MyLayer.py

# encoding: utf-8
import tensorflow as tf
from keras.engine import Layer



def dot_product(x, kernel):
    """
    Wrapper for dot product operation, in order to be compatible with both
    Theano and Tensorflow
    Args:
        x (): input
        kernel (): weights
    Returns:
    """
    if K.backend() == 'tensorflow':
        return K.squeeze(K.dot(x, K.expand_dims(kernel)), axis=-1)
    else:
        return K.dot(x, kernel)


def squash(x, axis=-1):
    s_squared_norm = K.sum(K.square(x), axis, keepdims=True)
    scale = K.sqrt(s_squared_norm + K.epsilon())
    return x / scale

from keras.layers import merge
from keras.layers.core import *

import numpy as np


def get_activations(model, inputs, print_shape_only=False, layer_name=None):
    # Documentation is available online on Github at the address below.
    # From: https://github.com/philipperemy/keras-visualize-activations
    print('----- activations -----')
    activations = []
    inp = model.input
    if layer_name is None:
        outputs = [layer.output for layer in model.layers]
    else:
        outputs = [layer.output for layer in model.layers if layer.name == layer_name]  # all layer outputs
    funcs = [K.function([inp] + [K.learning_phase()], [out]) for out in outputs]  # evaluation functions
    layer_outputs = [func([inputs, 1.])[0] for func in funcs]
    for layer_activations in layer_outputs:
        activations.append(layer_activations)
        if print_shape_only:
            print(layer_activations.shape)
        else:
            print(layer_activations)
    return activations


def get_data(n, input_dim, attention_column=1):
    """
    Data generation. x is purely random except that it's first value equals the target y.
    In practice, the network should learn that the target = x[attention_column].
    Therefore, most of its attention should be focused on the value addressed by attention_column.
    :param n: the number of samples to retrieve.
    :param input_dim: the number of dimensions of each element in the series.
    :param attention_column: the column linked to the target. Everything else is purely random.
    :return: x: model inputs, y: model targets
    """
    x = np.random.standard_normal(size=(n, input_dim))
    y = np.random.randint(low=0, high=2, size=(n, 1))
    x[:, attention_column] = y[:, 0]
    return x, y


def get_data_recurrent(n, time_steps, input_dim, attention_column=10):
    """
    Data generation. x is purely random except that it's first value equals the target y.
    In practice, the network should learn that the target = x[attention_column].
    Therefore, most of its attention should be focused on the value addressed by attention_column.
    :param n: the number of samples to retrieve.
    :param time_steps: the number of time steps of your series.
    :param input_dim: the number of dimensions of each element in the series.
    :param attention_column: the column linked to the target. Everything else is purely random.
    :return: x: model inputs, y: model targets
    """
    x = np.random.standard_normal(size=(n, time_steps, input_dim))
    y = np.random.randint(low=0, high=2, size=(n, 1))
    x[:, attention_column, :] = np.tile(y[:], (1, input_dim))
    return x, y

class Multiply(Layer):
    def __init__(self, output_dim, **kwargs):
        self.output_dim = output_dim
        super(Multiply, self).__init__(**kwargs)

    def call(self, x):
        return tf.multiply(x[0], x[1])

    def compute_output_shape(self, input_shape):
        return input_shape[0]

class ImageEmbeding(Layer):

    def __init__(self, output_dim,img_weight, **kwargs):
        self.output_dim = output_dim
        self.img_weight = img_weight
        super(ImageEmbeding, self).__init__(**kwargs)

    def call(self, x):
        return tf.nn.embedding_lookup(self.img_weight, x)

    def compute_output_shape(self, input_shape):
        return (input_shape[0],)+self.output_dim


from keras import backend as K
from keras.engine.topology import Layer