Mohammad Shadaab's repositories
Human-Action-Recognition
A Human Action Recognition pipeline using MMAction2 and kinetics400 dataset. MMAction2 is an open-source toolbox for video understanding based on PyTorch.
Fake-Handwritten-Digits-using-DCGAN
Implementation of DCGAN model to train a neural network on mnist dataset and generate fake handwritten digits close enough to the real images from the dataset.
background_removal_DL
Files for Image and Video Background Removal using U-2-net model
DeepFashion
Apparel detection using deep learning
DeepFashion2
DeepFashion2 Dataset https://arxiv.org/pdf/1901.07973.pdf
Face_detector
This is a simple face detector app which can detect more than 15 faces in a pic with very high accuracy. I have used Flutter and Firebase ML-kit for creating this app.
Playing-Rock-Paper-Scissor-with-AI
It’s pretty simple. I’ve Fine-tuned NASNETMobile model to recognize my hand signs when it’s inside the box, so when the model predicts my hand signs, the AI randomly generates its own move. And then the winner of that move is decided. The application is designed in a way that you can decide whether to go for the best of 5, best of 10, or any number for that number.
Traffic-sign-classification
A traffic-sign-classifier made using CNN in keras with tensorflow as the backend.
cat_vs_non_cat_classifier
A 4 layer Neural Network to predict if an image is of cat or not.
contextualized-topic-models
A python package to run contextualized topic modeling
ETL_Pipeline
Data collection, transformation and loading, user data(logs) using apache airflow and neo4j graph database.
Flutter-Tutorials
Code for my YouTube Videos
pytorch-unet-segmentation
Clothing segmentation using Unet and Deep Fashion 2 dataset.
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."