Pytorch:RuntimeError:reduce未能同步：CudaErrorRassert:deviceside断言已触发

Question

在this dataset上训练this时，我遇到了以下错误

由于这是论文中公布的配置，我假设我做了一些难以置信的错误

每次我尝试运行训练时，此错误都会出现在不同的映像上

C:/w/1/s/windows/pytorch/aten/src/THCUNN/ClassNLLCriterion.cu:106: block: [0,0,0], thread: [6,0,0] Assertion `t >= 0 && t < n_classes` failed.
Traceback (most recent call last):
  File "C:\Program Files\JetBrains\PyCharm Community Edition 2019.1.1\helpers\pydev\pydevd.py", line 1741, in <module>
    main()
  File "C:\Program Files\JetBrains\PyCharm Community Edition 2019.1.1\helpers\pydev\pydevd.py", line 1735, in main
    globals = debugger.run(setup['file'], None, None, is_module)
  File "C:\Program Files\JetBrains\PyCharm Community Edition 2019.1.1\helpers\pydev\pydevd.py", line 1135, in run
    pydev_imports.execfile(file, globals, locals)  # execute the script
  File "C:\Program Files\JetBrains\PyCharm Community Edition 2019.1.1\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile
    exec(compile(contents+"\n", file, 'exec'), glob, loc)
  File "C:/Noam/Code/vision_course/hopenet/deep-head-pose/code/original_code_augmented/train_hopenet_with_validation_holdout.py", line 187, in <module>
    loss_reg_yaw = reg_criterion(yaw_predicted, label_yaw_cont)
  File "C:\Noam\Code\vision_course\hopenet\venv\lib\site-packages\torch\nn\modules\module.py", line 541, in __call__
    result = self.forward(*input, **kwargs)
  File "C:\Noam\Code\vision_course\hopenet\venv\lib\site-packages\torch\nn\modules\loss.py", line 431, in forward
    return F.mse_loss(input, target, reduction=self.reduction)
  File "C:\Noam\Code\vision_course\hopenet\venv\lib\site-packages\torch\nn\functional.py", line 2204, in mse_loss
    ret = torch._C._nn.mse_loss(expanded_input, expanded_target, _Reduction.get_enum(reduction))
RuntimeError: reduce failed to synchronize: cudaErrorAssert: device-side assert triggered

---

有什么想法吗

Answer 1

这种错误通常发生在使用NLLLoss或CrossEntropyLoss时，以及数据集具有负标签（或标签大于类数）时。这也是您得到的断言t >= 0 && t < n_classes失败的确切错误

这不会发生在MSELoss上，但OP提到某个地方有一个CrossEntropyLoss，因此发生了错误（程序在另一行异步崩溃）。解决方案是清理数据集并确保满足t >= 0 && t < n_classes（其中t表示标签）

另外，如果您使用NLLLoss或BCELoss，请确保您的网络输出在0到1的范围内（然后分别需要softmax或sigmoid激活）。注意CrossEntropyLoss或BCEWithLogitsLoss不需要这样做，因为它们在loss函数中实现了激活函数。（感谢@PouyaB指出）