-
New York University
- New York City
- https://www.linkedin.com/in/john-shin-1b2a9776/
Stars
Karras et al. (2022) diffusion models for PyTorch
This repository contains the code for our paper "Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs".
LAVIS - A One-stop Library for Language-Vision Intelligence
PyTorch implementation for "Temperature as Uncertainty in Contrastive Learning" (https://arxiv.org/abs/2110.04403).
HOTA (and other) evaluation metrics for Multi-Object Tracking (MOT).
BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models
The simplest, fastest repository for training/finetuning medium-sized GPTs.
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Tools for understanding how transformer predictions are built layer-by-layer
Code for Auditing Visualizations: Transparency Methods Struggle to Detect Anomalous Behavior
Google Research
Making Sense of CNNs: Interpreting Deep Representations & Their Invariances with Invertible Neural Networks
PyTorch implementation of Mahendran & Vedaldi, 2015: "Understanding Deep Image Representations by Inverting Them"
PyTorch implementation of Barlow Twins.
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
Denoising Diffusion Probabilistic Models
Github Pages template for personal, portfolio-based websites; forked from mmistakes/minimal-mistakes
❗ This is a read-only mirror of the CRAN R package repository. ecp — Non-Parametric Multiple Change-Point Analysis of Multivariate Data
Latent space autoregression for novelty detection.
My attempt at reproducing the paper Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection
pytorch tutorial for beginners
VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.
Python/STAN Implementation of Multiplicative Marketing Mix Model, with deep dive into Adstock (carry-over effect), ROAS, and mROAS
Robyn is an experimental, AI/ML-powered and open sourced Marketing Mix Modeling (MMM) package from Meta Marketing Science. Our mission is to democratise modeling knowledge, inspire the industry thr…
LightweightMMM 🦇 is a lightweight Bayesian Marketing Mix Modeling (MMM) library that allows users to easily train MMMs and obtain channel attribution information.