如何修复这个奇怪的错误:“RuntimeError: CUDA error: out of memory" [英] How to fix this strange error: "RuntimeError: CUDA error: out of memory"

问题描述

我运行了一个关于深度学习网络的代码，首先我训练了网络，它运行良好，但运行到验证网络时出现此错误.

I ran a code about the deep learning network,first I trained the network,and it works well,but this error occurs when running to the validate network.

我有五个 epoch，每个 epoch 都有一个训练和验证的过程.我在第一个纪元验证时遇到了错误.所以我没有运行验证代码，我发现代码可以运行到第二个epoch并且没有错误.

I have five epoch,every epoch has a process of training and validation. I met the error when validate in the first epoch. So I don not run the validate code, I found that code can run to the second epoch and have no error.

我的代码:

for epoch in range(10,15): # epoch: 10~15
    if(options["training"]["train"]):
        trainer.epoch(model, epoch)

    if(options["validation"]["validate"]):
    #if(epoch == 14):
        validator.epoch(model)

我觉得验证的代码可能有一些错误.但我找不到那个.

I feel the code of validation may have some bugs. But I can not find that.

推荐答案

显示您提供的错误，因为您的 GPU 内存不足.解决此问题的一种方法是减少批处理大小，直到您的代码运行时不会出现此错误.

The error, which you has provided is shown, because you ran out of memory on your GPU. A way to solve it is to reduce the batch size until your code will run without this error.

这篇关于如何修复这个奇怪的错误:“RuntimeError: CUDA error: out of memory"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！