Pytorch view -1 meaning

View(-1) in pytorch

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

Pytorch view -1 meaning

If there is any situation that you don't know how many rows you want but are sure of the number of columns, then you can specify this with a -1. (Note that you can extend this to tensors with more dimensions. Only one of the axis value can be -1). This is a way of telling the library: "give me a tensor that has these many columns and you compute the appropriate number of rows that is necessary to make this happen".

Similar codes

5 votes117 views4 answers
Create python list
Python
4 votes94 views1 answer
Loop through python object
Python
0 vote94 views2 answers
Python starting multiple processes in a loop
Python
0 vote105 views1 answer
Python every other including first
Python
33 votes138 views5 answers
How to filter out all NaN values in pandas df
Python
4 votes98 views2 answers
How to make a screen in pygame
Python
0 vote99 views1 answer
Roblox api python
Python
0 vote100 views4 answers
Dfs and bfs in python
Python
0 vote62 views1 answer
Pandas loop through unique values
Python
0 vote110 views1 answer
Tkinter get child in frame
Python