使用 Tensorflow 训练时修改张量的值 [英] Modify the value of a tensor when training with Tensorflow

问题描述

我想在使用 Tensorflow 训练模型时修改张量的值.

I want to modify the value of a tensor when I am training my model with Tensorflow.

这个张量是我模型中的张量之一

This tensor is one of the tensors in my model

weight = tf.Variable(np_matrix)

经过一些迭代后，weight的值会自动更新.

After some iterations, the value of weight will be updated automatically.

我的问题是:如何非自动修改 weight 的值.我已经尝试过这种方法，但没有奏效.

My question is: How can I modify the value of weight nonautomatically. I have tried this method but it didn't work.

modify_weight = sess.run([weight], feed_dict = feed_dict)
modify_weight[0] = [0, 0]
weight = tf.Variable(modify_weight)

这部分代码在 tf.Session() 部分(因为我想在训练期间修改值.)

This part code is in tf.Session() section(since I want to modify the value during the training time.)

谢谢！

推荐答案

和其他一切一样，赋值也是一个操作，我们必须用 tf.assign 并在会话中运行它.

Like everything else, also the assignment is an operation, and we have to create a graph with the tf.assign and run it in a session.

所以你创建一个这样的操作:

So you you create an operation like this:

assign = tf.assign(weight, value)

其中 value 是一个 numpy 数组，其形状与 weight(或一个 tf.Placeholder您可以使用提要字典进行修改)然后在会话中运行此图:

where value is a numpy array with the same shape of weight (or a tf.Placeholder that you can modify with a feed dictionary) then you run this graph in the session:

sess.run(assign)

tf.Variable 也有一个方法assign，因此你可以直接从变量开始创建操作:

The tf.Variable also has a method assign, thus you can directly create the operation starting from the variable:

assign = weight.assign(value)

然后在会话中运行它.

这篇关于使用 Tensorflow 训练时修改张量的值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！