keras:set_weights()不会更改值

时间:2018-05-07 13:40:55

标签: keras keras-layer

使用已接受的答案here,我正在尝试使用set_weights()方法更改图层的权重,但它似乎无效... 这里是我使用的代码

from keras.layers import Input
from keras.layers.convolutional import Convolution2D
from keras.models import Model
import numpy as np
print("Building Model...")
inp = Input(shape=(20,20,1))
output   = Convolution2D(1, (3,3), padding='same',bias=False)(inp)
model_network=Model(inp, output)


print("Weights before change:")
print (model_network.layers[1].get_weights())
w = np.asarray([ 
    [[[
    [2,2,2],
    [2,2,2],
    [2,2,2]
    ]]]
    ])

w=np.reshape(w,np.shape(model_network.layers[1].get_weights()))
#print("W:",w)

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

但我的体重保持不变; (在评论中输出)

0 个答案:

没有答案