Torch view

Torch.view

import torch

x = torch.arange(6)

print(x.view(3, -1))      # inferred size will be 2 as 6 / 3 = 2
# tensor([[ 0.,  1.],
#         [ 2.,  3.],
#         [ 4.,  5.]])

print(x.view(-1, 6))      # inferred size will be 1 as 6 / 6 = 1
# tensor([[ 0.,  1.,  2.,  3.,  4.,  5.]])

print(x.view(1, -1, 2))   # inferred size will be 3 as 6 / (1 * 2) = 3
# tensor([[[ 0.,  1.],
#          [ 2.,  3.],
#          [ 4.,  5.]]])

# print(x.view(-1, 5))    # throw error as there's no int N so that 5 * N = 6
# RuntimeError: invalid argument 2: size '[-1 x 5]' is invalid for input with 6 elements

print(x.view(-1, -1, 3))  # throw error as only one dimension can be inferred
# RuntimeError: invalid argument 1: only one dimension can be inferred

Source: stackoverflow.com

Similar codes

3 votes207 views3 answers
Flask migrate
Python Flask
4 votes143 views4 answers
Asyncio sleep
Python
0 vote73 views1 answer
Can i change color of text in jupyter notebook
Python
-1 vote119 views1 answer
PyPDF2 Python PDF
Python
0 vote113 views1 answer
Group by, aggregate multiple column -pandas
Python
1 vote114 views1 answer
How to make pyautogui faster
Python
0 vote180 views1 answer
Django-filter field name greater than
Python
1 vote132 views1 answer
Python Convert a string to lowercase
Python
0 vote161 views2 answers
Python bytes to dict
Python
0 vote111 views1 answer
Tweepy aut code
Python