onkarsus13 Goto Github PK

actionai

custom human activity recognition modules by pose estimation and cascaded inference using sklearn API

adelaidepth

This repo contains the projects: 'Virtual Normal', 'DiverseDepth', and '3D Scene Shape'. They aim to solve the monocular depth estimation, 3D scene reconstruction from single image problems.

airplane-detection-for-satellites

Airplanes are detected on images taken from satellite

audiosignalprocessingforml

Code and slides of my YouTube series called "Audio Signal Proessing for Machine Learning"

audiotext-classififcation

Audio Aware Text Classification

bert

TensorFlow code and pre-trained models for BERT

bsl1k

BSL-1K: Scaling up co-articulated sign language recognition using mouthing cues, ECCV 2020

caffeenet-object-detection

cell-detection

Used open cv and tensorflow for traing the images and segmented the traning and test result

coformer-wacv-2024

Source code of "Textual Alchemy: CoFormer for Scene Text Understanding", published in WACV 2024

concept-segmentation

Medical Imagning

consep-segmentation

crnn

crnn.pytorch

Convolutional recurrent network in pytorch

darklight-pytorch

A CNN for dark recognition

deep-learning-approch-for-hindi_mlqa

Deep learning model for Hindi QA (BIADF for hindi)

deep-virtual-try-on-with-clothes-transform

An image-based virtual try-on system with deep learning.

diff_scenetexteraser

diffctseg

efficient_net_v2

Pytorch implementation of efficientnet v2 backbone with detectron2 for object detection (Just for fun)

eluvio

fake-news-classifier

Used LSTM for detetion of fake news in the sentences

feedforward-neural-network

feednet

This paper first introduces a novel model, named FEEDNet, for accurately segmenting the nuclei in HE stained WSIs. FEEDNet is an encoder-decoder network that uses LSTM units and “feature enhancement blocks” (FE-blocks). Our proposed FE-block avoids the loss of location information incurred by pooling layers by concatenating the downsampled version of the original image to preserve pixel intensities. FEEDNet uses an LSTM unit to capture multi-channel representations compactly

glyphcontrol-release

[NeurIPS2023] This is an official inference code of the paper "GlyphControl: Glyph Conditional Control for Visual Text Generation"

handwriting-synthesis

A GAN model that can generate handwritten samples

hrnet-human-pose-estimation

This repo is copied from https://github.com/leoxiaobin/deep-high-resolution-net.pytorch

iit-jodhpu--challange

IIT-Jodhpur challange for Research Associate

image-detection

language-translation

A Gated CNN Sequence to Sequence for Machine Translation Task. Currently it is for German to English Translation.