1) Ultra-Light and Fast Face Detector

This is a phenomenal open-source release. Don’t be put off by the Chinese page (you can easily translate it into English). This is an ultra-light version of a face detection model – a really useful application of computer vision.

The size of this face detection model is just 1MB! I honestly had to read that a few times to believe it.

This model is a lightweight face detection model for edge computing devices based on the lib face detection architecture. There are two versions of the model:

1. Version-slim (slightly faster simplification)

2. Version-RFB (with the modified RFB module, higher precision)

This is a great repository to get your hands on. We don’t typically get such a brilliant opportunity to build computer vision models on our local machine – let’s not miss this one.

If you’re new to the world of face detection and computer vision, we recommend this project.

2) T5: Text-to-Text Transfer Transformer by Google Research

How could Google every stay out of a “latest breakthroughs” list? They have allocated vast amounts of money into machine learning, deep learning and reinforcement learning research and their results reflect that. I’m delighted they open-source their projects from time to time – there’s a lot to learn from them.

T5, short for Text-to-Text Transfer Transformer, is powered by the concept of transfer learning. In this latest NLP project, the developers behind T5 introduce a unified framework that converts every language problem into a text-to-text format.

This framework achieves state-of-the-art results on various benchmarks in the tasks of summarization,  question answering, text classification, and more. They have open-sourced the dataset, pre-trained models, and the code behind T5 in this GitHub repository.

As the Google folks put it, “T5 can be used as a library for future model development by providing useful modules for training and fine-tuning (potentially huge) models on mixtures of text-to-text tasks.”

NLP is the hottest field right now, you really don’t want to miss out on these developments.

3) Gaussian YOLOv3: An Accurate and Fast Object Detector for Autonomous Driving

I’m a huge fan of self-driving cars. But progress has been slow due to a variety of reasons (architecture, public policy, acceptance among the community, etc.). So it’s always heartening to see any framework or algorithm that promises a better future for these autonomous cars.

Object detection algorithms are at the heart of these autonomous vehicles – I’m sure you already know that. And detecting objects at high accuracy with fast inference speed is vital to ensure safety. All this has been around for a few years now, so what differentiates this project?

"The Gaussian YOLOv3 architecture improves the system’s detection accuracy and supports real-time operation (a critical aspect). Compared to a conventional YOLOv3, Gaussian YOLOv3 improves the mean average precision (mAP) by 3.09 and 3.5 on the KITTI and Berkeley deep drive (BDD) data sets, respectively."

4) Few-Shot vid2vid by NVIDIA

I came across the concept of video-to-video (vid2vid) synthesis last year and was blown away by its effectiveness. vid2vid essentially converts a semantic input video to an ultra-realistic output video. This idea has come a long way since then.

But there are currently two primary limitations with these vid2vid models:

• They require humongous amounts of training data

• These models struggle to generalize beyond the training data

That’s where NVIDIA’s Few-Shot viv2vid framework comes in. As the creator state, we can use it for “generating human motions from poses, synthesizing people talking from edge maps, or turning semantic label maps into photo-realistic videos.

5)  Movie Recommendation System Project

The aim of this interesting Data Science project including code is to build a recommendation system that recommends movies to the users.

Let’s understand this with an example. Have you ever been on an online streaming platform like Netflix or Amazon Prime? If yes, then you must have noticed that after some time these platform starts recommending you different movies and TV shows according to your genre preference. This project in R programming is designed to help you understand the functioning of how a recommendation system works.

6)  Customer Segmentation using Machine Learning

Customer segmentation is one of the most essential applications for all customer-facing industries (B2C companies). It uses the clustering algorithm of Machine Learning that allows companies to target the potential user base and also they can identify the best customers.

It uses clustering techniques through which companies can identify the several segments of customers allowing them to target the potential user base for a specific campaign. Customer segmentation also uses K-means clustering algorithm which is essential for clustering unlabeled dataset.

7)   Traffic Signs Recognition

Achieve accuracy in self-driving cars technology with Data Science Project on Traffic Signs Recognition using CNN with Source Code 

Traffic signs and rules are very important that every driver must follow to avoid any accident. To follow the rule one must first understand how the traffic sign looks like. A human has to learn all the traffic signs before they are given the license to drive any vehicle. But now autonomous vehicles are rising and there will be no human drivers in the upcoming future. In the Traffic signs recognition project, you will learn how a program can identify the type of traffic sign by taking an image as input. The German Traffic signs recognition benchmark dataset (GTSRB) is used to build a Deep Neural Network to recognize the class a traffic sign belongs to. We also build a simple GUI to interact with the application.

Language: Python

Dataset: GTSRB (German Traffic Sign Recognition Benchmark)

8)  Uber Data Analysis Project

Data is the oil for uber. With data analysis tools and great insights, Uber improve its decisions, marketing strategy, promotional offers and predictive analytics.

With more than 15 million rides per day across 600 cities in 65 countries, Uber is growing rapidly with Data Science starting from data visualization and gaining insights that help them to craft better decisions. Data Science tools play a key role in every operation of Uber.

9)  Credit Card Fraud Detection Project in R/Python

The credit card fraud detection project uses machine learning and R programming concepts.

