Python engine.Input方法代码示例

# 需要导入模块: from keras import engine [as 别名]
# 或者: from keras.engine import Input [as 别名]
def build_encoder(config: BEGANConfig, name="encoder"):
    n_filters = config.n_filters
    hidden_size = config.hidden_size
    n_layer = config.n_layer_in_conv

    dx = image_input = Input((config.image_height, config.image_width, 3))

    # output: (N, 32, 32, n_filters)
    dx = convolution_image_for_encoding(dx, n_filters, strides=(2, 2), name="%s/L1" % name, n_layer=n_layer)

    # output: (N, 16, 16, n_filters*2)
    dx = convolution_image_for_encoding(dx, n_filters * 2, strides=(2, 2), name="%s/L2" % name, n_layer=n_layer)

    # output: (N, 8, 8, n_filters*3)
    dx = convolution_image_for_encoding(dx, n_filters * 3, strides=(2, 2), name="%s/L3" % name, n_layer=n_layer)

    # output: (N, 8, 8, n_filters*4)
    dx = convolution_image_for_encoding(dx, n_filters * 4, strides=(1, 1), name="%s/L4" % name, n_layer=n_layer)

    dx = Flatten()(dx)
    hidden = Dense(hidden_size, activation='linear', name="%s/Dense" % name)(dx)

    encoder = Container(image_input, hidden, name=name)
    return encoder 

# 需要导入模块: from keras import engine [as 别名]
# 或者: from keras.engine import Input [as 别名]
def build_discriminator(config: BEGANConfig, autoencoder: Container):
    """
    
    Keras Model class is able to have several inputs/outputs. 
    But, loss functions should be defined each other, and the loss function cannot reference other inputs/outputs.
    For computing loss, two inputs/outputs are concatenated.
    """
    # IN Shape: [ImageHeight, ImageWidth, (real data(3 channels) + generated data(3 channels))]
    in_out_shape = (config.image_height, config.image_width, 3 * 2)
    all_input = Input(in_out_shape)

    # Split Input Data
    data_input = Lambda(lambda x: x[:, :, :, 0:3], output_shape=(config.image_height, config.image_width, 3))(all_input)
    generator_input = Lambda(lambda x: x[:, :, :, 3:6], output_shape=(config.image_height, config.image_width, 3))(all_input)

    # use same autoencoder(weights are shared)
    data_output = autoencoder(data_input)  # (bs, row, col, ch)
    generator_output = autoencoder(generator_input)

    # concatenate output to be same shape of input
    all_output = Concatenate(axis=-1)([data_output, generator_output])

    discriminator = DiscriminatorModel(all_input, all_output, name="discriminator")
    return discriminator 

# 需要导入模块: from keras import engine [as 别名]
# 或者: from keras.engine import Input [as 别名]
def test_layer_call_arguments():
    # Test the ability to pass and serialize arguments to `call`.
    inp = layers.Input(shape=(2,))
    x = layers.Dense(3)(inp)
    x = layers.Dropout(0.5)(x, training=True)
    model = Model(inp, x)
    assert not model.uses_learning_phase

    # Test that argument is kept when applying the model
    inp2 = layers.Input(shape=(2,))
    out2 = model(inp2)
    assert not out2._uses_learning_phase

    # Test that argument is kept after loading a model
    config = model.get_config()
    model = Model.from_config(config)
    assert not model.uses_learning_phase 

# 需要导入模块: from keras import engine [as 别名]
# 或者: from keras.engine import Input [as 别名]
def test_recursion_with_bn_and_loss():
    model1 = Sequential([
        layers.Dense(5, input_dim=5, activity_regularizer='l1'),
        layers.BatchNormalization(),
        layers.Dense(5),
    ])

    print('NEW MODEL')
    inputs = layers.Input(shape=(5,))
    outputs = model1(inputs)
    model2 = Model(inputs=inputs, outputs=outputs)

    assert len(model1.updates) == 2
    assert len(model2.updates) == 2
    assert len(model1.losses) == 1
    assert len(model2.losses) == 1, model2.layers[1]._per_input_losses

    model1.compile(optimizer='sgd', loss='categorical_crossentropy')
    model2.compile(optimizer='sgd', loss='categorical_crossentropy')

    x = np.ones((3, 5))
    y = np.ones((3, 5))
    model1.fit(x, y, verbose=0, epochs=1)
    model2.fit(x, y, verbose=0, epochs=1) 

