Alankar Shukla's Projects
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
Image Composition is an important task in Computer Vision to generate high quality real life like images. Usually, when an extracted portion of an image is pasted on to another image, it does not look natural. This is because the properties of both the images are different. Image Composition can help with blending these images seamlessly.
A test repo for a ton of things
This is the project containing source codes and pre-trained models about ACL2021 Long Paper ``LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations".
Tez is a super-simple and lightweight Trainer for PyTorch. It also comes with many utils that you can use to tackle over 90% of deep learning projects in PyTorch.
A tinder bot which auto swipes for you and then sends whatsapp message on how many swipes you did. All hosted on Heroku
A list of tools to improve the git workflow for code review engineers.
π€Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.
Transformers for Natural Language Processing, published by Packt
Trax β Deep Learning with Clear Code and Speed
π‘ Build AI-powered semantic search applications
UniLM AI - Large-scale Self-supervised Pre-training across Tasks, Languages, and Modalities
Build real time speech2text web apps using OpenAI's Whisper https://openai.com/blog/whisper/
WIT (Wikipedia-based Image Text) Dataset is a large multimodal multilingual dataset comprising 37M+ image-text sets with 11M+ unique images across 100+ languages.
Object tracking implemented with YOLOv3, Deep Sort and Tensorflow.
YOLOv5 π in PyTorch > ONNX > CoreML > TFLite