5

我有一个自动编码器，我需要在输出后添加一个高斯噪声层。我需要一个自定义层来执行此操作，但我真的不知道如何生成它，我需要使用张量来生成它。 在此处输入图像描述

如果我想在下面代码的调用部分实现上面的等式怎么办？

class SaltAndPepper(Layer):

    def __init__(self, ratio, **kwargs):
        super(SaltAndPepper, self).__init__(**kwargs)
        self.supports_masking = True
        self.ratio = ratio

    # the definition of the call method of custom layer
    def call(self, inputs, training=None):
        def noised():
            shp = K.shape(inputs)[1:]

         **what should I put here????**            
                return out

        return K.in_train_phase(noised(), inputs, training=training)

    def get_config(self):
        config = {'ratio': self.ratio}
        base_config = super(SaltAndPepper, self).get_config()
        return dict(list(base_config.items()) + list(config.items()))

我也尝试使用 lambda 层来实现，但它不起作用。

4

3 回答 3

6

如果您正在寻找加法或乘法高斯噪声，那么它们已经在 Keras 中作为一个层实现：（GuassianNoise加法）和GuassianDropout（乘法）。

但是，如果您在图像处理中专门寻找高斯模糊滤镜中的模糊效果，那么您可以简单地使用具有固定权重的深度卷积层（在每个输入通道上独立应用滤镜）以获得所需的输出（请注意，您需要生成高斯核的权重以将它们设置为 DepthwiseConv2D 层的权重。为此，您可以使用此答案中介绍的函数）：

import numpy as np
from keras.layers import DepthwiseConv2D

kernel_size = 3  # set the filter size of Gaussian filter
kernel_weights = ... # compute the weights of the filter with the given size (and additional params)

# assuming that the shape of `kernel_weighs` is `(kernel_size, kernel_size)`
# we need to modify it to make it compatible with the number of input channels
in_channels = 3  # the number of input channels
kernel_weights = np.expand_dims(kernel_weights, axis=-1)
kernel_weights = np.repeat(kernel_weights, in_channels, axis=-1) # apply the same filter on all the input channels
kernel_weights = np.expand_dims(kernel_weights, axis=-1)  # for shape compatibility reasons

# define your model...

# somewhere in your model you want to apply the Gaussian blur,
# so define a DepthwiseConv2D layer and set its weights to kernel weights
g_layer = DepthwiseConv2D(kernel_size, use_bias=False, padding='same')
g_layer_out = g_layer(the_input_tensor_for_this_layer)  # apply it on the input Tensor of this layer

# the rest of the model definition...

# do this BEFORE calling `compile` method of the model
g_layer.set_weights([kernel_weights])
g_layer.trainable = False  # the weights should not change during training

# compile the model and start training...
于 2019-04-12T21:07:42.520 回答
1

经过一段时间试图弄清楚如何使用@today 提供的代码来做到这一点，我决定与将来可能需要它的任何人分享我的最终代码。我创建了一个非常简单的模型，它只对输入数据应用模糊：

import numpy as np
from keras.layers import DepthwiseConv2D
from keras.layers import Input
from keras.models import Model


def gauss2D(shape=(3,3),sigma=0.5):

    m,n = [(ss-1.)/2. for ss in shape]
    y,x = np.ogrid[-m:m+1,-n:n+1]
    h = np.exp( -(x*x + y*y) / (2.*sigma*sigma) )
    h[ h < np.finfo(h.dtype).eps*h.max() ] = 0
    sumh = h.sum()
    if sumh != 0:
        h /= sumh
    return h

def gaussFilter():
    kernel_size = 3
    kernel_weights = gauss2D(shape=(kernel_size,kernel_size))
    
    
    in_channels = 1  # the number of input channels
    kernel_weights = np.expand_dims(kernel_weights, axis=-1)
    kernel_weights = np.repeat(kernel_weights, in_channels, axis=-1) # apply the same filter on all the input channels
    kernel_weights = np.expand_dims(kernel_weights, axis=-1)  # for shape compatibility reasons
    
    
    inp = Input(shape=(3,3,1))
    g_layer = DepthwiseConv2D(kernel_size, use_bias=False, padding='same')(inp)
    model_network = Model(input=inp, output=g_layer)
    model_network.layers[1].set_weights([kernel_weights])
    model_network.trainable= False #can be applied to a given layer only as well
        
    return model_network

a = np.array([[[1, 2, 3], [4, 5, 6], [4, 5, 6]]])
filt = gaussFilter()
print(a.reshape((1,3,3,1)))
print(filt.predict(a.reshape(1,3,3,1)))

出于测试目的，数据仅具有形状1,3,3,1，该函数gaussFilter()创建了一个非常简单的模型，该模型只有输入和一个卷积层，该卷积层提供具有函数中定义的权重的高斯模糊gauss2D()。您可以向函数添加参数以使其更具动态性，例如形状、内核大小、通道。根据我的发现，权重只能在图层添加到模型后应用。

于 2020-12-09T12:13:26.003 回答
0

作为 Error: AttributeError: 'float' object has no attribute 'dtype'，只需更改K.sqrt为math.sqrt，然后它将起作用。

于 2019-04-12T05:54:43.960 回答