Python regularizers.l1l2方法代码示例

# 需要导入模块: from keras import regularizers [as 别名]
# 或者: from keras.regularizers import l1l2 [as 别名]
def model_discriminator(latent_dim, input_shape, output_dim=1, hidden_dim=1024,
                        reg=lambda: l1l2(1e-4, 1e-4), batch_norm_mode=1):
    z = Input((latent_dim,))
    x = Input(input_shape, name="x")
    h = merge([z, Flatten()(x)], mode='concat')
    h = Dense(hidden_dim, name="discriminator_h1", W_regularizer=reg())(h)
    h = BatchNormalization(mode=batch_norm_mode)(h)
    h = LeakyReLU(0.2)(h)
    h = Dropout(0.5)(h)
    h = Dense(hidden_dim / 2, name="discriminator_h2", W_regularizer=reg())(h)
    h = BatchNormalization(mode=batch_norm_mode)(h)
    h = LeakyReLU(0.2)(h)
    h = Dropout(0.5)(h)
    h = Dense(hidden_dim / 4, name="discriminator_h3", W_regularizer=reg())(h)
    h = BatchNormalization(mode=batch_norm_mode)(h)
    h = LeakyReLU(0.2)(h)
    h = Dropout(0.5)(h)
    y = Dense(output_dim, name="discriminator_y", activation="sigmoid", W_regularizer=reg())(h)
    return Model([z, x], y, name="discriminator") 

# 需要导入模块: from keras import regularizers [as 别名]
# 或者: from keras.regularizers import l1l2 [as 别名]
def test_W_reg(self):
        for reg in [regularizers.identity(), regularizers.l1(), regularizers.l2(), regularizers.l1l2()]:
            model = create_model(weight_reg=reg)
            model.compile(loss='categorical_crossentropy', optimizer='rmsprop')
            model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch, verbose=0)
            model.evaluate(X_test[test_ids, :], Y_test[test_ids, :], verbose=0) 

# 需要导入模块: from keras import regularizers [as 别名]
# 或者: from keras.regularizers import l1l2 [as 别名]
def compile_model(self):
        '''
        compiles standard single model with 4 convolitional/max-pooling layers.
        '''
        print 'Compiling single model...'
        single = Sequential()

        single.add(Convolution2D(self.n_filters[0], self.k_dims[0], self.k_dims[0], border_mode='valid', W_regularizer=l1l2(l1=self.w_reg, l2=self.w_reg), input_shape=(self.n_chan,33,33)))
        single.add(Activation(self.activation))
        single.add(BatchNormalization(mode=0, axis=1))
        single.add(MaxPooling2D(pool_size=(2,2), strides=(1,1)))
        single.add(Dropout(0.5))
        single.add(Convolution2D(self.n_filters[1], self.k_dims[1], self.k_dims[1], activation=self.activation, border_mode='valid', W_regularizer=l1l2(l1=self.w_reg, l2=self.w_reg)))
        single.add(BatchNormalization(mode=0, axis=1))
        single.add(MaxPooling2D(pool_size=(2,2), strides=(1,1)))
        single.add(Dropout(0.5))
        single.add(Convolution2D(self.n_filters[2], self.k_dims[2], self.k_dims[2], activation=self.activation, border_mode='valid', W_regularizer=l1l2(l1=self.w_reg, l2=self.w_reg)))
        single.add(BatchNormalization(mode=0, axis=1))
        single.add(MaxPooling2D(pool_size=(2,2), strides=(1,1)))
        single.add(Dropout(0.5))
        single.add(Convolution2D(self.n_filters[3], self.k_dims[3], self.k_dims[3], activation=self.activation, border_mode='valid', W_regularizer=l1l2(l1=self.w_reg, l2=self.w_reg)))
        single.add(Dropout(0.25))

        single.add(Flatten())
        single.add(Dense(5))
        single.add(Activation('softmax'))

        sgd = SGD(lr=0.001, decay=0.01, momentum=0.9)
        single.compile(loss='categorical_crossentropy', optimizer='sgd')
        print 'Done.'
        return single 

# 需要导入模块: from keras import regularizers [as 别名]
# 或者: from keras.regularizers import l1l2 [as 别名]
def comp_two_path(self):
        '''
        compiles two-path model, takes in a 4x33x33 patch and assesses global and local paths, then merges the results.
        '''
        print 'Compiling two-path model...'
        model = Graph()
        model.add_input(name='input', input_shape=(self.n_chan, 33, 33))

