Ankit Shah's Projects
StarNet: Gradient-Free Generative Modeling
Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation
STEAL - Learning Semantic Boundaries from Noisy Annotations
MSVC's implementation of the C++ Standard Library.
A C++/Python implementation of the StreetLearn environment based on images from Street View, as well as a TensorFlow implementation of goal-driven navigation agents solving the task published in โLearning to Navigate in Cities Without a Mapโ, NeurIPS 2018
StrengthNet: Deep Learning-based Emotion Strength Assessment for Emotional Speech Synthesis
Official repo for the STRFNet system appeared in INTERSPEECH2020
A Lua package to detect reading of undeclared variables and creating of global variables.
"Learning Rhyming Constraints using Structured Adversaries. Jhamtani H., Mehta S., Carbonell J., Berg-Kirkpatrick T. EMNLP-IJCNLP (Short paper) 2019"
Spatial-Temporal Transformer for Dynamic Scene Graph Generation, ICCV2021
Just a list of free software dev tools students can get
Deep Learning Study Group
StyleGAN2 - Official TensorFlow Implementation
Style guides for Google-originated open-source projects
Code for SuDoRm-Rf networks for efficient audio source separation. SuDoRm-Rf stands for SUccessive DOwnsampling and Resampling of Multi-Resolution Features which enables a more efficient way of separating sources from mixtures.
Code to reproduce the results in the FAIR research papers "Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples" https://arxiv.org/abs/2104.13963 and "Supervision Accelerates Pre-training in Contrastive Semi-Supervised Learning of Visual Representations" https://arxiv.org/abs/2006.10803
The open source Firebase alternative. Follow to stay updated about our public Beta.
SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)
Code for "Supermasks in Superposition"
A comprehensive survey of deep metric learning and related works
SVHF-Net for Cross-modal binary matching
We provide a PyTorch implementation of the paper Voice Separation with an Unknown Number of Multiple Speakers In which, we present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art, which, as we show, is not competitive for more than two speakers.
Unofficial implementation of Swapping Autoencoder for Deep Image Manipulation (https://arxiv.org/abs/2007.00653) in PyTorch
PyTorch implementation of SwAV https//arxiv.org/abs/2006.09882
Swift for TensorFlow's high-level API, modeled after fastai
A colab that implements the Symplectic Gradient Adjustment optimizer from "The mechanics of n-player differentiable games"
Simple and Distributed Machine Learning
Tensorflow implementation of DeepMind's Tacotron-2 (without wavenet)
Code for TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning (CVPR 2019)