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 vote331 views1 answer
Chatbot in python github
Python
-2 votes318 views6 answers
List comprehension in python
Python
8 votes311 views6 answers
Python add to list
Python
2 votes333 views3 answers
Request session python
Python
68 votes335 views6 answers
Python clear console
Python
4 votes352 views2 answers
Python read array line by line
Python
0 vote305 views1 answer
How to input a full array in one input in python
Python
0 vote278 views1 answer
Import OpenEXR ModuleNotFoundError: No module named 'OpenEXR'
Python
0 vote316 views1 answer
How to do an if input = python
Python
0 vote303 views1 answer
Comment interpreter tuple python avec valeur unique
Python