Pytorch tensor to numpy array

Question

I have a pytorch Tensor of size torch Size  4  3  966  1296    I want to convert it to numpy array using the following code   imgs   imgs numpy        -1         Can anyone please explain what this code is doing

User · Accepted Answer

There are 4 dimensions of the tensor you want to convert.

[:, ::-1, :, :]

: means that the first dimension should be copied as it is and converted, same goes for the third and fourth dimension.

::-1 means that for the second axes it reverses the the axes

User · Answer

This worked for me  np arr   torch tensor cpu   detach   numpy

User · Answer

Your question is very poorly worded  Your code  sort of  already does what you want  What exactly are you confused about  x numpy   answer the original title of your question   Pytorch tensor to numpy array  you need improve your question starting with your title  Anyway  just in case this is useful to others  You might need to call detach for your code to work  e g  RuntimeError  Can t call numpy   on Variable that requires grad   So call  detach    Sample code    creating data and running through a nn and saving it  import torch import torch nn as nn  from pathlib import Path from collections import OrderedDict  import numpy as np  path   Path    data tmp    expanduser   path mkdir parents True  exist ok True   num samples   3 Din  Dout   1  1 lb  ub   -1  1  x   torch torch distributions Uniform low lb  high ub  sample  num samples  Din    f   nn Sequential OrderedDict         f1   nn Linear Din Dout          out   nn SELU        y   f x     save data y numpy   x np  y np   x detach   cpu   numpy    y detach   cpu   numpy   np savez path    db   x x np  y y np   print x np   cpu goes after detach  See  https   discuss pytorch org t should-it-really-be-necessary-to-do-var-detach-cpu-numpy 35489 5  Also I won t make any comments on the slicking since that is off topic and that should not be the focus of your question  See this  Understanding slice notation

User · Answer

While other answers perfectly  explained the question I will add some real life examples converting tensors to numpy array  Example  Shared storage PyTorch tensor residing on CPU shares the same storage as numpy array na import torch a   torch ones  1 2   print a  na   a numpy   na 0  0  10 print na  print a   Output  tensor   1   1       10   1    tensor   10    1      Example  Eliminate effect of shared storage  copy numpy array first To avoid the effect of shared storage we need to copy   the numpy array na to a new numpy array nac  Numpy copy   method creates the new separate storage  import torch a   torch ones  1 2   print a  na   a numpy   nac   na copy   nac 0  0  10  print nac  print na  print a   Output  tensor   1   1       10   1      1  1    tensor   1   1      Now  just the nac numpy array will be altered with the line nac 0  0  10  na and a will remain as is  Example  CPU tensor with requires grad True import torch a   torch ones  1 2   requires grad True  print a  na   a detach   numpy   na 0  0  10 print na  print a   Output  tensor   1   1     requires grad True    10   1    tensor   10    1     requires grad True   In here we call  na   a numpy     This would cause  RuntimeError  Can t call numpy   on Tensor that requires grad  Use tensor detach   numpy   instead   because tensors that require grad True are recorded by PyTorch AD  Note that tensor detach   is the new way for tensor data  This explains why we need to detach   them first before converting using numpy    Example  CUDA tensor with requires grad False a   torch ones  1 2   device  cuda   print a  na   a to  cpu   numpy   na 0  0  10 print na  print a   Output  tensor   1   1     device  cuda 0     10   1    tensor   1   1     device  cuda 0      Example  CUDA tensor with requires grad True a   torch ones  1 2   device  cuda   requires grad True  print a  na   a detach   to  cpu   numpy   na 0  0  10  print na  print a   Output  tensor   1   1     device  cuda 0   requires grad True    10   1    tensor   1   1     device  cuda 0   requires grad True   Without detach   method the error RuntimeError  Can t call numpy   on Tensor that requires grad  Use tensor detach   numpy   instead  will be set  Without  to  cpu   method TypeError  can t convert cuda 0 device type tensor to numpy  Use Tensor cpu   to copy the tensor to host memory first  will be set  You could use cpu   but instead of to  cpu   but I prefer the newer to  cpu

User · Answer

You can use this syntax if some grads are attached with your variables   y torch Tensor cpu x  detach   numpy         -1

User · Answer

I believe you also have to use  detach    I had to convert my Tensor to a numpy array on Colab which uses CUDA and GPU  I did it like the following    this is just my embedding matrix which is a Torch tensor object embedding   learn model u weight  embedding list   list range 0  64382    input   torch cuda LongTensor embedding list  tensor array   embedding input    the output of the line below is a numpy array tensor array cpu   detach   numpy

[python] Pytorch tensor to numpy array

Examples related to python

Examples related to numpy

Examples related to pytorch