Ashish Abraham's Projects
A simple CLI tool to convert the images to ASCII art with rust π¦π
Neural Style Transfer featuring styles of world's greatest artists.
Config files for my GitHub profile.
Checkout my Portfolio π
A curated list of awesome READMEs
ML powered tool to identify 120 breeds of dogs. Network architecture is a ResNet18 fine tuned to classify dogs. Code for fine tuning and feature extraction of other architectures included in scripts.
Metal Casting Quality Inspection with CNN, built using TensorFlow in Python
[CVPR 2021] Teachers Do More Than Teach: Compressing Image-to-Image Models (CAT)
Our experiments with Common Voice Turkish datasets, colab notebooks with training results.
Notes, programming assignments and quizzes from all courses within the Coursera Deep Learning specialization offered by deeplearning.ai: (i) Neural Networks and Deep Learning; (ii) Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization; (iii) Structuring Machine Learning Projects; (iv) Convolutional Neural Networks;
Leveraging code LLMs to build and use your own personal coding assistant on VSCode π
A Retrieval-Augmented Generation (RAG) System for PDF Chat using Qdrant Vector Database.
A face detection model build using transfer learning on the MobileNet architecture. The model has then been implemented using openCV to detect faces in live streams.
DeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral
A Random Forest Regressor machine learning model that determines gold price per gram in USD corresponding to S&P500 index, USD/EUR value, oil-ETF, and other dependencies.
Create UIs for your machine learning model in Python in 3 minutes
A heart failure prediction model built on Scikit-Learn that analyses user input data from a simple lab report to alert you of heart failure risk.
A python program implementing Optical Character Recognition using OpenCV, PIL, OS libraries which takes jpg and png formats of documents-identifies lines, words and characters-crops it accordingly.
Python scripts to detect and segment face using opencv, pixellib. Separate scripts for face detction and instance segmentation using Mask R-CNN and Xception-65.
Predict fuel consumption of classic vehicles from the 70s and 80s, enabling the user to consider necessary factors during their restoration.
ML-capsule is a Project for beginners and experienced data science Enthusiasts who don't have a mentor or guidance and wish to learn Machine learning. Using our repo they can learn ML, DL, and many related technologies with different real-world projects and become Interview ready.
12 weeks, 25 lessons, 50 quizzes, classic Machine Learning for all
Open Source Computer Vision Library
This project aims to automatically detect surface defects in Hot-Rolled Steel Strips such as rolled-in scale, patches, crazing, pitted surface, inclusion and scratches. A CNN is trained on the NEU Metal Surface Defects Database which contains 1800 grayscale images with 300 samples of each of the six different kinds of surface defects.
RAG (Retrieval Augmented Generation) and vector search to translate natural language into SQL queries for PostgreSQL databases.
Django REST API for extracting insights from resumes in PDF format.
Extracting keywords from a job description and looking for them in a resume
The repo for Saturday Hack Night 24-07-2021