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 vote149 views1 answer
Php datatables serverside
Python
1 vote320 views1 answer
[0] * 10 python
Python
1 vote126 views1 answer
Random question generator python
Python
1 vote131 views1 answer
Discord.py send messages
Python
0 vote136 views1 answer
Get video duration opencv python
Python
0 vote176 views2 answers
Call javascript function flask
Python Flask
110 votes170 views6 answers
Python json open file
Python
-1 vote139 views1 answer
How to block a ip adress
Python
1 vote137 views3 answers
Flatmap python
Python
0 vote131 views1 answer
Gizeh python
Python