The aim of this project is to build a classifier that can detect credit card fraudulent transactions using a variety of machine learning algorithms that will be able to discern fraudulent from non-fraudulent ones. Learn how to implement machine learning algorithms and data analysis and visualization to detect fraudulent transactions from other types of data from – Data Science Project on Credit Card Fraud Detection

10)  Fake News Detection

Drive your career to new heights by working on Data Science Project for Beginners  – Detecting Fake News with Python

A king of yellow journalism, fake news is false information and hoaxes spread through social media and other online media to achieve a political agenda. In this data science project idea, we will use Python to build a model that can accurately detect whether a piece of news is real or fake. We’ll build a TfidfVectorizer and use a PassiveAggressiveClassifier to classify news into “Real” and “Fake”. We’ll be using a dataset of shape 7796×4 and execute everything in Jupyter Lab.

Language: Python

Dataset/Package: news.csv

11)   Detecting Parkinson’s Disease

Put your best foot forward by working on Data Science Project Idea – Detecting Parkinson’s Disease with XGBoost

We have started using data science to improve healthcare and services – if we can predict a disease early, it has many advantages on the prognosis. So in this data science project idea, we will learn to detect Parkinson’s Disease with Python. This is a neurodegenerative, progressive disorder of the central nervous system that affects movement and causes tremors and stiffness. This affects dopamine-producing neurons in the brain and every year, it affects more than 1 million individuals in India.

Language: Python

Dataset/Package: UCI ML Parkinsons dataset

12)  Speech Emotion Recognition

Explore the complete implementation of Data Science Project Example  – Speech Emotion Recognition with Librosa

Let’s learn to use different libraries now. This data science project uses librosa to perform Speech Emotion Recognition. SER is the process of trying to recognize human emotion and affective states from speech. Since we use tone and pitch to express emotion through voice, SER is possible; but it is tough because emotions are subjective and annotating audio is challenging. We’ll use the mfcc, chroma, and mel features and use the RAVDESS dataset to recognize emotion on. We’ll build an MLPClassifier for the model.

Language: Python

Dataset/Package: RAVDESS dataset

13)   Gender and Age Detection

Put the pedal to the metal & impress recruiters with ultimate Data Science Project – Gender and Age Detection with OpenCV

This is an interesting data science project with Python. Using just one image, you’ll learn to predict the gender and age range of an individual. In this, we introduce you to Computer Vision and its principles. We’ll build a Convolutional Neural Network and use models trained by Tal Hassner and Gil Levi for the Adience dataset. We’ll use some .pb, .pbtxt, .prototxt, and .caffemodel files along the way.

Language: Python

Dataset/Package: Adience

14)  Driver Drowsiness detection

Drive your career to new heights by working on Top Data Science Project  – Drowsiness Detection System with OpenCV & Keras

Drowsy driving is extremely dangerous and around thousands of accidents happen each year due to drivers falling asleep while driving. In this Python project, we will build a system that can detect sleepy drivers and also alert them by beeping alarm.

This project is implemented using Keras and OpenCV. We will use OpenCV for face and eye detection and with Keras, we will classify the state of the eye (Open or Close) using Deep neural network techniques.

15)  Image Caption Generator

Check the complete implementation of data science project with source code – Image Caption Generator with CNN & LSTM

Describing what’s in an image is an easy task for humans but for computers, an image is just a bunch of numbers that represent the color value of each pixel. So this is a difficult task for computers to understand what is in the image and then generating the description in Natural language like English is another difficult task. This project uses deep learning techniques where we implement a Convolutional neural network (CNN) with Recurrent Neural Network( LSTM) to build the image caption generator.

Dataset: Flickr 8K

Language: Python

Framework: Keras

16)  Credit Card Fraud Detection

Put your best foot forward by working on Data Science Project Idea  – Credit Card Fraud Detection with Machine Learning

By now, you’ve begun to understand the methods and concepts. Let’s move on to some advanced data science projects. In this project, we’ll use R with algorithms like Decision Trees, Logistic Regression, Artificial Neural Networks, and Gradient Boosting Classifier. We’ll use the Card Transactions dataset to classify credit card transactions into fraudulent and genuine. We’ll fit the different models and plot performance curves for them.

Language: R

Dataset/Package: Card Transactions dataset

17)  Movie Recommendation System

Explore the implementation of the Best Data Science Project with Source Code- Movie Recommendation System Project in R

In this data science project, we’ll use R to perform a movie recommendation through machine learning. A recommendation system sends out suggestions to users through a filtering process based on other users’ preferences and browsing history. If A and B like Home Alone and B likes Mean Girls, it can be suggested to A – they might like it too. This keeps customers engaged with the platform.

Language: R

Dataset/Package: MovieLens dataset

18)   Customer Segmentation

Put the medal to the pedal & impress recruiters with Data Science Project (Source Code included) – Customer Segmentation with Machine Learning

Customer Segmentation is a popular application of unsupervised learning. Using clustering, companies identify segments of customers to target the potential user base. They divide customers into groups according to common characteristics like gender, age, interests, and spending habits so they can market to each group effectively. We’ll use K-means clustering and also visualize the gender and age distributions. Then, we’ll analyze their annual incomes and spending scores.

Language: R

Dataset/Package: Mall_Customers dataset

19) Exploratory Data Analysis 

20) Interactive Data Visualizations 

21) Data Fusion