Machine Learning and Deep Learning Projects

A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow

Project Highlights:

• Anime Face Generation Using DCGAN: Dive into the world of anime art with this project. Using Deep Convolutional Generative Adversarial Networks (DCGAN), create unique and captivating anime-style faces that will spark your creativity.

• Anime Face Generation Using VAE: Explore the enchanting realm of anime face generation with the Variational Autoencoder (VAE). Craft expressive and imaginative anime faces, and let your artistic imagination run wild.

• Cataract Detection: Enhance medical diagnostics with Cataract Detection. Employ CNN, and Transfer Learning techniques to identify cataracts and contribute to early and accurate diagnosis.

• Credit Card Churn: Tackle financial analysis with Credit Card Churn prediction. Employ machine learning and deep learning to anticipate and address credit card churn, ensuring better customer retention strategies.

• Credit Card Fraud Detection: Safeguard financial transactions with Credit Card Fraud Detection. Employ machine learning and deep learning to detect and prevent fraudulent activities, providing secure payment environments.

• DeepDream: Unlock the surreal with DeepDream. Venture into the world of neural networks and create captivating, dream-like images that defy reality.

• Diabetes Prediction: Promote health and wellness with Diabetes Prediction. Employ machine learning and deep learning to anticipate and manage diabetes, making strides in early detection and prevention.

• Emotion Detection: Explore the realm of human emotions with Emotion Detection. Utilize CNN and Transfer Learning techniques to identify and understand emotions, opening doors to innovative applications.

• Heart Disease: Prioritize cardiovascular health with Heart Disease prediction. Leverage machine learning and deep learning to assess and predict heart conditions, contributing to better patient care.

• IMDB Movie Reviews: Delve into the world of film critique with IMDB Movie Reviews. Analyze user reviews to gain insights into the sentiment of movie reviews.

• Image Caption Generator: Combine the power of computer vision and natural language processing with the Image Caption Generator. Create descriptions for images, making content more accessible and informative.

• Language Detection: Identify languages effortlessly with Language Detection. Employ machine learning and deep learning techniques to identify languages.

• MNIST Classification: Enhance your understanding of image classification with MNIST Classification. Utilize deep learning to identify handwritten digits with high accuracy.

• Mall Customer Segmentation: Revolutionize marketing strategies with Mall Customer Segmentation. Use data analysis and clustering algorithms to categorize customers.

• Movie Genre Prediction: Predict movie genres with Movie Genre Prediction. Apply machine learning and deep learning techniques to analyze a given portion of a movie script and make genre classifications.

• Multiclass Text Classification: Master the art of text classification with Multiclass Text Classification. Employ natural language processing techniques to categorize text data effectively.

• Photo to Sketch Using Autoencoder: Transform photos into sketches with Photo to Sketch Using Autoencoder. Explore artistic rendering and image manipulation using autoencoders.

• Pneumonia Detection: Enhance healthcare with Pneumonia Detection. Employ CNN, and Transfer Learning techniques to detect pneumonia, improving early diagnosis and patient care.

• Receipt to OCR: Transform the way you handle receipts with Receipt to OCR. This project goes beyond mere optical character recognition (OCR) by isolating and extracting receipts from images with various objects and complex backgrounds. Leveraging advanced perspective transformation techniques, it ensures accurate data extraction and simplifies the process of digitizing your receipts.

• Salary Prediction: Predict salary ranges and gain insights into compensation trends with my Salary Prediction project. Using regression analysis, I provide a data-driven approach to estimating salaries based on various factors

• Spam Detection: Keep your inbox clean and efficient with Spam Detection. Employ machine learning and deep learning techniques to filter out unwanted emails and streamline your communication.

• Spot the Nuclei Using U-Net: Advance medical diagnostics with Spot the Nuclei Using U-Net. Leverage deep learning to identify cell nuclei, contributing to research and healthcare.

• Style Transfer: Unleash your creativity with Style Transfer. Merge artistic styles onto your images and give them a unique, artistic flair.

• Text Summarizer: Simplify complex text with Text Summarizer. Utilize abstractive summarization, and extractive summarization to generate concise and informative summaries.

• Traffic Signs Detection: Promote road safety with Traffic Signs Detection. Employ CNN and Transfer Learning techniques to identify and interpret traffic signs, enhancing driver awareness.

• Twitter Suicidal Ideation Detection: Support mental health with Twitter Suicidal Ideation Detection. Use natural language processing techniques to identify signs of potential suicidal ideation, offering early intervention and support.

• Creative Image Filters: Transform ordinary images into extraordinary pieces of art with this project! Implementing various image effects using the OpenCV library in Python, you can apply Grayscale, Cartoonize, Blurred, Sharpened, and a range of other effects. Unleash your creativity with thermal vision, watercolor, cinematic, pencil sketch, lomo, and rainbow effects.

• Driver Drowsiness Detection: Enhance road safety with Driver Drowsiness Detection! Utilize Transfer Learning and Convolutional Neural Networks with Parallel Convolution Architecture to identify and classify driver drowsiness.

• Edge Detection: Explore the fundamental task of edge detection using OpenCV. Implementing techniques like Canny, Sobel, Laplacian, Kirsch, Robinson, Prewitt, and Roberts Edge Detection, this project allows you to visualize and understand boundaries within images.

• Eye Diseases: Contribute to healthcare with a deep learning project focused on classifying eye diseases. Employ Convolutional Neural Networks (CNNs), including those with a Parallel Convolution Architecture, for accurate disease classification.

• Face & Eye Detection: Detect faces and eyes in images using OpenCV and Haar cascades. This project provides functions to identify faces, eyes, or both in an image, offering a valuable tool for applications like facial recognition and security systems.

• Image Colorization: Transform grayscale images into vibrant works of art using deep learning. This colorization tool, equipped with a pre-trained model, enables you to add color to images seamlessly, bringing life to black-and-white photographs.

• Image Compression: Efficiently compress and convert images with this project. Adjust compression quality, output format, and optionally resize images. The user-friendly graphical user interface (GUI) version simplifies the interaction for convenient image processing.

• Image Steganography: Explore the world of hidden messages with steganography using the Least Significant Bit (LSB) encoding technique. This project allows you to encode and decode secret messages within images, adding a layer of intrigue to your digital communication.

• Image to Pencil Sketch: Give your images an artistic touch by converting them into pencil sketches using OpenCV. This simple yet effective Python code can breathe new life into your photos, providing a unique and hand-drawn appearance.

• Image Watermarking: Protect your images and add a professional touch with this simple Python code for watermarking. Using the popular PIL (Pillow) library, you can easily incorporate watermarks into your images for branding or copyright purposes.

• Lane Detection for Autonomous Vehicles: Contribute to the development of autonomous vehicles with a lane detection algorithm using computer vision techniques. Highlight detected lanes on the road, providing a visual representation crucial for vehicle navigation and safety.

• Object Detection Using YOLOv3: Experience the speed and accuracy of the YOLOv3 algorithm for real-time object detection. This repository provides code for implementing object detection and showcases the versatility of YOLOv3 in identifying and tracking various objects.