How to use torch.isnan () and torch.isfinite () in pytorch

This article mainly explains "how to use torch.isnan () and torch.isfinite () in pytorch". The content in the article is simple and clear, and it is easy to learn and understand. Please follow the editor's train of thought to study and learn how to use torch.isnan () and torch.isfinite () in pytorch.

1.torch.isfinite ()

Import torchnum = torch.tensor (1) # Digital 1res = torch.isfinite (num) print (res)''output: tensor (True)''

This num must be tensor.

Import torchnum = torch.tensor (float ('inf')) # positive infinity res = torch.isfinite (num) print (res)' 'output: tensor (False)' 'import torchnum = torch.tensor (float ('-inf')) # negative infinity res = torch.isfinite (num) print (res)''output: tensor (False)' 'import torchnum = torch.tensor (float (' nan')) # empty res = torch.isfinite (num) print (res)''output: tensor (False)'

2.torch.isnan ()

Import torchres=torch.isnan (torch.tensor ([1, float ('inf'), 2, float ('-inf'), float ('nan')]) print (res)' output: tensor ([False, True])''

You can see that torch.isnan () is a function used to determine whether the input tensor is empty or not, and returns True when the input is empty.

Thank you for your reading, the above is the content of "how to use torch.isnan () and torch.isfinite () in pytorch". After the study of this article, I believe you have a deeper understanding of how to use torch.isnan () and torch.isfinite () in pytorch. Here is, the editor will push for you more related knowledge points of the article, welcome to follow!