Stars
A beautiful, simple, clean, and responsive Jekyll theme for academics
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 ;)
[CVPR 2022] Official code for the paper: "A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration"
pyqtlet2 extends pyqtlet which initially brought Leaflet maps to PyQt5 and PySide6.
The most cited deep learning papers
Source code for "Improved Trainable Calibration Method for Neural Networks on Medical Imaging Classification" accepted to BMVC2020.
A repository of links with advice related to grad school applications, research, phd etc
DRIFT is a tool for Diachronic Analysis of Scientific Literature.
A plugin that will automatically download PDFs of zotero items from sci-hub
Code for the paper "When to Trust Your Model: Model-Based Policy Optimization"
Python adaptation of the Range-dependent Acoustic Model (RAM).
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Open-Source code for Project Eva: A Targeted Testing Protocol for Greece
Massively parallel rigidbody physics simulation on accelerator hardware.
JAX - A curated list of resources https://github.com/google/jax
3.8% and 18.3% on CIFAR-10 and CIFAR-100 A2A4
Model-agnostic posthoc calibration without distributional assumptions
Code for the paper "Calibrating Deep Neural Networks using Focal Loss"
borb is a library for reading, creating and manipulating PDF files in python.
Automatic fingering generator for piano scores
Libraries, tools and tasks created and used at DeepMind Robotics.
openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.
Open source code for AlphaFold 2.
Open Source Neural Machine Translation and (Large) Language Models in PyTorch
Design and implementation of deep learning models trained for automated annotation of ecg signal with various preprocessing steps.
Falken provides developers with a service that allows them to train AI that can play their games
Shared repository for open-sourced projects from the Google AI Language team.
This is where I put things I find useful that speed up my work with Machine Learning. Ever looked in your old projects to reuse those cool functions you created before? Well, this repo is designed …
A game theoretic approach to explain the output of any machine learning model.