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

14 votes158 views4 answers
Spyder python
Python
5 votes195 views3 answers
How to run flask in port 80
Python
21 votes144 views1 answer
Python date now plus days
Python
74 votes141 views6 answers
Remove duplicates from list python
Python
9 votes157 views2 answers
Clear terminal in python
Python
0 vote143 views1 answer
How to compare current date to future date pythono
Python
1 vote146 views2 answers
How to sort nested list in python
Python
0 vote152 views1 answer
Python Command '['latexmk', '--pdf', '--interaction=nonstopmode', % returned non-zero exit status 2.
Python
1 vote155 views1 answer
Pipenv install --python 3.8 jupyter is not recognised as an internal commmand
Python
0 vote150 views1 answer
Unpack a sequence into variables python
Python