Ankit Shah's Projects
Benchmarking protocol for visual localization and detection with natural language queries
🧠 Implementations/tutorials of deep learning papers with side-by-side notes; including transformers (original, xl, switch, feedback), optimizers(adam, radam, adabelief), gans(dcgan, cyclegan), reinforcement learning (ppo, dqn), capsnet, sketch-rnn, etc.
Code Samples from Neural Networks for NLP
A repository of concepts related to neural networks for NLP
Python tools for analyzing the robustness properties of neural networks (NNs) from MIT ACL
Fast and production-ready question answering in Node.js
Real-time microphone noise suppression on Linux.
Code for NoisyStudent on SVHN. https://arxiv.org/abs/1911.04252
Notebooks using the Hugging Face libraries 🤗
To summarize notes from ICASSP 2019
Implementation for Negative Sampling in Semi-Supervised Learning
NUANCED is a user-centric conversational recommendation dataset that contains 5.1k annotated dialogues and 26k high-quality user turns.
Free online textbook of Jupyter notebooks for fast.ai Computational Linear Algebra course
The fundamental package for scientific computing with Python.
Machine learning, in numpy
Nvdiffrast - Modular Primitives for High-Performance Differentiable Rendering
Automatically exported from code.google.com/p/nyt-salience
NYU Deep Learning Spring 2021
Code, data and benchmark from the paper "Unmasking the Inductive Biases of Unsupervised Object Representations for Video Sequences".
Object Detection Framework for Surveillance Video
Out-of-the-box code and models for CMU's object detection and tracking system for surveillance videos.
ObjectHash for protocol buffers
Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and planes. In each video, the camera moves around and above the object and captures it from different views. Each object is annotated with a 3D bounding box. The 3D bounding box describes the object’s position, orientation, and dimensions. The dataset contains about 15K annotated video clips and 4M annotated images in the following categories: bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops, and shoes
Octave 3.8.2 compiled with --enable-64 (experimental switch) on 64-bit Ubuntu Linux Desktop 14.04 (and higher)
Benchmark datasets, data loaders, and evaluators for graph machine learning
[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment
Code for One-shot Relational Learning for Knowledge Graphs (EMNLP18)
What Makes for End-to-End Object Detection, ICML2021
Common utilities for ONNX converters
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator