Keras 如何设置卷积2D的权重?
我想设置Keras 如何设置卷积2D的权重?,keras,Keras,我想设置卷积2D层的权重: conv=Convolution2D(conv\u out\u大小、窗口大小、嵌入大小、, border_mode='same', 激活='relu', 重量=重量, name='conv{:d}.格式(i))(in_x) 但我不确定这里会发生什么。我试过几种方法,但大多数时候我都失败了 ValueError: You called `set_weights(weights)` on layer "conv_0" with a weight list of len
卷积2D
层的权重:
conv=Convolution2D(conv\u out\u大小、窗口大小、嵌入大小、,
border_mode='same',
激活='relu',
重量=重量,
name='conv{:d}.格式(i))(in_x)
但我不确定这里会发生什么。我试过几种方法,但大多数时候我都失败了
ValueError: You called `set_weights(weights)` on layer "conv_0" with a weight list of length 1, but the layer was expecting 2 weights.
我不知道这到底意味着什么 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,如果你想设置你的权重,你需要添加一个额外的维度 例如,如果要将1x3x3过滤器设置为除中心元素外的所有权重均为零,则应将其设置为:
w = np.asarray([
[[[
[0,0,0],
[0,2,0],
[0,0,0]
]]]
])
然后设置它
对于可以运行的代码:
#!/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')
创建所需的权重张量w和一些输入矩阵
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.]
]]
])
设定重量并打印出来
model_network.layers[1].set_weights(w)
print("Weights after change:")
print(model_network.layers[1].get_weights())
最后,使用它生成带有predict的输出(predict自动编译您的模型)
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.]]]]
哦,谢谢!我不清楚。文件中没有具体说明砝码形状的具体要求。谢谢你的例子!
print(model_network.predict(input_mat))
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.]]]]