報錯原因分析:
train_loss += loss.data[0] 是pytorch0.3.1版本代碼,在0.4-0.5版本的pytorch會出現警告,不會報錯,但是0.5版本以上的pytorch就會報錯,總的來說是版本更新問題.
解決方法:
將datra[0]換成item（） 即可
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
IndexError: invalid index of a 0-dim tensor. Use tensor.item() to convert a 0-dim tensor to a Python number
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
報錯：invalid index of a 0-dim tensor. Use tensor.item() to convert a 0-dim tensor to a Python number
pytorch--(MisMatch in shape & invalid index of a 0-dim tensor)
TypeError: Fetch argument 0 has invalid type
, must be a string or Tensor. (Can not convert a int into a Tensor or Operation.)
ValueError: Can't convert non-rectangular Python sequence to Tensor.
什么是Tensor
tensor
TypeError: can't convert CUDA tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory ..
TypeError: Fetch argument 0.484375 has invalid type
, must be a string or Tensor. (Can not convert a float32 into a Tensor or Operation.)