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 vote274 views1 answer
A chef has a large container full of olive oil. In one night, after he used 252525 quarts of olive oil, 35.9\%35.9%35, point, 9, percent of the full container of olive oil remained. How many quarts of olive oil remained in the container?
Python
0 vote388 views1 answer
Python << meaning
Python
0 vote391 views1 answer
Python multiclass inheritance with inputs
Python
1 vote353 views2 answers
N factorial
Python
0 vote332 views1 answer
Python find if strings have common substring
Python
0 vote424 views1 answer
: UserWarning: Matplotlib is currently using module://matplotlib_inline.backend_inline, which is a non-GUI backend,
Python
0 vote347 views1 answer
Herons rule python
Python
1 vote329 views1 answer
Select realted for foreign key table in django
Python
0 vote331 views1 answer
Remove env variable python
Python
0 vote299 views1 answer
Plt.tight_layout()
Python