如何抑制 Tensorflow (Python) 中的特定警告 [英] How to suppress specific warning in Tensorflow (Python)

问题描述

我有一个模型，根据某些条件，它有一些不相关的梯度，而这正是我想要的.但是 Tensorflow 每次遇到未连接的梯度时都会打印出警告.

I have a model that, based on certain conditions, has some unconnected gradients, and this is exactly what I want. But Tensorflow is printing out a Warning every time it encounters the unconnected gradient.

WARNING:tensorflow:Gradients do not exist for variables

有没有办法只抑制这个特定的警告?我不想盲目地抑制所有警告，因为我仍在研究我的模型，因此将来可能会出现意外(并且可能有用)的警告.

Is there any way to only suppress this specific warning? I don't want to blindly suppress all warnings since there might be unexpected (and potentially useful) warnings in the future as I'm still working on my model.

推荐答案

有点 hacky 的方式:

Kinda hacky way:

gradients = tape.gradient(loss, model.trainable_variables)
optimizer.apply_gradients([
    (grad, var) 
    for (grad, var) in zip(gradients, model.trainable_variables) 
    if grad is not None
])

这篇关于如何抑制 Tensorflow (Python) 中的特定警告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！