Python core.Dense方法代码示例

# 需要导入模块: from keras.layers import core [as 别名]
# 或者: from keras.layers.core import Dense [as 别名]
def deep_mlp(self):
        """
        Deep Multilayer Perceptrop.
        """
        if self._config.num_mlp_layers == 0:
            self.add(Dropout(0.5))
        else:
            for j in xrange(self._config.num_mlp_layers):
                self.add(Dense(self._config.mlp_hidden_dim))
                if self._config.mlp_activation == 'elu':
                    self.add(ELU())
                elif self._config.mlp_activation == 'leaky_relu':
                    self.add(LeakyReLU())
                elif self._config.mlp_activation == 'prelu':
                    self.add(PReLU())
                else:
                    self.add(Activation(self._config.mlp_activation))
                self.add(Dropout(0.5)) 

# 需要导入模块: from keras.layers import core [as 别名]
# 或者: from keras.layers.core import Dense [as 别名]
def create(self):

        assert self._config.textual_embedding_dim == 0, \
                'Embedding cannot be learnt but must be fixed'

        language_forward = Sequential()
        language_forward.add(self._config.recurrent_encoder(
            self._config.hidden_state_dim, return_sequences=False,
            input_shape=(self._config.max_input_time_steps, self._config.input_dim)))
        self.language_forward = language_forward

        language_backward = Sequential()
        language_backward.add(self._config.recurrent_encoder(
            self._config.hidden_state_dim, return_sequences=False,
            go_backwards=True,
            input_shape=(self._config.max_input_time_steps, self._config.input_dim)))
        self.language_backward = language_backward

        self.add(Merge([language_forward, language_backward]))
        self.deep_mlp()
        self.add(Dense(self._config.output_dim))
        self.add(Activation('softmax')) 

# 需要导入模块: from keras.layers import core [as 别名]
# 或者: from keras.layers.core import Dense [as 别名]
def setUp(self):
        iris = load_iris()

        theano.config.floatX = 'float32'
        X = iris.data.astype(theano.config.floatX)
        y = iris.target.astype(np.int32)
        y_ohe = np_utils.to_categorical(y)

        model = Sequential()
        model.add(Dense(input_dim=X.shape[1], output_dim=5, activation='tanh'))
        model.add(Dense(input_dim=5, output_dim=y_ohe.shape[1], activation='sigmoid'))
        model.compile(loss='categorical_crossentropy', optimizer='sgd')
        model.fit(X, y_ohe, nb_epoch=10, batch_size=1, verbose=3, validation_data=None)

        params = {'copyright': 'Václav Čadek', 'model_name': 'Iris Model'}
        self.model = model
        self.pmml = keras2pmml(self.model, **params)
        self.num_inputs = self.model.input_shape[1]
        self.num_outputs = self.model.output_shape[1]
        self.num_connection_layers = len(self.model.layers)
        self.features = ['x{}'.format(i) for i in range(self.num_inputs)]
        self.class_values = ['y{}'.format(i) for i in range(self.num_outputs)] 

# 需要导入模块: from keras.layers import core [as 别名]
# 或者: from keras.layers.core import Dense [as 别名]
def get_residual_model(is_mnist=True, img_channels=1, img_rows=28, img_cols=28):
    model = keras.models.Sequential()
    first_layer_channel = 128
    if is_mnist: # size to be changed to 32,32
        model.add(ZeroPadding2D((2,2), input_shape=(img_channels, img_rows, img_cols))) # resize (28,28)-->(32,32)
        # the first conv 
        model.add(Convolution2D(first_layer_channel, 3, 3, border_mode='same'))
    else:
        model.add(Convolution2D(first_layer_channel, 3, 3, border_mode='same', input_shape=(img_channels, img_rows, img_cols)))

    model.add(Activation('relu'))
    # [residual-based Conv layers]
    residual_blocks = design_for_residual_blocks(num_channel_input=first_layer_channel)
    model.add(residual_blocks)
    model.add(BatchNormalization(axis=1))
    model.add(Activation('relu'))
    # [Classifier]    
    model.add(Flatten())
    model.add(Dense(nb_classes))
    model.add(Activation('softmax'))
    # [END]
    return model 

