Keras-重用上一层的权重-转换为keras张量 [英] Keras - Reuse weights from a previous layer - converting to keras tensor

问题描述

我正在尝试重用上一层的权重矩阵.作为一个玩具示例，我想做这样的事情:

I am trying to reuse the weight matrix from a previous layer. As a toy example I want to do something like this:

import numpy as np
from keras.layers import Dense, Input
from keras.layers import merge
from keras import backend as K
from keras.models import Model

inputs = Input(shape=(4,))
inputs2 = Input(shape=(4,))
dense_layer = Dense(10, input_shape=(4,))
dense1 = dense_layer(inputs)

def my_fun(my_inputs):
    w = my_inputs[0]
    x = my_inputs[1]

    return K.dot(w, x)

merge1 = merge([dense_layer.W, inputs2], mode=my_fun)

问题在于dense_layer.W不是keras张量.所以我收到以下错误:

The problem is that dense_layer.W is not a keras tensor. So I get the following error:

Exception: Output tensors to a Model must be Keras tensors. Found: dot.0

关于如何将dense_layer.W转换为Keras张量的任何想法吗?

Any idea on how to convert dense_layer.W to a Keras tensor?

谢谢

推荐答案

似乎您想在图层之间共享权重. 我认为您可以将密集层用作输入和输入2的共享层.

It seems that you want to share weights between layers. I think You can use denselayer as shared layer for inputs and inputs2.

merge1=dense_layer(inputs2)

请在 https://keras处检查共享层. io/getting-started/functional-api-guide/#shared-layers

这篇关于Keras-重用上一层的权重-转换为keras张量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！