Exploring the deep world of machine learning and artificial intelligence, today I will introduce my fellow AI enthusiasts to Pytorch. Primarily developed by Facebook’s AI Research Lab, Pytorch is an open-source machine learning library that aids in the production deployment of models from research prototyping by accelerating the process.

The library consists of Python programs that facilitate building deep learning projects. Pytorch is easier to read and understand, is flexible, and allows deep learning models to be expressed in idiomatic Python, making it a go-to tool for those looking to develop apps that leverage computer vision and natural language processing.

How to get started with Pytorch

The best way to get started with Pytorch is through Google Colaboratory. Using this, you can easily write and execute Python in your browser. Colab is ideal as it is not only a great tool to help improve your coding skills but also allows you to develop deep learning applications using libraries such as Pytorch, TensorFlow, Keras, and OpenCV.

The best part? Colab supports free GPU. The flexibility of the tool lets you create, upload, store, or share notebooks, import from directories, or upload your personal Jupyter notebooks to get started. Recently, Colab added support for native Pytorch, enabling you to run Torch imports without the following code:

## http://pytorch.org/
from os.path import exists
from wheel.pep425tags import get_abbr_impl, get_impl_ver, get_abi_tag
platform = '{}{}-{}'.format(get_abbr_impl(), get_impl_ver(), get_abi_tag())
cuda_output = !ldconfig -p|grep cudart.so|sed -e 's/.*\.\([0-9]*\)\.\([0-9]*\)$/cu\1\2/'
accelerator = cuda_output[0] if exists('/dev/nvidia0') else 'cpu'!pip install -q http://download.pytorch.org/whl/{accelerator}/torch-0.4.1-{platform}-linux_x86_64.whl torchvision
import torch

#artificial-intelligence #pytorch #machine-learning #deep-learning #python