# 需要导入模块: from keras import engine [as 别名]
# 或者: from keras.engine import Input [as 别名]
def test_activity_regularization_with_model_composition():

    def reg(x):
        return K.sum(x)

    net_a_input = Input((2,))
    net_a = net_a_input
    net_a = Dense(2, kernel_initializer='ones',
                  use_bias=False,
                  activity_regularizer=reg)(net_a)
    model_a = Model([net_a_input], [net_a])

    net_b_input = Input((2,))
    net_b = model_a(net_b_input)
    model_b = Model([net_b_input], [net_b])

    model_b.compile(optimizer='sgd', loss=None)
    x = np.ones((1, 2))
    loss = model_b.evaluate(x)
    assert loss == 4 

# 需要导入模块: from keras import engine [as 别名]
# 或者: from keras.engine import Input [as 别名]
def test_shared_layer_depth_is_correct():
    # Basic outline here: we have a shared embedding layer, and two inputs that go through
    # different depths of computation in the graph before the final output.  We need the computed
    # depth of the input layers to be the same, because they both pass through the embedding layer
    # before anything else happens.  That's what we're testing.
    from keras.layers import Embedding, Input, Dense, Concatenate
    from keras.models import Model
    input1 = Input(shape=(10,), name='input1')
    input2 = Input(shape=(10,), name='input2')
    embedding_layer = Embedding(name='embedding', input_dim=5, output_dim=10)
    embedded_input1 = embedding_layer(input1)
    embedded_input2 = embedding_layer(input2)
    transformed_input2 = Dense(6)(Dense(5)(Dense(3)(embedded_input2)))
    final_output = Dense(2)(Concatenate()([embedded_input1, transformed_input2]))
    model = Model(inputs=[input1, input2], outputs=final_output)
    input1_depth = -1
    input2_depth = -1
    for depth, layers in model.layers_by_depth.items():
        for layer in layers:
            if layer.name == 'input1':
                input1_depth = depth
            if layer.name == 'input2':
                input2_depth = depth
    assert input1_depth != -1
    assert input1_depth == input2_depth 

# 需要导入模块: from keras import engine [as 别名]
# 或者: from keras.engine import Input [as 别名]
def test_layer_sharing_at_heterogeneous_depth():
    x_val = np.random.random((10, 5))

    x = Input(shape=(5,))
    A = Dense(5, name='A')
    B = Dense(5, name='B')
    output = A(B(A(B(x))))
    M = Model(x, output)

    output_val = M.predict(x_val)

    config = M.get_config()
    weights = M.get_weights()

    M2 = Model.from_config(config)
    M2.set_weights(weights)

    output_val_2 = M2.predict(x_val)
    np.testing.assert_allclose(output_val, output_val_2, atol=1e-6) 

# 需要导入模块: from keras import engine [as 别名]
# 或者: from keras.engine import Input [as 别名]
def test_layer_sharing_at_heterogeneous_depth_with_concat():
    input_shape = (16, 9, 3)
    input_layer = Input(shape=input_shape)

    A = Dense(3, name='dense_A')
    B = Dense(3, name='dense_B')
    C = Dense(3, name='dense_C')

    x1 = B(A(input_layer))
    x2 = A(C(input_layer))
    output = layers.concatenate([x1, x2])

    M = Model(inputs=input_layer, outputs=output)

    x_val = np.random.random((10, 16, 9, 3))
    output_val = M.predict(x_val)

    config = M.get_config()
    weights = M.get_weights()

    M2 = Model.from_config(config)
    M2.set_weights(weights)

    output_val_2 = M2.predict(x_val)
    np.testing.assert_allclose(output_val, output_val_2, atol=1e-6)