predict=predict.data.numpy() 這一行報錯
意思是:如果想把CUDA tensor格式的數據改成numpy時
，需要先將其轉換成cpu float-tensor隨后再轉到numpy格式。
numpy不能讀取CUDA tensor 需要將它轉化為 CPU tensor
將predict.data.numpy() 改為predict.data.cpu().numpy()即可
轉 https://blog.csdn.net/qq_38410428/article/details/82973711
can't convert CUDA tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.
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
TypeError: can't convert CUDA tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.
TypeError: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.
TypeError: can't convert CUDA tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory ..
【E-13】TypeError: can't convert CUDA tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.
張量與數組運算報錯(Use Tensor.cpu() to copy the tensor to host memory first;RuntimeError: Expected all tensors to be on the same device)
2、tensor數據的運算、numpy與Tensor互轉、Tensor轉cuda
IndexError: invalid index of a 0-dim tensor. Use `tensor.item()` in Python or `tensor.item
()` in C++ to convert a 0-dim tensor to a number
tensor和numpy
什么是Tensor
tensor