如何为Convolution2D设置权重？

Question

我想设置一个Convolution2D图层的权重:

conv = Convolution2D(conv_out_size, window_size, embedding_size,
                     border_mode='same',
                     activation='relu',
                     weights=weights,
                     name='conv_{:d}'.format(i))(in_x)

但我不确定这里的预期.我尝试了几件事,但大多数时候我都会尝试

ValueError: You called `set_weights(weights)` on layer "conv_0" with a  weight list of length 1, but the layer was expecting 2 weights. 

不确定这究竟意味着什么.

Answer 1

您应该通过set_weights方法将numpy数组传递给卷积层.

请记住,卷积层的权重不仅是每个单独滤波器的权重,还包括偏差.因此,如果您想设置权重,则需要添加额外的维度.

例如,如果要设置一个除了中心元素之外所有权重为零的1x3x3过滤器,则应该进行以下操作:

w = np.asarray([ 
    [[[
    [0,0,0],
    [0,2,0],
    [0,0,0]
    ]]]
    ])

然后设置它.

对于您可以运行的代码:

#!/usr/bin/env python
# -*- coding: utf-8 -*-
from __future__ import print_function
import numpy as np
np.random.seed(1234)
from keras.layers import Input
from keras.layers.convolutional import Convolution2D
from keras.models import Model
print("Building Model...")
inp = Input(shape=(1,None,None))
output   = Convolution2D(1, 3, 3, border_mode='same', init='normal',bias=False)(inp)
model_network = Model(input=inp, output=output)
print("Weights before change:")
print (model_network.layers[1].get_weights())
w = np.asarray([ 
    [[[
    [0,0,0],
    [0,2,0],
    [0,0,0]
    ]]]
    ])
input_mat = np.asarray([ 
    [[
    [1.,2.,3.],
    [4.,5.,6.],
    [7.,8.,9.]
    ]]
    ])
model_network.layers[1].set_weights(w)
print("Weights after change:")
print(model_network.layers[1].get_weights())
print("Input:")
print(input_mat)
print("Output:")
print(model_network.predict(input_mat))

尝试更改卷积填充器中的中心元素(示例中为2).

代码的作用:

首先建立一个模型.

inp = Input(shape=(1,None,None))
output   = Convolution2D(1, 3, 3, border_mode='same', init='normal',bias=False)(inp)
model_network = Model(input=inp, output=output)

打印原始权重(使用正态分布初始化,init ='normal')

print (model_network.layers[1].get_weights())

创建所需的权重张量w和一些输入input_mat

w = np.asarray([ 
    [[[
    [0,0,0],
    [0,2,0],
    [0,0,0]
    ]]]
    ])
input_mat = np.asarray([ 
    [[
    [1.,2.,3.],
    [4.,5.,6.],
    [7.,8.,9.]
    ]]
    ])

设置你的重量并打印它们

model_network.layers[1].set_weights(w)
print("Weights after change:")
print(model_network.layers[1].get_weights())

最后,用它来生成带预测的输出(预测自动编译你的模型)

print(model_network.predict(input_mat))

示例输出:

Using Theano backend.
Building Model...
Weights before change:
[array([[[[ 0.02357176, -0.05954878,  0.07163535],
         [-0.01563259, -0.03602944,  0.04435815],
         [ 0.04297942, -0.03182618,  0.00078482]]]], dtype=float32)]
Weights after change:
[array([[[[ 0.,  0.,  0.],
         [ 0.,  2.,  0.],
         [ 0.,  0.,  0.]]]], dtype=float32)]
Input:
[[[[ 1.  2.  3.]
   [ 4.  5.  6.]
   [ 7.  8.  9.]]]]
Output:
[[[[  2.   4.   6.]
   [  8.  10.  12.]
   [ 14.  16.  18.]]]]