        # local pathway, first convolution/pooling
        model.add_node(Convolution2D(64, 7, 7, border_mode='valid', activation='relu', W_regularizer=l1l2(l1=0.01, l2=0.01)), name='local_c1', input= 'input')
        model.add_node(MaxPooling2D(pool_size=(4,4), strides=(1,1), border_mode='valid'), name='local_p1', input='local_c1')

        # local pathway, second convolution/pooling
        model.add_node(Dropout(0.5), name='drop_lp1', input='local_p1')
        model.add_node(Convolution2D(64, 3, 3, border_mode='valid', activation='relu', W_regularizer=l1l2(l1=0.01, l2=0.01)), name='local_c2', input='drop_lp1')
        model.add_node(MaxPooling2D(pool_size=(2,2), strides=(1,1), border_mode='valid'), name='local_p2', input='local_c2')

        # global pathway
        model.add_node(Convolution2D(160, 13, 13, border_mode='valid', activation='relu', W_regularizer=l1l2(l1=0.01, l2=0.01)), name='global', input='input')

        # merge local and global pathways
        model.add_node(Dropout(0.5), name='drop_lp2', input='local_p2')
        model.add_node(Dropout(0.5), name='drop_g', input='global')
        model.add_node(Convolution2D(5, 21, 21, border_mode='valid', activation='relu',  W_regularizer=l1l2(l1=0.01, l2=0.01)), name='merge', inputs=['drop_lp2', 'drop_g'], merge_mode='concat', concat_axis=1)

        # Flatten output of 5x1x1 to 1x5, perform softmax
        model.add_node(Flatten(), name='flatten', input='merge')
        model.add_node(Dense(5, activation='softmax'), name='dense_output', input='flatten')
        model.add_output(name='output', input='dense_output')

        sgd = SGD(lr=0.005, decay=0.1, momentum=0.9)
        model.compile('sgd', loss={'output':'categorical_crossentropy'})
        print 'Done.'
        return model 

# 需要导入模块: from keras import regularizers [as 别名]
# 或者: from keras.regularizers import l1l2 [as 别名]
def comp_double(self):
        '''
        double model. Simialar to two-pathway, except takes in a 4x33x33 patch and it's center 4x5x5 patch. merges paths at flatten layer.
        '''
        print 'Compiling double model...'
        single = Sequential()
        single.add(Convolution2D(64, 7, 7, border_mode='valid', W_regularizer=l1l2(l1=0.01, l2=0.01), input_shape=(4,33,33)))
        single.add(Activation('relu'))
        single.add(BatchNormalization(mode=0, axis=1))
        single.add(MaxPooling2D(pool_size=(2,2), strides=(1,1)))
        single.add(Dropout(0.5))
        single.add(Convolution2D(nb_filter=128, nb_row=5, nb_col=5, activation='relu', border_mode='valid', W_regularizer=l1l2(l1=0.01, l2=0.01)))
        single.add(BatchNormalization(mode=0, axis=1))
        single.add(MaxPooling2D(pool_size=(2,2), strides=(1,1)))
        single.add(Dropout(0.5))
        single.add(Convolution2D(nb_filter=256, nb_row=5, nb_col=5, activation='relu', border_mode='valid', W_regularizer=l1l2(l1=0.01, l2=0.01)))
        single.add(BatchNormalization(mode=0, axis=1))
        single.add(MaxPooling2D(pool_size=(2,2), strides=(1,1)))
        single.add(Dropout(0.5))
        single.add(Convolution2D(nb_filter=128, nb_row=3, nb_col=3, activation='relu', border_mode='valid', W_regularizer=l1l2(l1=0.01, l2=0.01)))
        single.add(Dropout(0.25))
        single.add(Flatten())

        # add small patch to train on
        five = Sequential()
        five.add(Reshape((100,1), input_shape = (4,5,5)))
        five.add(Flatten())
        five.add(MaxoutDense(128, nb_feature=5))
        five.add(Dropout(0.5))

        model = Sequential()
        # merge both paths
        model.add(Merge([five, single], mode='concat', concat_axis=1))
        model.add(Dense(5))
        model.add(Activation('softmax'))

        sgd = SGD(lr=0.001, decay=0.01, momentum=0.9)
        model.compile(loss='categorical_crossentropy', optimizer='sgd')
        print 'Done.'
        return model