search

chenyuntc / pytorch-book

PyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation (《深度学习框架PyTorch：入门与实战》)
MIT License
11.99k stars 3.73k forks source link

第三章 Tensor和autograd第90页代码bug #217

Open Gamkiu opened 4 years ago

Gamkiu commented 4 years ago

文章代码运行错误,（第三段代码） x = V(t.arange(-2,4),requires_grad = True). 运行时出现“only Tensor of floating point type can require grad.”错误

QAQEthan commented 3 years ago

改成t.arange(-2,4).float()就可以了 老版本的pytorch用arange创建默认是FloatTensor类型的 新版本arange创建时dtype默认是LongTensor