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

25 votes104 views7 answers
Remove space from start and end of string in python
Python
0 vote152 views1 answer
Pip vs conda
Python
11 votes142 views6 answers
Python get file size
Python
0 vote153 views1 answer
Grouped box plot in python
Python
0 vote136 views1 answer
Int to alphabet letter python
Python
0 vote167 views1 answer
Form action in django
Python
0 vote169 views1 answer
Find each geometry overlap python
Python
9 votes131 views1 answer
How to make it so a discord bot messages in a certain channel python
Python
0 vote134 views1 answer
Example 1: Reset Index & Drop Old Index pandas
Python
1 vote144 views1 answer
Polynomial regression using scikit-learn library
Python