torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 58.00 MiB (GPU 0; 6.00 GiB total capacity; 5.25 GiB already allocated; 0 bytes free; 5.28 GiB reserved in total by PyTorch) If reserved memory is >> allocated memory try setting max_split_size_mb to avoid fragmentation. See documentation for Memory Management and PYTORCH_CUDA_ALLOC_CONF

这个错误表示您的GPU内存不足，无法分配足够的内存来执行当前的操作。在PyTorch中，可以通过调整一些参数来尝试解决这个问题。

首先，您可以尝试减少模型的批量大小（batch size），这样每次分配给GPU的内存需求就会减少。您可以尝试将批量大小减小到一个较小的值，看看是否能够解决问题。

另外，您可以尝试释放已经分配的显存。可以使用以下代码片段来清除GPU内存：

import torch
torch.cuda.empty_cache()

如果问题仍然存在，您可以尝试设置`max_split_size_mb`参数来避免内存碎片化。可以在PyTorch初始化之前添加以下代码：

import torch
torch.cuda.set_per_process_memory_fraction(0.5, 0)

这将设置`max_split_size_mb`为0.5GB，可以根据您的实际情况进行调整。

最后，如果您的显存仍然不足，可能需要考虑更大的显卡或使用更小的模型。

希望这些解决方案能帮助您解决问题。如果还有其他疑问，请随时向我提问。

相关问题

torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 20.00 MiB (GPU 0; 2.00 GiB total capacity; 1.67 GiB a

vailable; 40.00 KiB already allocated; 19.94 MiB free; 4.00 MiB cached)

This error message indicates that the program tried to allocate 20.00 MiB of memory on the GPU, but there was not enough memory available. The GPU has a total capacity of 2.00 GiB, but only 1.67 GiB was available at the time. 40.00 KiB had already been allocated, leaving only 19.94 MiB free. Additionally, 4.00 MiB had been cached, which means that it was reserved for future use but not currently in use.

To resolve this issue, you can try one or more of the following:

1. Reduce the size of the input data or the size of the model being used. This will reduce the amount of memory required.

2. Increase the GPU memory capacity. If possible, add more memory to the GPU or switch to a GPU with a larger memory capacity.

3. Use a smaller batch size. This will reduce the amount of memory required for each iteration.

4. Use gradient checkpointing. This technique allows the model to compute gradients for small subsets of parameters at a time, reducing the amount of memory required.

5. Use mixed precision training. This technique allows the model to use 16-bit floating point numbers instead of 32-bit, reducing the amount of memory required.

torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 148.00 MiB (GPU 0; 4.00 GiB total capacity; 5.23 GiB already allocated;

torch.cuda.OutOfMemoryError是指在使用PyTorch时，尝试在CUDA显存中分配内存时出现错误，因为显存已经被其他操作占用完毕。其中引用和引用提到了相同的错误信息和可能的解决方法。根据这些引用内容，可以推测解决此错误的方法是通过设置max_split_size_mb参数来避免内存碎片化。你可以参考PyTorch的Memory Management和PYTORCH_CUDA_ALLOC_CONF文档了解更多的信息。引用也提到了类似的错误信息，但给出了不同的显存容量和已分配内存的数值。这说明出现该错误的具体原因可能因系统配置不同而有所不同。<span class="em">1</span><span class="em">2</span><span class="em">3</span>
#### 引用[.reference_title]
- *1* *2* [成功解决torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 86.00 MiB (GPU 0； 2.00 ...](https://blog.csdn.net/qq_41185868/article/details/131015210)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v93^chatsearchT3_1"}}] [.reference_item style="max-width: 50%"]
- *3* [报错记录torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 90.00 MiB (GPU 0； 7.93 ...](https://blog.csdn.net/gongkeguo/article/details/127674524)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v93^chatsearchT3_1"}}] [.reference_item style="max-width: 50%"]
[ .reference_list ]