# 需要导入模块: from keras.layers import core [as 别名]
# 或者: from keras.layers.core import Dense [as 别名]
def model_create(input_shape, num_classes):
        logging.debug('input_shape {}'.format(input_shape))

        model = Sequential()

        model.add(Conv2D(32, (3, 3), border_mode='same', input_shape=input_shape))
        model.add(Activation('relu'))

        model.add(Conv2D(32, (3, 3)))
        model.add(Activation('relu'))
        model.add(MaxPooling2D(pool_size=(2, 2)))
        model.add(Dropout(0.5))

        model.add(Flatten())
        model.add(Dense(128))
        model.add(Activation('relu'))
        model.add(Dropout(0.5))

        model.add(Dense(num_classes))
        model.add(Activation('softmax'))

        # use binary_crossentropy if has just 2 prediction yes or no
        model.compile(loss='categorical_crossentropy', optimizer='adadelta', metrics=['accuracy'])

        return model 

# 需要导入模块: from keras.layers import core [as 别名]
# 或者: from keras.layers.core import Dense [as 别名]
def test_1o_1i(self):
        print('test a non-sequential graph with 1 input and 1 output')
        graph = Graph()
        graph.add_input(name='input1', ndim=2)

        graph.add_node(Dense(32, 16), name='dense1', input='input1')
        graph.add_node(Dense(32, 4), name='dense2', input='input1')
        graph.add_node(Dense(16, 4), name='dense3', input='dense1')

        graph.add_output(name='output1', inputs=['dense2', 'dense3'], merge_mode='sum')
        graph.compile('rmsprop', {'output1': 'mse'})

        history = graph.fit({'input1': X_train, 'output1': y_train}, nb_epoch=10)
        out = graph.predict({'input1': X_test})
        assert(type(out == dict))
        assert(len(out) == 1)
        loss = graph.test_on_batch({'input1': X_test, 'output1': y_test})
        loss = graph.train_on_batch({'input1': X_test, 'output1': y_test})
        loss = graph.evaluate({'input1': X_test, 'output1': y_test})
        print(loss)
        assert(loss < 2.5) 

# 需要导入模块: from keras.layers import core [as 别名]
# 或者: from keras.layers.core import Dense [as 别名]
def test_1o_1i_2(self):
        print('test a more complex non-sequential graph with 1 input and 1 output')
        graph = Graph()
        graph.add_input(name='input1', ndim=2)

        graph.add_node(Dense(32, 16), name='dense1', input='input1')
        graph.add_node(Dense(32, 4), name='dense2-0', input='input1')
        graph.add_node(Activation('relu'), name='dense2', input='dense2-0')

        graph.add_node(Dense(4, 16), name='dense3', input='dense2')
        graph.add_node(Dense(16, 4), name='dense4', inputs=['dense1', 'dense3'], merge_mode='sum')

        graph.add_output(name='output1', inputs=['dense2', 'dense4'], merge_mode='sum')
        graph.compile('rmsprop', {'output1': 'mse'})

        history = graph.fit({'input1': X_train, 'output1': y_train}, nb_epoch=10)
        out = graph.predict({'input1': X_train})
        assert(type(out == dict))
        assert(len(out) == 1)
        loss = graph.test_on_batch({'input1': X_test, 'output1': y_test})
        loss = graph.train_on_batch({'input1': X_test, 'output1': y_test})
        loss = graph.evaluate({'input1': X_test, 'output1': y_test})
        print(loss)
        assert(loss < 2.5)
        graph.get_config(verbose=1) 

# 需要导入模块: from keras.layers import core [as 别名]
# 或者: from keras.layers.core import Dense [as 别名]
def test_1o_2i(self):
        print('test a non-sequential graph with 2 inputs and 1 output')
        graph = Graph()
        graph.add_input(name='input1', ndim=2)
        graph.add_input(name='input2', ndim=2)

        graph.add_node(Dense(32, 16), name='dense1', input='input1')
        graph.add_node(Dense(32, 4), name='dense2', input='input2')
        graph.add_node(Dense(16, 4), name='dense3', input='dense1')

        graph.add_output(name='output1', inputs=['dense2', 'dense3'], merge_mode='sum')
        graph.compile('rmsprop', {'output1': 'mse'})

        history = graph.fit({'input1': X_train, 'input2': X2_train, 'output1': y_train}, nb_epoch=10)
        out = graph.predict({'input1': X_test, 'input2': X2_test})
        assert(type(out == dict))
        assert(len(out) == 1)
        loss = graph.test_on_batch({'input1': X_test, 'input2': X2_test, 'output1': y_test})
        loss = graph.train_on_batch({'input1': X_test, 'input2': X2_test, 'output1': y_test})
        loss = graph.evaluate({'input1': X_test, 'input2': X2_test, 'output1': y_test})
        print(loss)
        assert(loss < 3.0)
        graph.get_config(verbose=1) 

