input_shape=(2, 3, 4))

def buildFeatures(self, type='shared'):
        assert self.checkTensor('q-channels')
        assert self.checkTensor('a-channels')
        srelu = lambda name: SReLU(name=name)
        features = []
        if type == 'shared':
            q_features = self.linkFeature('q-channels', 'shared-convolution', activation='tanh')
            a_features = self.linkFeature('a-channels', 'shared-convolution', activation='tanh')
        else:
            raise Error('Not Supported')
        print('q-features', q_features._keras_shape, K.ndim(q_features))
        print('a-features', a_features._keras_shape, K.ndim(a_features))
        self.tensors['q-features'] = q_features
        self.tensors['a-features'] = a_features

def buildFeatures(self, type='shared'):
        assert self.checkTensor('q+')
        assert self.checkTensor('q-')
        assert self.checkTensor('a+')
        assert self.checkTensor('a-')
        srelu = lambda name: SReLU(name=name)
        if type == 'shared':
            q_features = self.doubleFeature('q+', 'q-', 'shared-convolution', activation=srelu)
            a_features = self.doubleFeature('a+', 'a-', 'shared-convolution', activation=srelu)
        else:
            raise Error('Not Supported')
        print('q-features', q_features._keras_shape)
        print('a-features', a_features._keras_shape)
        self.tensors['q-features'] = q_features
        self.tensors['a-features'] = a_features

def buildFeatures(self, type='shared'):
        assert self.checkTensor('q+')
        assert self.checkTensor('q-')
        assert self.checkTensor('a+')
        assert self.checkTensor('a-')
        srelu = lambda name: SReLU(name=name)
        features = []
        if type == 'shared':
            q_features = Merge(
                mode='concat',
                name='q-features',
            )([
                self.linkFeature('q+', 'shared-convolution', activation=srelu),
                self.linkFeature('q-', 'shared-convolution', activation=srelu)
            ])
            a_features = Merge(
                mode='concat',
                name='a-features',
            )([
                self.linkFeature('a+', 'shared-convolution', activation=srelu),
                self.linkFeature('a-', 'shared-convolution', activation=srelu)
            ])
        else:
            raise Error('Not Supported')
        self.tensors['q-features'] = q_features
        self.tensors['a-features'] = a_features

def test_srelu():
    from keras.layers.advanced_activations import SReLU
    layer_test(SReLU, kwargs={},
               input_shape=(2, 3, 4))

def test_srelu_share():
    from keras.layers.advanced_activations import SReLU
    layer_test(SReLU, kwargs={'shared_axes': 1},
               input_shape=(2, 3, 4))

def test_srelu():
    from keras.layers.advanced_activations import SReLU
    layer_test(SReLU, kwargs={},
               input_shape=(2, 3, 4))

def test_srelu_share():
    from keras.layers.advanced_activations import SReLU
    layer_test(SReLU, kwargs={'shared_axes': 1},
               input_shape=(2, 3, 4))

def create_model():
    # advanced activation not used yet
    srelu = advanced_activations.SReLU(
        t_left_init='zero', 
        a_left_init='glorot_uniform', 
        t_right_init='glorot_uniform', 
        a_right_init='one'
    )

    # create and return model
    model = Sequential()
    model.add(Dense(256, input_dim=input_dim, activation='sigmoid'))
    model.add(Dense(256, activation='sigmoid'))
    model.add(Dense(output_dim, activation='sigmoid'))
    return model

def build_model(X,dim=128):

    inputs_p = Input(shape=(1,), dtype='int32')

    embed_p = Embedding(
                    num_q,
                    dim,
                    dropout=0.2,
                    input_length=1
                    )(inputs_p)

    inputs_d = Input(shape=(1,), dtype='int32')

    embed_d = Embedding(
                    num_e,
                    dim,
                    dropout=0.2,
                    input_length=1
                    )(inputs_d)


    flatten_p= Flatten()(embed_p)

    flatten_d= Flatten()(embed_d)

    flatten = merge([
                flatten_p,
                flatten_d,
                ],mode='concat')

    fc1 = Dense(512)(flatten)
    fc1 = SReLU()(fc1)
    dp1 = Dropout(0.7)(fc1)

    outputs = Dense(1,activation='sigmoid',name='outputs')(dp1)

    inputs = [
                inputs_p,
                inputs_d,
            ]



    model = Model(input=inputs, output=outputs)
    nadam = Nadam()
    sgd = SGD(lr=1e-3, decay=1e-6, momentum=0.9, nesterov=True)
    model.compile(
                optimizer=nadam,
                loss= 'binary_crossentropy'
              )

    return model