.報錯For debugging consider passing CUDA_LAUNCH_BLOCKING=1.

/aten/src/ATen/native/cuda/NLLLoss2d.cu:103: nll_loss2d_forward_kernel: block: [29,0,0], thread: [707,0,0] Assertion t >= 0 && t < n_classes failed.

報錯信息如下：

./aten/src/ATen/native/cuda/NLLLoss2d.cu:103: nll_loss2d_forward_kernel: block: [29,0,0], thread: [707,0,0] Assertion t >= 0 && t < n_classes failed.
。。。。。。

。。。。。。
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.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

模型運行訓練，可到epoch=9 ，報錯
刪除models/__pycache__下的緩存文件，重新運行數據集，還是會報錯。

解決方案：
是標簽有問題，有一張圖片標簽壞了，某張圖片的label標簽個數超過了設定的類別數。