Pranay Saha's repositories
Background-Remover
Welcome to the Background Remover project! This tool allows you to effortlessly replace backgrounds in images and videos, making it perfect for creating professional LinkedIn profile pictures and more.
Comic-Avatar
Converts Real human faces to Comic figures
Signature-Verification
A Deep Learning model that can be used to match signatures
DeepFaceLab
DeepFaceLab is the leading software for creating deepfakes.
DeepSolo
The official repo for [CVPR'23] "DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting" & [ArXiv'23] "DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Text Spotting"
Document_Scnner
This is my Btech major project In this Document Scanner, we added many features like manual border area and complete folder scan with an accuracy of 92.2%
EasyOCR
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
grok-1
Grok open release
keras-cv
Industry-strength Computer Vision workflows with Keras
Mangio-RVC
*CREPE+HYBRID TRAINING* A very experimental fork of the Retrieval-based-Voice-Conversion-WebUI repo that incorporates a variety of other f0 methods, along with a hybrid f0 nanmedian method.
ML-Algorithm-from-scratch
This repository contains some of the traditional Machine Learning algorithm from scratch
mlx-examples
Examples in the MLX framework
mmocr
OpenMMLab Text Detection, Recognition and Understanding Toolbox
natbot
Drive a browser with GPT-3
People-Counter
People Counter using YOLOv8 and Object Tracking |People Counting (Entering & Leaving)
PersonVehicle-Reidentification
The repository contains the work regarding the Person and Vehicle Reidentification using Symmetry Concepts
Photo-Restoration
Restoring Old-Photos and Removing Impainting
pranay-009
Config files for my GitHub profile.
rembg
Rembg is a tool to remove images background
sparrow-ocr
Data extraction from documents with ML
stable-diffusion
A latent text-to-image diffusion model
TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
U-2-Net
The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."
YOLO-World
[CVPR 2024] Real-Time Open-Vocabulary Object Detection