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 vote260 views1 answer
Extends template django file system
Python Django
1 vote242 views1 answer
How to make a blank window open up in python
Python
1 vote191 views1 answer
Drop a row with a specific value of a column
Python
2 votes140 views1 answer
Python ridge regression
Python
0 vote215 views1 answer
Query first 5 element in django
Python Django
-1 vote176 views1 answer
PyPDF2 Python PDF
Python
1 vote202 views1 answer
Frequency
Python
0 vote214 views1 answer
Response 200 python
Python
0 vote180 views1 answer
Django admin manytomanyfield filter
Python Django
0 vote249 views1 answer
Minimal requirements.txt django
Python Django