在使用pytorch訓練模型時遇到上面的問題，查了好久也不知道啥原因，最后在別人的帖子里找到類似的問題，就試試
解決辦法：檢查labels中是否有負值，如果有改成非負整數就可以了
免責聲明！
本站轉載的文章為個人學習借鑒使用，本站對版權不負任何法律責任。如果侵犯了您的隱私權益，請聯系本站郵箱yoyou2525@163.com刪除。
猜您在找
RuntimeError: CUDA error: device-side assert triggered的解決
解決RuntimeError: cuda runtime error (30) : unknown error at /pytorch/aten/src/THC/THCGeneral.cpp:70&NVIDIA-SMI has failed because it couldn't communicate with the NVIDIA driver. Make sure that the late
PyTorch錯誤解決RuntimeError: Attempting to deserialize object on a CUDA device but torch.cu
RuntimeError: cuda runtime error (30) : unknown errorr
fastai v2 windows運行錯誤解決：RuntimeError: cuda runtime error (801) : operation not supported at ..\torch/csrc/generic/StorageSharing.cpp:247
【E-14-Pytorch】RuntimeError: Expected object of device type cuda but got device type cpu for argument #2 'mat1' in call to _th_addmm
解決RuntimeError: CUDA error: out of memory
RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is Fal
pytorch查看CUDA支持情況，只需要三行代碼，另附Cuda runtime error (48) : no kernel image is available for execution處理辦法
Pytorch RuntimeError: expected type torch.cuda.FloatTensor but got torch.FloatTensor