A beginner’s guide to 5 PyTorch Mathematical functions you didn’t know you needed

PyTorch is a magical deep learning framework. It is a magic tool for Zero to GAN’s Human.

Md. Harun-Ur-Rashid

Published in

Predict

4 min readMay 29, 2020

Introduction

Formal Intro is “PyTorch is an open-source deep learning framework for python, primarily developed by Facebook’s AI research lab. In simple terms, PyTorch is a library for processing tensors.”

I think that PyTorch is a magical deep learning framework. It has magical power which can help to accelerate the research that goes into deep learning models by making them computationally faster and less expensive (A Data Scientist’s magic tool!).

I found PyTorch framework really useful for my work. It’s worked like magic in my work. I suggested everyone it’s a very flexible framework in Deep learning and Computer Vision.

Functions

Here are the list and explanation of the most commonly used function in PyTorch

torch.abs
torch.acos
torch.add
torch.addcdiv
torch.addcmul

Function 1 — torch.abs(input, out=None)

Computes the element-wise absolute value of the given input tensor.

Parameters:

input (Tensor) — the input tensor.
out (Tensor, optional) — the output tensor.

Example of abs Function

We saw that we gave negative input tensor and the `torch.abs` function returned positive tensor as an output. I think that this function will be very helpful for our deep learning model as like magic.

Function 2 — torch.acos(input, out=None)

It returns a new tensor with the arccosine of the elements of the input.

Parameters:

input (Tensor) — the input tensor.
out (Tensor, optional) — the output tensor.

Example of acos Function

We got random cosine tensor output for using `torch.acos` function.

Example of acos Function

I think that this function also will be very helpful for our deep learning model as like magic.

Function 3 — torch.add(input, other, out=None)

Adds the scalar `other` to each element of the input `input` and returns a new resulting tensor.

out = input + other

If `input` is of type FloatTensor or DoubleTensor, `other` must be a real number, otherwise, it should be an integer.

Parameters:

input (Tensor) — the input tensor.
value (Number) — the number to be added to each element of input

Keyword Arguments:

out (Tensor, optional) — the output tensor.

Example of add function

Here we can easily addition by using `torch.add` function.

Example of add function

This function will be very helpful in a deep learning model for easily addition.

Function 4 — torch.addcdiv(input, tensor1, tensor2, *, value=1, out=None)

Performs the element-wise division of `tensor1` by `tensor2`, multiply the result by the scalar `value` and add it to `input`.

The shapes of `input`, `tensor1`, and `tensor2` must be broadcastable.

For inputs of type FloatTensor or DoubleTensor, `value` must be a real number, otherwise an integer.

Parameters:

input (Tensor) — the tensor to be added
tensor1 (Tensor) — the numerator tensor
tensor2 (Tensor) — the denominator tensor
value (Number, optional) — multiplier for tensor1/tensor2
out (Tensor, optional) — the output tensor.

Example of addcdiv Function

Function 5 — torch.addcmul(input, tensor1, tensor2, *, value=1, out=None)

Performs the element-wise multiplication of `tensor1` by `tensor2`, multiply the result by the scalar `value ` and add it to `input`.

The shapes of `tensor`, `tensor1`, and `tensor2` must be broadcastable.

For inputs of type FloatTensor or DoubleTensor, `value` must be a real number, otherwise an integer.

Parameters:

input (Tensor) — the tensor to be added
tensor1 (Tensor) — the tensor to be multiplied
tensor2 (Tensor) — the tensor to be multiplied
value (Number, optional) — multiplier for tensor1 .* tensor2
out (Tensor, optional) — the output tensor.

Example of addcmul Function

Conclusion

PyTroch is a very useful deep learning framework. It works very faster as like magical tool. It also a magical tool for Data Scientists. So, I recommended every beginner’s to learn this framework. In this blog, I was tried to present 5 magical mathematical functions.

Reference Links

Official documentation for `torch.Tensor`: https://pytorch.org/docs/stable/tensors.html
Beginners Guide to Building Neural Networks using PyTorch: https://medium.com/fse-ai/pytorch-909e81f54ee1

With that, we have come to the end of the article. You read this far, You Go! I am excited to know how it worked for you. The entire notebook is available here. And, Don’t forget to give your 👏 ! More cool articles lined up. Coming soon!