Doing the asl sign language classification on static images using graph neural networks.

Overview

SignLangGNN

When GNNs 💜 MediaPipe. This is a starter project where I tried to implement some traditional image classification problem i.e. the ASL sign language classification problem. The twist here is we used the graph generated from the hand images using mediapipe. And the graph I got, I extrated the {x, y, z} co-ordinates of the nodes and also the edge index for the connecteion and translated this image classification problem to a graph classiciation problem.

Project Structure

--------- Data
            |___ CSVs # containing the co-ordinates of per images
            |___ raw
                   |___ train.csv
                   |___ valid.csv
                   |___ test.csv 
            |___ ImageData
                   |___ asl_alphabet_test
                            |___ A/
                            |___ B/ 
                            ....
                            |___ space

                   |___ asl_alphabet_train
            |
            |___ Models # the GNN models
            |___ src
                   |__ dataset.py # pyg custom data
                   |__ train.py   # train loop
                   |__ utils.py   # different utility functions
            |
            |___ main.py # from data to train
            |___ run.py  # real time video visualization

I used PyTorch geometric and PyTorch for the project. To view the results in details head over to the IPYNB folder and see the first IPYNB file. To run this project first clone this repo using this command:

git clone https://github.com/Anindyadeep/SignLangGNN

After that run the main.py using this command. Other things will be managed automatically, provided al,l the essential libraries are installed.

python3 main.py

Initial Results

The traning and validation process went smooth as with a very simple base model it gave an train acc of 0.85 and validation acc of 0.86. It also provided an test acc of 0.84. The model was run for 8 epochs. The model also gets confused with some sort of examples and we can say that it currently suffers from adverserial attacks.

Improvements

These are the improvements we can do with this project:

  1. Improved GNN models. We can make more robust and complex models and improve the performance.

  2. Adding edge features. Some of the edge features like distance between two nodes and the angle between two nodes could produce some potential improvements to the performance of our model.

Future Works

Using Temporal Graph Neural Nets could make more robust and accurate model for this kind of problem. But for that we need temporal data like videos instaed of images, so that we could generate static temporal graphs and compute on them as a dynamic graph sequence problem.

Owner
Deep learning enthusiast, like to know something new every time....
Multi-modal Vision Transformers Excel at Class-agnostic Object Detection

Multi-modal Vision Transformers Excel at Class-agnostic Object Detection

Muhammad Maaz 206 Jan 04, 2023
The Self-Supervised Learner can be used to train a classifier with fewer labeled examples needed using self-supervised learning.

Published by SpaceML • About SpaceML • Quick Colab Example Self-Supervised Learner The Self-Supervised Learner can be used to train a classifier with

SpaceML 92 Nov 30, 2022
UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model

UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model Official repository for the ICCV 2021 paper: UltraPose: Syn

MomoAILab 92 Dec 21, 2022
Official implementation of "Motif-based Graph Self-Supervised Learning forMolecular Property Prediction"

Motif-based Graph Self-Supervised Learning for Molecular Property Prediction Official Pytorch implementation of NeurIPS'21 paper "Motif-based Graph Se

zaixi 71 Dec 20, 2022
CoSMA: Convolutional Semi-Regular Mesh Autoencoder. From Paper "Mesh Convolutional Autoencoder for Semi-Regular Meshes of Different Sizes"

Mesh Convolutional Autoencoder for Semi-Regular Meshes of Different Sizes Implementation of CoSMA: Convolutional Semi-Regular Mesh Autoencoder arXiv p

Fraunhofer SCAI 10 Oct 11, 2022
Utilizes Pose Estimation to offer sprinters cues based on an image of their running form.

