In this we are going to use PyTorch to train a CNN to recognize handwritten digit classifier using the MNIST dataset.MNIST is a widely used dataset for hand-written classification task covering more than 70k labeled 28*28 pixel grayscale images of handwritten digits. The dataset contains almost 60k training images and 10k test images. Our job is to train a model using 60k training images and subsequently test its classification accuracy on 10k test images.InstallationFirst we need the MXNet latest version, for that just run the following on your terminal:$pip install mxnetAnd you will something like, Collecting mxnet Downloading https://files.pythonhosted.org/packages/60/6f/071f9ef51467f9f6cd35d1ad87156a29314033bbf78ad862a338b9eaf2e6/mxnet-1.2.0-py2.py3-none-win32.whl (12.8MB) ... Read More

We can extract content in web pages from a variety of domains such as data mining, information retrieval etc. To extract information from the websites of newspapers and magazines we are going to use newspaper library.The main purpose of this library is to extract and curates the articles from the newspapers and similar websites.Installation:To Newspaper library installation, run in your terminal:$ pip install newspaper3kFor lxml dependencies, run below command in your terminal$pip install lxmlTo install PIL, run$pip install PillowThe NLP corpora will be downloaded:$ curl https://raw.githubusercontent.com/codelucas/newspaper/master/download_corpora.py | pythonThe python newpaper library is used to collect information associated with articles. This ... Read More

There are multiple ways to wrap your existing C or C++ functionality in Python. In this section, we are going to see how we can wrap C/C++ functionality with SWIG. Below are other options to wrap c/c++ functionality in python.Manual wrappingUsing pyrex to wrap C code.CtypesSIPBoost PythonSWIG (Simple Wrapper Interface Generator) is capable of wrapping C code with numerous other languages including Perl, Python, PHP, Ruby, Tcl, C#, Common Lisp (CLISP, Allegro, CL, UFFI, CFFI), Java, Modula-3 and OCAML. Swig also supports multiple interpreted and compiled Scheme implementations (like Guile, MzScheme, Chicken) are supported.But we will discuss its implementation with ... Read More

The main idea behind Natural Language Processing is machine can do some form of analysis or processing without human intervention at least to some level like understanding some part of what the text means or trying to say.While trying to process the text, computers needs to filter out useless or less-important data(words) from the text. In NLTK, useless words(data) are referred to as stop words.Installing Required libraryFirst you need the nltk library, just run the below command in your terminal:$pip install nltkSo we are going to remove these stop words, so they don’t take space in our database or taking ... Read More

In this, we are going to see how differently we can display our text in a very unique way using python.So let suppose I want to display “Hello, Python” and out many ways I could display my text/string (“Hello, Python”) like:Input“Hello, Python”Output 1___ ___ .__ .__ / | \ ____ | | | | ____ / ~ \_/ __ \| | | | / _ \ \ Y /\ ___/| |_| |_( ) \___|_ / \___ >____/____/\____/ /\ \/ \/ )/ __________ __ .__ \______ \___.__._/ |_| |__ ____ ____ | ___< | |\ __\ | \ / _ ... Read More

Python now provides new way to format strings, called f-strings. This features is available from Python 3.6 under PEP-498. They are so called (f-string) because of the letter ‘f’ prefix with a string. The letter ‘f’ also indicates that these f-strings can be used for formatting.Below are some of the examples to demonstrates the use of f-strings.Program#1name = 'Rajesh' age = 13 * 3 fString = f'My name is {name} and my age is {age}' print(fString) #We can use Uppercase 'F' instead of lowercase 'f'. print(F'My name is {name} and my age is {age}') #As the fString valuation is done, ... Read More

Steganography is a technique of hiding information behind the scene. It’s is not like cryptography which focuses on encrypting data(through different algorithms like SHA1, MD5 etc), steganography focuses more on hiding the data (data can be a file, image, message or video) within another file, image, message or video to avoid any attraction.So in this we’ll try to create a simple python program that hides the information behind the image without noticiable changes in the looks of the image. There are two main parts of the program – first is a decoding function that can extract secret information from an ... Read More

Python provides lots of libraries for image processing, including −OpenCV − Image processing library mainly focused on real-time computer vision with application in wide-range of areas like 2D and 3D feature toolkits, facial & gesture recognition, Human-computer interaction, Mobile robotics, Object identification and others.Numpy and Scipy libraries − For image manipuation and processing.Sckikit − Provides lots of alogrithms for image processing.Python Imaging Library (PIL) − To perform basic operations on images like create thumnails, resize, rotation, convert between different file formats etc.In this section we are going to see some basics of image processing in python.Install required library Our first step ... Read More

Folium is a very powerful python library which let you create seveal kind of Leaflet maps. As Leaflet/folium maps are interactive, so they are ideal for making dashborad building.InstallationInstalling folium is very easy using pip −$pip install foliumLike you can see from the below screenshot, you just need to type above command in your console/cmd and pip will install the folium as well as dependencies for your python installation.Basic Map#Import library import folium #Uses lat then lon. & zoomlevel 4.The bigger the zoom number, the closer in you get. mapOBJ = folium.Map(location=[17.3616, 78.4747], zoom_start = 4, tiles = 'Stamen ... Read More

Image recognition used to be done using much simpler methods such as linear regression and comparison of similarities. The results were obviously not very good, even the simple task of recognizing hand-written alphabets proved difficult. Convolution neural networks (CNNs) are supposed to be a step up from what we traditionally do by offering a computationally cheap method of loosely simulating the neural activities of a human brain when it perceives images.Convolutional neural network overviewVery similar to how we recognise different objects, computer algorithms need to go through millions of images before it is able to generalize the input and make ... Read More