Created
August 6, 2018 08:17
-
-
Save vikene/c2baf8e0f256605be86899fe8c74c9a6 to your computer and use it in GitHub Desktop.
Basic Tensors using pytorch tutorial
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import torch #import torch | |
X = torch.tensor(1.0) | |
Y = torch.tensor([1.0,2.0]) | |
#Creates two tensor objects | |
#Alternatively we can also create a tensor from data like this | |
Z = torch.tensor([[1.0,2.0,3.0], | |
[2.0,3.0,4.0], | |
[3.0,4.0,5.0]]) | |
#We can also look at the shape of each tensor as follows | |
print('Shape of Z: ',Z.shape) #prints same as Z.size() | |
#we can create Tensors with different default values using | |
A = torch.rand(3,3) #Fills with uniform distribution from (0,1] | |
#Or | |
B = torch.randn(3,3) #Fills random numbers between mean 0 and variance 1 | |
#Both creates a 3x3 tensor | |
C = torch.empty(20,20) #Uninitalized data, could be anything :P | |
D = torch.zeros(5,5) #strictly zeros | |
#We can get the type and also size using following | |
print(C.dtype) | |
print(C.size()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment