nll_loss_forward_reduce_cuda_kernel_2d: Assertion `t ＞= 0 && t ＜ n_

这篇具有很好参考价值的文章主要介绍了nll_loss_forward_reduce_cuda_kernel_2d: Assertion `t ＞= 0 && t ＜ n__classes` failed.。希望对大家有所帮助。如果存在错误或未考虑完全的地方，请大家不吝赐教，您也可以点击"举报违法"按钮提交疑问。

报错如下：

../aten/src/ATen/native/cuda/Loss.cu:271: nll_loss_forward_reduce_cuda_kernel_2d: block: [0,0,0], thread: [26,0,0] Assertion `t >= 0 && t < n_classes` failed.
../aten/src/ATen/native/cuda/Loss.cu:271: nll_loss_forward_reduce_cuda_kernel_2d: block: [0,0,0], thread: [27,0,0] Assertion `t >= 0 && t < n_classes` failed.
../aten/src/ATen/native/cuda/Loss.cu:271: nll_loss_forward_reduce_cuda_kernel_2d: block: [0,0,0], thread: [28,0,0] Assertion `t >= 0 && t < n_classes` failed.
../aten/src/ATen/native/cuda/Loss.cu:271: nll_loss_forward_reduce_cuda_kernel_2d: block: [0,0,0], thread: [29,0,0] Assertion `t >= 0 && t < n_classes` failed.
../aten/src/ATen/native/cuda/Loss.cu:271: nll_loss_forward_reduce_cuda_kernel_2d: block: [0,0,0], thread: [30,0,0] Assertion `t >= 0 && t < n_classes` failed.
../aten/src/ATen/native/cuda/Loss.cu:271: nll_loss_forward_reduce_cuda_kernel_2d: block: [0,0,0], thread: [31,0,0] Assertion `t >= 0 && t < n_classes` failed.

Test Iter:  140/ 143. Data: 0.313s. Batch: 0.342s. Loss: 3.9630. top1: 6.09. top5: 22.77. :  98%|█████████▊| 140/143 [00:56<00:01,  2.48it/s]
Traceback (most recent call last):
  File "./train.py", line 533, in <module>
    main()
  File "./train.py", line 314, in main
    train(args, labeled_trainloader, unlabeled_trainloader, test_loader,
  File "./train.py", line 450, in train
    test_loss, test_acc = test(args, test_loader, test_model, epoch)
  File "./train.py", line 508, in test
    losses.update(loss.item(), inputs.shape[0])
RuntimeError: CUDA error: device-side assert triggered
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.

然后在函数里输出inputs和targets的形状，发现维度也没有问题，然后输出标签的值看一下

print(targets.min(), targets.max())

然后发现target的值==num_class,发现num_class的值写错了。
还有一种可能就是你的target的值不是从0开始的，是从1开始的也会报错。文章来源地址https://www.toymoban.com/news/detail-820294.html

到了这里，关于nll_loss_forward_reduce_cuda_kernel_2d: Assertion `t ＞= 0 && t ＜ n__classes` failed.的文章就介绍完了。如果您还想了解更多内容，请在右上角搜索TOY模板网以前的文章或继续浏览下面的相关文章，希望大家以后多多支持TOY模板网！