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

0 vote342 views1 answer
Convert string to integer in dictionary python
Python
1 vote364 views1 answer
Vscode jupyter notebook python not started
Python
1 vote331 views3 answers
Plot python x axis range
Python
5 votes346 views2 answers
Allauth django
Python Django
107 votes366 views6 answers
Python install opencv
Python
5 votes322 views1 answer
How to make a sigmoid function in python
Python
0 vote342 views1 answer
Python logger format time
Python
0 vote387 views1 answer
Python string: built-in function len()
Python
1 vote363 views1 answer
Rename one dataframe column python
Python
17 votes357 views1 answer
Take off character in python string
Python