Ankit Shah's Projects
π100 Times Faster Natural Language Processing in Python - iPython notebook
CMU Course 11-364: Introduction to Human Aided Deep Learning
3D ResNets for Action Recognition (CVPR 2018)
This repository contains the 3D shapes dataset, used in Kim, Hyunjik and Mnih, Andriy. "Disentangling by Factorising." In Proceedings of the 35th International Conference on Machine Learning (ICML). 2018. to assess the disentanglement properties of unsupervised learning methods.
The repo of Street View Image, Pose, and 3D Cities Dataset. Used in "Generic 3D Representation via Pose Estimation and Matching", ECCV16
The PyTorch improved version of TPAMI 2017 paper: Face Alignment in Full Pose Range: A 3D Total Solution.
The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 2020.
Visualize 3DPeople Dataset
Official PyTorch implementation of "AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks"
A collection of 300+ survey papers on Natural Language Processing (NLP) and Machine Learning (ML)
Abseil Common Libraries (C++)
Progressive matrices dataset, as described in: Measuring abstract reasoning in neural networks (Barrett*, Hill*, Santoro*, Morcos, Lillicrap), ICML2018
Free tech resources for faculty, students, researchers, life-long learners, and academic community builders for use in tech based courses, workshops, and hackathons.
π A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision
Accessibility Insights for Web
Official repository: Environmental Sound Classiο¬cation on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices
A library of reinforcement learning components and agents
Code for the paper: Audio-Visual Model Distillation Using Acoustic Images
Base image for ActEV SDL submission of CMU
Scoring software for the TRECVID Activities in Extended Video (ActEV) evaluation
A video database bridging human actions and human-object relationships
Diagnostic tools and additional visualizations from "What Actions are Needed for Understanding Human Actions in Videos?" ICCV 2017
Active Learning for Emotionally Salient Utterances and Segments using Text & Audio
Repository for NeurIPS 2020 Spotlight "AdaBelief Optimizer: Adapting stepsizes by the belief in observed gradients"
An optimizer that trains as fast as Adam and as good as SGD.