Python initializers.orthogonal方法代碼示例

本文整理匯總了Python中keras.initializers.orthogonal方法的典型用法代碼示例。如果您正苦於以下問題：Python initializers.orthogonal方法的具體用法？Python initializers.orthogonal怎麽用？Python initializers.orthogonal使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類keras.initializers的用法示例。

在下文中一共展示了initializers.orthogonal方法的13個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。

示例1: test_orthogonal

# 需要導入模塊: from keras import initializers [as 別名]
# 或者: from keras.initializers import orthogonal [as 別名]
def test_orthogonal(tensor_shape):
    _runner(initializers.orthogonal(), tensor_shape,
            target_mean=0.)

開發者ID:hello-sea，項目名稱:DeepLearning_Wavelet-LSTM，代碼行數:5，代碼來源:initializers_test.py

示例2: get_model

# 需要導入模塊: from keras import initializers [as 別名]
# 或者: from keras.initializers import orthogonal [as 別名]
def get_model(embed_weights):
    input_layer = Input(shape=(MAX_LEN, ), name='input')
    # 1. embedding layer
    # get embedding weights
    print('load pre-trained embedding weights ......')
    input_dim = embed_weights.shape[0]
    output_dim = embed_weights.shape[1]
    x = Embedding(
        input_dim=input_dim,
        output_dim=output_dim,
        weights=[embed_weights],
        trainable=False,
        name='embedding'
    )(input_layer)
    # clean up
    del embed_weights, input_dim, output_dim
    gc.collect()
    # 2. dropout
    x = SpatialDropout1D(rate=SPATIAL_DROPOUT)(x)
    # 3. bidirectional lstm
    x = Bidirectional(
        layer=CuDNNLSTM(RNN_UNITS, return_sequences=True,
                        kernel_initializer=glorot_normal(seed=1029),
                        recurrent_initializer=orthogonal(gain=1.0, seed=1029)),
        name='bidirectional_lstm')(x)
    # 4. capsule layer
    capsul = Capsule(num_capsule=10, dim_capsule=10, routings=4, share_weights=True)(x) # noqa
    capsul = Flatten()(capsul)
    capsul = DropConnect(Dense(32, activation="relu"), prob=0.01)(capsul)

    # 5. attention later
    atten = Attention(step_dim=MAX_LEN, name='attention')(x)
    atten = DropConnect(Dense(16, activation="relu"), prob=0.05)(atten)
    x = Concatenate(axis=-1)([capsul, atten])

    # 6. output (sigmoid)
    output_layer = Dense(units=1, activation='sigmoid', name='output')(x)
    model = Model(inputs=input_layer, outputs=output_layer)
    # compile model
    model.compile(loss='binary_crossentropy', optimizer='adam')
    return model

開發者ID:KevinLiao159，項目名稱:Quora，代碼行數:43，代碼來源:submission_v50.py

示例3: _build_fn_regressor

# 需要導入模塊: from keras import initializers [as 別名]
# 或者: from keras.initializers import orthogonal [as 別名]
def _build_fn_regressor(input_shape):
    model = Sequential(
        [
            Dense(100, activation="relu", input_shape=input_shape),
            Dense(Integer(40, 60), activation="relu", kernel_initializer="glorot_normal"),
            Dropout(Real(0.2, 0.7)),
            Dense(1, activation=Categorical(["relu", "sigmoid"]), kernel_initializer="orthogonal"),
        ]
    )
    model.compile(
        optimizer=Categorical(["adam", "rmsprop"]),
        loss="mean_absolute_error",
        metrics=["mean_absolute_error"],
    )
    return model

開發者ID:HunterMcGushion，項目名稱:hyperparameter_hunter，代碼行數:17，代碼來源:test_keras.py

示例4: _build_fn_glorot_normal_1

# 需要導入模塊: from keras import initializers [as 別名]
# 或者: from keras.initializers import orthogonal [as 別名]
def _build_fn_glorot_normal_1(input_shape):  # `"glorot_normal"`
    model = Sequential(
        [
            Dense(Integer(50, 100), input_shape=input_shape),
            Dense(1, kernel_initializer="glorot_normal"),
        ]
    )
    model.compile(optimizer="adam", loss="binary_crossentropy", metrics=["accuracy"])
    return model


#################### `orthogonal` - Excluding default (`Initializer`) ####################

開發者ID:HunterMcGushion，項目名稱:hyperparameter_hunter，代碼行數:14，代碼來源:test_keras.py