What's the difference between torch.stack () and torch.cat ()?

This article will explain in detail what is the difference between torch.stack () and torch.cat (). The editor thinks it is very practical, so I share it with you for reference. I hope you can get something after reading this article.

The difference between torch.stack () and torch.cat () is:

Torch.stack () creates a new dimension and splices on it.

Torch.cat () does not create new dimensions, but splices existing dimensions.

Example 1:

Import torcha = torch.tensor ([[1,2,3]]) b = torch.stack ((a, a)). Size () c = torch.cat ((a, a)) .size () print (b) print (c)

The result is:

Torch.Size ([2,1,3]) torch.Size ([2,3])

Example 2:

Import torcha = torch.tensor ([1,2,3]) b = torch.stack ((a, a)). Size () c = torch.cat ((a, a)) .size () print (b) print (c)

The result is:

Torch.Size ([2,3]) torch.Size ([6]) this article about "what's the difference between torch.stack () and torch.cat ()" ends here. I hope the above content can be helpful to you, so that you can learn more knowledge. If you think the article is good, please share it out for more people to see.