# 需要导入模块: from keras.layers import core [as 别名]
# 或者: from keras.layers.core import Dense [as 别名]
def test_recursive(self):
        print('test layer-like API')

        graph = containers.Graph()
        graph.add_input(name='input1', ndim=2)
        graph.add_node(Dense(32, 16), name='dense1', input='input1')
        graph.add_node(Dense(32, 4), name='dense2', input='input1')
        graph.add_node(Dense(16, 4), name='dense3', input='dense1')
        graph.add_output(name='output1', inputs=['dense2', 'dense3'], merge_mode='sum')

        seq = Sequential()
        seq.add(Dense(32, 32, name='first_seq_dense'))
        seq.add(graph)
        seq.add(Dense(4, 4, name='last_seq_dense'))

        seq.compile('rmsprop', 'mse')

        history = seq.fit(X_train, y_train, batch_size=10, nb_epoch=10)
        loss = seq.evaluate(X_test, y_test)
        print(loss)
        assert(loss < 2.5)

        loss = seq.evaluate(X_test, y_test, show_accuracy=True)
        pred = seq.predict(X_test)
        seq.get_config(verbose=1) 

# 需要导入模块: from keras.layers import core [as 别名]
# 或者: from keras.layers.core import Dense [as 别名]
def test_vector_clf(self):
        nb_hidden = 10

        print('vector classification data:')
        (X_train, y_train), (X_test, y_test) = get_test_data(nb_train=1000, nb_test=200, input_shape=(10,),
                                                             classification=True, nb_class=2)
        print('X_train:', X_train.shape)
        print('X_test:', X_test.shape)
        print('y_train:', y_train.shape)
        print('y_test:', y_test.shape)

        y_train = to_categorical(y_train)
        y_test = to_categorical(y_test)

        model = Sequential()
        model.add(Dense(X_train.shape[-1], nb_hidden))
        model.add(Activation('relu'))
        model.add(Dense(nb_hidden, y_train.shape[-1]))
        model.add(Activation('softmax'))
        model.compile(loss='categorical_crossentropy', optimizer='rmsprop')
        history = model.fit(X_train, y_train, nb_epoch=12, batch_size=16, validation_data=(X_test, y_test), show_accuracy=True, verbose=2)
        print(history.history)
        self.assertTrue(history.history['val_acc'][-1] > 0.9) 

# 需要导入模块: from keras.layers import core [as 别名]
# 或者: from keras.layers.core import Dense [as 别名]
def test_vector_reg(self):
        nb_hidden = 10
        print('vector regression data:')
        (X_train, y_train), (X_test, y_test) = get_test_data(nb_train=1000, nb_test=200, input_shape=(10,), output_shape=(2,),
                                                             classification=False)
        print('X_train:', X_train.shape)
        print('X_test:', X_test.shape)
        print('y_train:', y_train.shape)
        print('y_test:', y_test.shape)

        model = Sequential()
        model.add(Dense(X_train.shape[-1], nb_hidden))
        model.add(Activation('tanh'))
        model.add(Dense(nb_hidden, y_train.shape[-1]))
        model.compile(loss='hinge', optimizer='adagrad')
        history = model.fit(X_train, y_train, nb_epoch=12, batch_size=16, validation_data=(X_test, y_test), verbose=2)
        self.assertTrue(history.history['val_loss'][-1] < 0.9) 

