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 vote166 views1 answer
Numpy remove rows containing nan
Python
5 votes173 views2 answers
How to reset username and password in django admin
Python
25 votes186 views10 answers
Github
Python
0 vote160 views3 answers
Lcm python
Python
2 votes162 views1 answer
Zermelo api
Python
21 votes134 views5 answers
Tkinter window
Python
0 vote182 views1 answer
Beautifulsoup remove empty tags
Python
0 vote195 views1 answer
Django sesssion can't works when web app call inside an iframe from other website
Python Django
18 votes179 views6 answers
Strptime
Python
0 vote167 views1 answer
Instantiate a dictionary python
Python