Atharva Sehgal's repositories
apex
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
audio-visualizer
CS 225 Fall 2020 Embedding Systems Honors: Guide to making a Raspberry Pi based Bluetooth audio visualizer.
Cognitive-Speech-TTS
Microsoft Text-to-Speech API Android SDK and sample code in several languages, part of Cognitive Services.
emosandy
Hurricane data + emotion detection model = interesting stuff.
cordic
Arbitrary-precision floating-point and fixed-point math library based on CORDIC shifts and adds
darknet
YOLOv4v / Scaled-YOLOv4 - Neural Networks for Object Detection (Windows and Linux version of Darknet )
diffRASP
Class project for James' Class
FloatX
Header-only C++ library for low precision floating point type emulation.
image-similarity-using-deep-ranking
🖼️ **Unofficial** PyTorch implementation of "Learning Fine-grained Image Similarity with Deep Ranking" (arXiv:1404.4661)
kamome
The front-end components of karasu.
karasu
A self-hosted remote communication system designed for math discussions.
mark-text-images
Images from notes.
MFixedPoint
MFixedPoint is a header-only fixed-point C++ library suitable for fast arithmetic operations on systems which don't have a FPU (e.g. embedded systems).. Suitable for performing computationally intensive operations on a computing platform that does not have a floating-point unit (like most smaller embedded systems, such as Cortex-M3, CortexM0, ATmega, PSoC 5, PSoC 5 LP, PSoC 4, Arduino platforms e.t.c). Common applications include BLDC motor control and image processing. Best performance on a 32-bit or higher architecture (although 8-bit architectures should still be fine).
newt
Natural World Tasks
Probabilistic-Programming-and-Bayesian-Methods-for-Hackers
aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Scene-Graph-Benchmark.pytorch
A new codebase for popular Scene Graph Generation methods (2020). Visualization & Scene Graph Extraction on custom images/datasets are provided. It's also a PyTorch implementation of paper “Unbiased Scene Graph Generation from Biased Training CVPR 2020”
stitch
A scalable abstraction learning library
vdp
[draft](https://arxiv.org/abs/1907.05878)
vision
Datasets, Transforms and Models specific to Computer Vision