sreekiranar Goto Github PK

augraphy

Augmentation pipeline for rendering synthetic paper printing, faxing, scanning and copy machine processes

bham_cvcw

Computer Vision & Imaging Coursework notebook

box_detection_opencv

This Repository contains a Jupyter notebook explaining how to detect checkboxes/table cells from a scanned image

clarity-ai

A simple Perplexity AI clone.

cleanlab

The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

createpackage

Python package which creates the filestructure, basic readme, setup.py with dependencies provided on your requirements file, code blocks with class and function templates with doc strings.

deepchecks

Deepchecks - Tests for Continuous Validation of ML Models & Data. Deepchecks is a Python package for comprehensively validating your machine learning models and data with minimal effort.

docbank

DocBank: A Benchmark Dataset for Document Layout Analysis

doccreator

DIAR software for synthetic document image and groundtruth generation, with various degradation models for data augmentation

docentr

DocEnTr: An end-to-end document image enhancement transformer

docquery

An easy way to extract information from documents

dolly

Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

einops

Deep learning operations reinvented (for pytorch, tensorflow, jax and others)

evals

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

examples

fastwer

A PyPI package for fast word/character error rate (WER/CER) calculation

filehandlingpython

This repository contains an example notebook which helps in finding all the image files from a given folder using my library, TreeHandler, processing it using a simple sample algorithm, color to grayscale conversion and storing the output to the given output folder retaining the file structure.

filtered-relevant-context-openapi-prompt

Here is a simple DIY experiment with a UI that can input a large text and a query from the user to return the responses from multiple models passing only the relevant context. The large file text is embedded using Sentence Transformers. Then it uses the FAISS to select the top N-matched data, pass the relevant information to OpenAPI for quality O/P

finbert

Financial Sentiment Analysis with BERT

gan-htr

This is an implementation for the paper Enhance to Read Better: A Multi-Task Adversarial Network for Handwritten Document Image Enhancement designed to enhance the document quality before the recognition process. It could be used for document cleaning and binarization. The weights are available to test the enhancement.

gc-net

ECCV 2020 paper

gpt_enabled_google_ui

A simple UI that accepts prompt from the user, modifies the prompt and displays the relevant information from the top three google search links. This is a beginners project to experiment the power of OpenAI APis applied into google to get the best of both technologies.

gradio

Create UIs for prototyping your machine learning model in 3 minutes

h2ogpt

Come join the movement to make the world's best open source GPT led by H2O.ai

labelme

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

langchain

⚡ Building applications with LLMs through composability ⚡

langchain-data-demo

Jupyter Notebook that demonstrates LLM-driven voter file data engineering, using LangChain to write SQL and Python

langchain-hub

layout-parser

A unified toolkit for Deep Learning Based Document Image Analysis

lida

Automatic Generation of Visualizations and Infographics using Large Language Models