Harshit Muhal's repositories
Image-Captioning
Given any real-world image, this project generates an appropriate caption using Machine Learning/Deep Learning.
IMDb-review-sentiment-analysis
Implemented multiple CNN-LSTM based neural networks. Achieved maximum accuracies for the network architecture which used a CNN-LSTM with combined kernels from multiple branches and other architecture that used a CNN-LSTM neural network with a residual connection. Achieved maximum accuracy of 89.39%.
Visual-Similarity-Based-Recommendation-System
It is a very basic recommender system that shows products similar to a given product based on their visual similarities. The pre-trained CNN models from Keras are used to extract the image features. To calculate the similarity between images cosine similarity is calculated for these image feature vectors. VGG16, ResNet50, VGG19, Xception, MobileNet models are used as feature extractors on the same corpus of images, and results are visualized separately for each model.
Tetris-Computer-Graphics-Project
Implemented Tetris game using pygame library.
Dominant-Color-Extraction-using-KMeans
Used KMeans algorithm to find the most dominant colors of a given image and created a new image with these dominant colors.
Emoji-Predictor
Implementation of a basic emoji predictor using stacked LSTM on a small dataset.
Handwritten-digit-image-Generation-using-DCGAN
Handwritten digit image Generation using DCGAN.
Cash-Settlement-Quiz
Webapp that generates random network of graph representing cash transactions among friends and also provides solution with minimised cashflow .It uses vis.js browser based library to visualise the problem graph and solution graph.
Competitive-Programming-Algorithms
The purpose of this repository is to get all the Algorithms required for Competitive Programming at one place. This will be very helpful. Also one can contribute to this repository and learn something from this.
Django
This repo contains code for mini django projects built as a part of learning Django Framework
face-detection-and-recognition
face detection and recognition using opencv
Image-Captioning-API
API for image captioning project using FastAPI framework.
InterviewBit
InterviewBit Programming Solutions
ML
This repo contains code for algorithms, frameworks, and tools coded by me as a part of learning Machine Learning, Deep Learning, Transfer Learning and Natural Language Processing.
Multi-Layer-Perceptron
implementation of a simple 3 layer perceptron from scratch.
Neural-Machine-Translation
Using Neural Machine Translation for translating English sentences to Hindi.
NumPy
implementation of some basic functions in NumPy which a library for the Python programming language, adding support for large, multi-dimensional arrays and matrices, along with a large collection of high-level mathematical functions to operate on these arrays
NXN-Sudoku
Generates NXN Random Sudoku puzzles and also provide solution to these puzzles using backtracking and bitmasking.
snake-game
snake game web app Using HTML and javascript
system-design-primer
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
text-to-speech
program to convert given text to speech
TextEditor
Simple text editor Webapp using stacks data structure capable of undo and clear operation.
Two-stage-Customer-Segmentation
In this project, we used the K-means algorithm to perform customer segmentation on data and tried to analyze the results with regards to how many clusters give us the best results. Then we trained a neural network on the data obtained from clustering to classify new samples so as to present the problem in a supervised way instead of finding clusters using K-means in an unsupervised fashion. This saves time as we do not have to perform clustering over all the data repeatedly.