如何在 Keras 中构建这个自定义层? [英] How to build this custom layer in Keras?

问题描述

我正在构建一个支持复数的神经网络.目前正在研究复杂的激活.根据 Benjio 的一篇论文，这是一篇不错的论文:

I'm building a NN that supports complex numbers. Currently working on complex activation. According to a Benjio paper, this is a good one:

其中 b 是要学习的可训练参数.所以我正在构建一个特殊层来执行此激活.我是 Keras 的新手并且已经陷入困境.我在下面创建了这段代码，但它给出了构建函数的错误.我不知道发生了什么，我只是试图复制模板.请帮忙.

Where b is a trainable parameter to be learnt. So I'm building a special layer to do this activation. I'm new to Keras and stuck already. I created this code below, but it gives an error with the build function. I have no idea what's happening, I just tried to copy the template. Please help.

class modrelu(Layer):
    def __init__(self, **kwargs):
        super(modrelu, self).__init__(**kwargs)

    def build(self):
        self.b= K.variable(value=np.random.rand()-0.5, dtype='float64')
        super(modrelu, self).build()  # Be sure to call this at the end

    def call(self, x):
        assert isinstance(x, list)
        ip_r, ip_i = x
        comp= tf.complex(ip_r, ip_i ) 
        ABS= tf.math.abs(comp)
        ANG= tf.math.angle(comp)

        ABS= K.relu( self.b + ABS) 

        op_r=  ABS * K.sin(angle) #K.dot ??
        op_i= ABS * K.cos(angle)
        return [op_r, op_i]

    def compute_output_shape(self, input_shape):
        assert isinstance(input_shape, list)
        shape_a, shape_b = input_shape
        return [shape_a, shape_b]

对我的代码的评论:在 init 中我没有添加任何东西，因为它是一个激活层，实例化时不需要输入.

Comments on my code: In the init I didn't add anything, cause it is an activation layer that takes no input when instantiated.

在构建方法中，我尝试添加 b.不确定我是否应该使用 self.add_weight 方法.理想情况下，我希望 b 的数量与输入的维度一样多.

In the build method, I tried to add the b's. Not sure if I should use the self.add_weight method. Ideally, I want to have as many b's as the dimension of input.

在调用方法中，这个，我很确定我在做什么.很简单，我只是实现了这个功能.

In the call method, this one, I'm pretty sure what I'm doing. It is easy, I just implemented the function.

最后一个，compute_output_shape，我只是复制粘贴了模板.输出应该和输入一样，因为它只是一个激活层.

The last one, compute_output_shape, I just copied-pasted the template. The output should be the same as the input, cause it is just an activation layer.

最后，错误的价值，我知道这是无稽之谈

Finally, the error for what its worth, I know it is nonsense

TypeError                                 Traceback (most recent call last)
<ipython-input-5-3101a9226da5> in <module>
      1 a=K.variable(np.array([1,2]))
      2 b=K.variable(np.array([3,4]))
----> 3 act([a,b])

~AppDataLocalcondacondaenvspython36libsite-packageskerasenginease_layer.py in __call__(self, inputs, **kwargs)
    429                                          'You can build it manually via: '
    430                                          '`layer.build(batch_input_shape)`')
--> 431                 self.build(unpack_singleton(input_shapes))
    432                 self.built = True
    433 

TypeError: build() takes 1 positional argument but 2 were given

推荐答案

您的代码有几个问题.

首先我应该解决你从解释器那里得到的错误:

First of all I should address the error you get from interpreter:

TypeError: build() takes 1 positional argument but 2 were given

build 方法应该采用 input_shape 参数.因此，您应该将构建方法声明为 build(self, input_shape)

The build method should take input_shape argument. Therefore you should declare build method as build(self, input_shape)

第二个问题是 build 方法中变量的未定义形状.您应该显式声明变量的形状.在您的情况下， np.random.rand 数组应该是 input_shape 形状.

The second issue is undefined shape of the variables in the build method. You should explicitly declare shape of the variables. In your case the np.random.rand array should be of input_shape shape.

另一个问题是您试图在 call 方法中返回 2 个结果 ([op_r, op_i]).我不是 Keras 的专家，但据我所知你做不到.每个 Keras 层都应该有一个且只有一个输出.详情请看这里:https://github.com/keras-team/keras/问题/3061

Another issue is that you are trying to return 2 results ([op_r, op_i]) in the call method. I'm not specialist in Keras but as far as I know you can't do it. Every Keras layer should have one and only one output. See here for the details: https://github.com/keras-team/keras/issues/3061

但是，如果您使用 tensorflow 后端，您可以使用复数 (tf.complex) 来返回实数 (op_r) 和图像数 (op_i)>) 复数的一部分.

However if you use tensorflow backend you may use complex numbers (tf.complex) to return both real (op_r) and imagenary (op_i) parts of the complex number.

这里是 modrelu 层的工作实现和简单的使用示例.它是为 TensorFlow 1.12.0 编写的，TensorFlow 1.12.0 随它自己的 Keras API 实现一起分发，但我认为您可以轻松地将它用于原始 Keras:

Here is the working implementation of modrelu layer with simple usage example. It is writtern for TensorFlow 1.12.0 which is distributed with it's own implementation of Keras API but I think you can easily adopt it for original Keras:

import tensorflow as tf
from tensorflow.python.keras import backend as K
from tensorflow.python.keras.engine import Layer
import numpy as np


class modrelu(Layer):

    def __init__(self, **kwargs):
        super(modrelu, self).__init__(**kwargs)

    # provide input_shape argument in the build method
    def build(self, input_shape):
        # You should pass shape for your variable
        self.b= K.variable(value=np.random.rand(*input_shape)-0.5,
                           dtype='float32')
        super(modrelu, self).build(input_shape)  # Be sure to call this at the end

    def call(self, inputs, **kwargs):
        assert inputs.dtype == tf.complex64

        ip_r = tf.math.real(inputs)
        ip_i = tf.math.imag(inputs)

        comp = tf.complex(ip_r, ip_i )
        ABS = tf.math.abs(comp)
        ANG = tf.math.angle(comp)

        ABS = K.relu(self.b + ABS)

        op_r = ABS * K.sin(ANG) #K.dot ??
        op_i = ABS * K.cos(ANG)

        # return single tensor in the call method
        return tf.complex(op_r, op_i)


real = tf.constant([2.25, 3.25])
imag = tf.constant([4.75, 5.75])

x = tf.complex(real, imag)

y = modrelu()(x)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())

    print(sess.run(y))

P.S.:我没有检查数学，所以你应该自己检查.

P.S.: I didn't check the math so you should check it by yourself.

这篇关于如何在 Keras 中构建这个自定义层?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！