This example demonstrates how to write custom layers for Keras.

我们构建了一个称为" Antirectifier"的自定义激活层,该层可以修改通过它的张量的形状. 我们需要指定两个方法: compute_output_shapecall .


由于我们的自定义层是使用Keras后端( K )中的基元编写的,因此我们的代码可以在TensorFlow和Theano上运行.

from __future__ import print_function
import keras
from keras.models import Sequential
from keras import layers
from keras.datasets import mnist
from keras import backend as K

class Antirectifier(layers.Layer):
    '''This is the combination of a sample-wise
    L2 normalization with the concatenation of the
    positive part of the input with the negative part
    of the input. The result is a tensor of samples that are
    twice as large as the input samples.

    It can be used in place of a ReLU.

    # Input shape
        2D tensor of shape (samples, n)

    # Output shape
        2D tensor of shape (samples, 2*n)

    # Theoretical justification
        When applying ReLU, assuming that the distribution
        of the previous output is approximately centered around 0.,
        you are discarding half of your input. This is inefficient.

        Antirectifier allows to return all-positive outputs like ReLU,
        without discarding any data.

        Tests on MNIST show that Antirectifier allows to train networks
        with twice less parameters yet with comparable
        classification accuracy as an equivalent ReLU-based network.

    def compute_output_shape(self, input_shape):
        shape = list(input_shape)
        assert len(shape) == 2  # only valid for 2D tensors
        shape[-1] *= 2
        return tuple(shape)

    def call(self, inputs):
        inputs -= K.mean(inputs, axis=1, keepdims=True)
        inputs = K.l2_normalize(inputs, axis=1)
        pos = K.relu(inputs)
        neg = K.relu(-inputs)
        return K.concatenate([pos, neg], axis=1)

# global parameters
batch_size = 128
num_classes = 10
epochs = 40

# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()

x_train = x_train.reshape(60000, 784)
x_test = x_test.reshape(10000, 784)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

# build the model
model = Sequential()
model.add(layers.Dense(256, input_shape=(784,)))

# compile the model

# train the model, y_train,
          validation_data=(x_test, y_test))

# next, compare with an equivalent network
# with2x bigger Dense layers and ReLU