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 vote193 views1 answer
Get variance of list python
Python
0 vote177 views1 answer
Row to column python numpy
Python
0 vote215 views1 answer
Dictionary Loop thru a dictionary's keys.
Python
3 votes250 views1 answer
Business logic in django
Python Django
0 vote192 views1 answer
Install lz4 python 3
Python
11 votes194 views6 answers
Python Dictionaries
Python
20 votes417 views6 answers
Python last item in list
Python
38 votes192 views6 answers
Pip is not recognized as an internal or external command
Python
5 votes211 views2 answers
Ubuntu remove python 2.7
Python
0 vote275 views1 answer
Django forms request
Python Django