Deep Learning

Optimization framework developed in Pytorch, allowing calibration, and joint optimization of optics and deep learning models.

Awesome Low-light Enhancement

Say hello to Alto, a little teachable object! Alto is designed to demonstrate the most basic aspects of machine learning (ML) by building a machine you can teach yourself. Alto uses the Coral USB Accelerator and Raspberry Pi to he

Asteroid is a Pytorch-based audio source separation toolkit that enables fast experimentation on common datasets. It comes with a source code that supports a large range of datasets and architectures, and a set of recipes to repro

The GreenGuard project is a collection of end-to-end solutions for machine learning problems commonly found in monitoring wind energy production systems. Most tasks utilize sensor data emanating from monitoring systems. We utilize

A dataset of 222 digital musical scores aligned with 1068 performances (more than 92 hours) of Western classical piano music.

Combining smooth constraint for building DAG with normalizing flow in order to replace autoregressive transformations while keeping tractable Jacobian.

MOCA (Modular Object-Centric Approach) addresses the task of long horizon instruction following with a modular architecture that decouples a task into visual perception and action policy prediction.

This repository contains PyTorch evaluation code, training code and pretrained models for PVT (Pyramid Vision Transformer). Like ResNet, PVT is a pure transformer backbone that can be easily plugged in most downstream task models.

MEAD: A Large-scale Audio-visual Dataset for Emotional Talking-face Generation [ECCV2020]

PyTorch implementation of the paper "SuperLoss: A Generic Loss for Robust Curriculum Learning" in NIPS 2020.

Revisiting Rainbow: Promoting more insightful and inclusive deep reinforcement learning research

This repository contains the paired word-tag data required to train a word-to-label sequence tagger (as described in our paper). In addition, the generated images from the proposed TReCS model are also provided for the LN-COCO and

QuarkDet lightweight object detection in PyTorch .Real-Time Object Detection on Mobile Devices.

This is the official PyTorch package for the discrete VAE used for DALL·E.

Kalman Filter book using Jupyter Notebook. Focuses on building intuition and experience, not formal proofs. Includes Kalman filters,extended Kalman filters, unscented Kalman filters, particle filters, and more. All exercises incl

DF21 is an implementation of Deep Forest 2021.2.1

Code and files to go along with CS329s machine learning model deployment tutorial.

RLStructures is a library to facilitate the implementation of new reinforcement learning algorithms. It includes a library, a tutorial, and different RL algorithms provided as examples.

Code for Langer et al. "Domain Transfer for Semantic Segmentation of LiDAR Data using Deep Neural Networks", IROS, 2020.

Deep Graph Library(DGL)은 기존의 DL 프레임워크(e.g. PyTorch, MXNet, Gluon 등)위에 그래프 뉴럴 네트워크 모델을 간편하게 구현하기 위한 Python 패키지입니다. DGL은 아키텍쳐 디자인 상에서 NetworkX의 API와 패러다임을 따르고 지향하고 있습니다.

TIGER is a Python toolbox to conduct graph vulnerability and robustness research. TIGER contains numerous state-of-the-art methods to help users conduct graph vulnerability and robustness analysis on graph structured data.

ProbNumDiffEq.jl provides probabilistic ODE solvers for the DifferentialEquations.jl ecosystem.

A Flax (Linen) implementation of ResNet (He, Kaiming, et al. 2015), ResNet-D (He, Tong et al. 2020), and ResNest (Zhang, Hang et al. 2020). The code is modular so you can mix and match the various stem, residual, and bottleneck im

Metatheory.jl is a general purpose metaprogramming and algebraic computation library for the Julia programming language, designed to take advantage of the powerful reflection capabilities to bridge the gap between symbolic mathema

Experiments on unsupervised point cloud reconstruction.

ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds

Pre-trained NFNets with 99% of the accuracy of the official paper "High-Performance Large-Scale Image Recognition Without Normalization".

The official implementation of "Puzzle-CAM: Improved localization via matching partial and full features".

This repository contains the source code of our ACL 2020 paper Screenplay Summarization Using Latent Narrative Structure.

Learning Cascaded Convolutional Networks for Blind Single Image Super-Resolution

Official implementation of the paper Image Generators with Conditionally-Independent Pixel Synthesis

The official implementation of the Molecule Attention Transformer.