Functions from PyTorch Library

An short introduction about PyTorch and about the chosen functions.

torch.argmax()
torch.argmin()
torch.mean()
torch.median()
torch.unique()

Before we begin, let's install and import PyTorch

# Uncomment and run the appropriate command for your operating system, if required

# Linux / Binder
# !pip install numpy torch==1.7.0+cpu torchvision==0.8.1+cpu torchaudio==0.7.0 -f https://download.pytorch.org/whl/torch_stable.html

# Windows
# !pip install numpy torch==1.7.0+cpu torchvision==0.8.1+cpu torchaudio==0.7.0 -f https://download.pytorch.org/whl/torch_stable.html

# MacOS
# !pip install numpy torch torchvision torchaudio

# Import torch and other required modules
import torch

Function 1 - torch.argmax()

Returns the indices of the maximum value of all elements in the input tensor.

a=torch.randn(4, 4)
a

tensor([[-1.4222, -0.4501,  2.1666, -0.2640],
        [ 0.9964,  0.8415, -0.4781,  0.8133],
        [-0.9866, -0.6095,  1.6877,  1.0005],
        [-0.9803,  1.7632,  0.2358, -0.8230]])