python - 反向传播会发生在标签中是什么意思？

Question

我今天收到一个警告，它说

softmax_cross_entropy_with_logits (from tensorflow.python.ops.nn_ops) is deprecated and will be removed in a future version. Instructions for updating:

Future major versions of TensorFlow will allow gradients to flow into the labels input on backprop by default.

然后我按照它的建议检查了 tf.nn.softmax_cross_entropy_with_logits_v2，并在下面找到了一些东西

Backpropagation will happen into both logits and labels. To disallow backpropagation into labels, pass label tensors through a stop_gradients before feeding it to this function.

我不太明白反向传播会发生在标签中是什么意思，标签不是设置为常量吗？

Answer 1

查看以下链接，有人问了类似的问题并得到了很好的答案。

https://stats.stackexchange.com/questions/327348/how-is-softmax-cross-entropy-with-logits-different-from-softmax-cross-entropy-wi