How to view data types and sizes in pytorch

This article mainly shows you "how to check the data type and size in pytorch", the content is simple and clear, and I hope it can help you solve your doubts. Let me lead you to study and learn this article "how to check data type and size in pytorch".

Problem description:

Data.shape () is used to view the size of tensor data, and an error is reported:

TypeError: 'torch.Size' object is not callable or TypeError:' tuple' object is not callable.

Solution:

View data type: data.dtype

View data size: data.shape

Add: pytorch tensor should pay attention to comparing large and small data types.

The following a = torch.tensor ([[0,0], [0,0]]) print (a > = 0.5)

Output

Tensor ([[1,1], [1,1]], dtype=torch.uint8)

The result is obviously wrong. The reason for the analysis is that an is of long type and 0.5 is float. 0. 5 will be converted to long, 0. 5%. Therefore, the result will go wrong, and the correct answer can be obtained by making the following changes.

Correct usage: a = torch.tensor ([[0,0], [0,0]]). Float () print (a > = 0.5) is all the contents of the article "how to check data types and sizes in pytorch". Thank you for reading! I believe we all have a certain understanding, hope to share the content to help you, if you want to learn more knowledge, welcome to follow the industry information channel!