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 vote135 views1 answer
Runpy.py", line 194, in _run_module_as_main return _run_code(code, main_globals, None,
Python
88 votes179 views6 answers
How to check python version
Python
0 vote176 views1 answer
Funcions in python
Python
0 vote183 views1 answer
Pydub audiosegment to numpy array
Python
1 vote220 views1 answer
How to add a cooment in python
Python
22 votes197 views4 answers
ModuleNotFoundError: No module named 'sklearn.cross_validation'
Python
0 vote214 views1 answer
Get number of nodes networkx
Python
1 vote315 views3 answers
List of dict to df
Python
0 vote205 views1 answer
Chatbot in python github
Python
-1 vote191 views1 answer
AttributeError: 'list' object has no attribute 'dtypes'
Python