# 需要导入模块: from keras.layers import core [as 别名]
# 或者: from keras.layers.core import Dense [as 别名]
def test_img_clf(self):
        print('image classification data:')
        (X_train, y_train), (X_test, y_test) = get_test_data(nb_train=1000, nb_test=200, input_shape=(3, 32, 32),
                                                             classification=True, nb_class=2)
        print('X_train:', X_train.shape)
        print('X_test:', X_test.shape)
        print('y_train:', y_train.shape)
        print('y_test:', y_test.shape)

        y_train = to_categorical(y_train)
        y_test = to_categorical(y_test)

        model = Sequential()
        model.add(Convolution2D(32, 3, 32, 32))
        model.add(Activation('sigmoid'))
        model.add(Flatten())
        model.add(Dense(32, y_test.shape[-1]))
        model.add(Activation('softmax'))
        model.compile(loss='categorical_crossentropy', optimizer='sgd')
        history = model.fit(X_train, y_train, nb_epoch=12, batch_size=16, validation_data=(X_test, y_test), show_accuracy=True, verbose=2)
        self.assertTrue(history.history['val_acc'][-1] > 0.9) 

# 需要导入模块: from keras.layers import core [as 别名]
# 或者: from keras.layers.core import Dense [as 别名]
def value_distribution_network(input_shape, num_atoms, action_size, learning_rate):
        """Model Value Distribution

        With States as inputs and output Probability Distributions for all Actions
        """

        state_input = Input(shape=(input_shape)) 
        cnn_feature = Convolution2D(32, 8, 8, subsample=(4,4), activation='relu')(state_input)
        cnn_feature = Convolution2D(64, 4, 4, subsample=(2,2), activation='relu')(cnn_feature)
        cnn_feature = Convolution2D(64, 3, 3, activation='relu')(cnn_feature)
        cnn_feature = Flatten()(cnn_feature)
        cnn_feature = Dense(512, activation='relu')(cnn_feature)

        distribution_list = []
        for i in range(action_size):
            distribution_list.append(Dense(num_atoms, activation='softmax')(cnn_feature))

        model = Model(input=state_input, output=distribution_list)

        adam = Adam(lr=learning_rate)
        model.compile(loss='categorical_crossentropy',optimizer=adam)

        return model 

# 需要导入模块: from keras.layers import core [as 别名]
# 或者: from keras.layers.core import Dense [as 别名]
def build_3dcnn_model(self, fusion_type, Fusion):
        if len(Fusion[0]) == 1: 
            input_shape = (32, 32, len(Fusion))
            model_in,model = self.cnn_2D(input_shape) 
        else:
            input_shape = (32, 32, 5, len(Fusion))
            model_in,model = self.cnn_3D(input_shape) 
        model = Dropout(0.5)(model)
        model = Dense(32, activation='relu', name = 'fc2')(model)
        model = Dense(self.config.classes, activation='softmax', name = 'fc3')(model) 
        model = Model(input=model_in,output=model)
        # 统计参数
        # model.summary()
        plot_model(model,to_file='experiments/img/' + str(Fusion) + fusion_type + r'_model.png',show_shapes=True)
        print('    Saving model  Architecture')
        
        adam = Adam(lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-8)
        # model.compile(optimizer=adam, loss=self.mycrossentropy, metrics=['accuracy']) #有改善，但不稳定
        model.compile(optimizer=adam, loss='categorical_crossentropy', metrics=['accuracy']) 
        
        return model 

# 需要导入模块: from keras.layers import core [as 别名]
# 或者: from keras.layers.core import Dense [as 别名]
def cnn_2D(self, input_shape, modual=''):
        #建立Sequential模型    
        model_in = Input(input_shape) 
        model = Conv2D(
                filters = 6,
                kernel_size = (3, 3),
                input_shape = input_shape,
                activation='relu',
                kernel_initializer='he_normal',
                name = modual+'conv1'
            )(model_in)# now 30x30x6
        model = MaxPooling2D(pool_size=(2,2))(model)# now 15x15x6
        model = Conv2D(
                filters = 8,
                kernel_size = (4, 4),
                activation='relu',
                kernel_initializer='he_normal',
                name = modual+'conv2'
            )(model)# now 12x12x8
        model = MaxPooling2D(pool_size=(2,2))(model)# now 6x6x8
        model = Flatten()(model)
        model = Dropout(0.5)(model)
        model_out = Dense(100, activation='relu', name = modual+'fc1')(model)
      
        return model_in, model_out