Running-Form-Correction Utilizes Pose Estimation to offer sprinters cues based on an image of their running form. How to Run Dependencies You will nee

3 Nov 08, 2022
Classic Papers for Beginners and Impact Scope for Authors.

There have been billions of academic papers around the world. However, maybe only 0.0...01% among them are valuable or are worth reading. Since our limited life has never been forever, TopPaper provi

Qiulin Zhang 228 Dec 18, 2022
Mmdet benchmark with python

mmdet_benchmark 本项目是为了研究 mmdet 推断性能瓶颈,并且对其进行优化。 配置与环境 机器配置 CPU:Intel(R) Core(TM) i9-10900K CPU @ 3.70GHz GPU:NVIDIA GeForce RTX 3080 10GB 内存:64G 硬盘:1T

杨培文 (Yang Peiwen) 24 May 21, 2022
SPRING is a seq2seq model for Text-to-AMR and AMR-to-Text (AAAI2021).

SPRING This is the repo for SPRING (Symmetric ParsIng aNd Generation), a novel approach to semantic parsing and generation, presented at AAAI 2021. Wi

Sapienza NLP group 98 Dec 21, 2022
The personal repository of the work: *DanceNet3D: Music Based Dance Generation with Parametric Motion Transformer*.

DanceNet3D The personal repository of the work: DanceNet3D: Music Based Dance Generation with Parametric Motion Transformer. Dataset and Results Pleas

南嘉Nanga 36 Dec 21, 2022
Implementation of ICCV21 paper: PnP-DETR: Towards Efficient Visual Analysis with Transformers

Implementation of ICCV 2021 paper: PnP-DETR: Towards Efficient Visual Analysis with Transformers arxiv This repository is based on detr Recently, DETR

twang 113 Dec 27, 2022
Wide Residual Networks (WideResNets) in PyTorch

Wide Residual Networks (WideResNets) in PyTorch WideResNets for CIFAR10/100 implemented in PyTorch. This implementation requires less GPU memory than

Jason Kuen 296 Dec 27, 2022
Official Pytorch implementation of ICLR 2018 paper Deep Learning for Physical Processes: Integrating Prior Scientific Knowledge.

Deep Learning for Physical Processes: Integrating Prior Scientific Knowledge: Official Pytorch implementation of ICLR 2018 paper Deep Learning for Phy

emmanuel 47 Nov 06, 2022
Official PyTorch implementation of "Physics-aware Difference Graph Networks for Sparsely-Observed Dynamics".

Physics-aware Difference Graph Networks for Sparsely-Observed Dynamics This repository is the official PyTorch implementation of "Physics-aware Differ

USC-Melady 46 Nov 20, 2022
exponential adaptive pooling for PyTorch

AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling Abstract Pooling layers are essential building blocks of Convolutional Ne

Alexandros Stergiou 55 Jan 04, 2023
pytorch implementation of the ICCV'21 paper "MVTN: Multi-View Transformation Network for 3D Shape Recognition"

MVTN: Multi-View Transformation Network for 3D Shape Recognition (ICCV 2021) By Abdullah Hamdi, Silvio Giancola, Bernard Ghanem Paper | Video | Tutori

Abdullah Hamdi 64 Jan 03, 2023
Machine Learning in Asset Management (by @firmai)

Machine Learning in Asset Management If you like this type of content then visit ML Quant site below: https://www.ml-quant.com/ Part One Follow this l

Derek Snow 1.5k Jan 02, 2023
Real-time multi-object tracker using YOLO v5 and deep sort

This repository contains a two-stage-tracker. The detections generated by YOLOv5, a family of object detection architectures and models pretrained on the COCO dataset, are passed to a Deep Sort algor

Mike 3.6k Jan 05, 2023
Pre-trained NFNets with 99% of the accuracy of the official paper

NFNet Pytorch Implementation This repo contains pretrained NFNet models F0-F6 with high ImageNet accuracy from the paper High-Performance Large-Scale

Benjamin Schmidt 133 Dec 09, 2022
Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification

Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification This repository is the official implementation of [Dealing With Misspeci

0 Oct 25, 2021