alexsax Goto Github PK

2d-3d-semantics

The data skeleton from Joint 2D-3D-Semantic Data for Indoor Scene Understanding

3dscenegraph

The data skeleton from "3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera" http://3dscenegraph.stanford.edu

abusive-comment-detection

academic-kickstart

📝 Easily create a beautiful website using Academic, Hugo, and Netlify

adversarialexamplesnlp

Extending adversarial examples to natural language

alexsax.github.io

aoc_22

cs224u_text_summatization

Final paper for CS224u

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

dfsdf

directfutureprediction

Code for the paper "Learning to Act by Predicting the Future", Alexey Dosovitskiy and Vladlen Koltun, ICLR 2017

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

ffcv

FFCV: Fast Forward Computer Vision (and other ML workloads!)

gym

A toolkit for developing and comparing reinforcement learning algorithms.

haskell

Haskell client for the kubernetes API. A work in progress.

homework

Assignments for CS294-112.

locality-prior

Implementation and analysis of adding a wiring cost to FC layers

lol_analysis

midlevel

midlevel-reps

Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Visuomotor Policies

mseg-api

An Official Repo of CVPR '20 "MSeg: A Composite Dataset for Multi-Domain Segmentation"

nerfstudio

A collaboration friendly studio for NeRFs

pytorch-visdom

Support powerful visual logging in PyTorch.

readthedocs.org

The source code that powers readthedocs.org

robust-policies-via-midlevel-vision

rubiks

A really simple rubiks cube solver done in a weekend for a bet

soda

Augmentation library. When your model is not exactly SotA, and you need some empty calories.

submitit

Python 3.6+ toolbox for submitting jobs to Slurm

tangerine

Tangerine: An app for assessing math and reading skills, designed for tablets but works everywhere.

taskonomy-1

Taskonomy: Disentangling Task Transfer Learning