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

1 vote138 views1 answer
Python import from other folder outside folder
Python
4 votes163 views1 answer
Dataframe to csv without ids
Python
0 vote138 views1 answer
How to sort values of pandas dataframe for iqr
Python
51 votes156 views4 answers
Online python compiler with all modules
Python
0 vote141 views1 answer
Pixmap in python
Python
0 vote135 views1 answer
Kroki - hello.dot
Python
0 vote139 views1 answer
Matlab index last element
Python
0 vote137 views1 answer
Concat and Append DFs Python
Python
3 votes170 views1 answer
Load pandas from text
Python
0 vote154 views1 answer
Error: The file/path provided (flaskr) does not appear to exist. Please verify the path is correct. If app is not on PYTHONPATH, ensure the extension is .py
Python