![](https://img-blog.csdnimg.cn/20201014180756926.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
小技巧与问题记录
walker_Tjj
这个作者很懒,什么都没留下…
展开
-
RuntimeError: Expected object of scalar type Long but got scalar type Float for argument #2 ‘target‘
pytorch框架模型报错:RuntimeError: Expected object of scalar type Long but got scalar type Float for argument #2 'target'原创 2022-04-24 21:47:11 · 824 阅读 · 0 评论 -
The “freeze_support()“ line can be omitted if the program isnot going to be frozen to produce an
The "freeze_support()" line can be omitted if the program is not going to be frozen to produce an executable.原创 2022-04-20 18:24:18 · 1860 阅读 · 0 评论 -
Windows10 中使用nvidia-smi
Windows 10 中使用nvidia-smi原创 2022-04-16 21:27:02 · 6852 阅读 · 0 评论 -
模型训练时报错:RuntimeError: Unable to find a valid cuDNN algorithm to run convolution
训练模型时报错,记录一下。这个错误是现存模型过大,GPU显存不足导致的错误,此时只需要将batch-size改小即可:128->64, 64-->32等等。原创 2022-03-31 16:01:56 · 2794 阅读 · 3 评论