Deep Learning

This application was developed to detect cars in Forza Horizon 4 gameplay video

Implementation of Nyström Self-attention, from the paper Nyströmformer

The Semantic Scholar Search Reranker

Code and Data for our EMNLP-2020 paper Weakly-Supervised Aspect-Based Sentiment Analysis via Joint Aspect-Sentiment Topic Embedding.

OV²SLAM is a Fully Online and Versatile Visual SLAM for Real-Time Applications

bsnes is a multi-platform Super Nintendo (Super Famicom) emulator, originally developed by Near, which focuses on performance, features, and ease of use.

BudgetML – Deploy your ML model in 10 lines of code while saving 80%

The templated deep learning framework, enabling framework-agnostic functions, layers and libraries.

This is an openFrameworks addon for the TensorFlow 2 ML (Machine Learning) library.

Storchastic is a PyTorch library for stochastic gradient estimation in Deep Learning

openSMILE (open-source Speech and Music Interpretation by Large-space Extraction) is a complete and open-source toolkit for audio analysis, processing and classification especially targeted at speech and music applications, e.g. a

VQVAEs, GumbelSoftmaxes and friends

Rembg Virtual Greenscreen Edition is a tool to create a green screen matte for videos

This is a JS/TS library for accelerated tensor computation intended to be run in the browser. It contains an implementation for numpy-style multidimensional arrays and their operators.

Number recognition with MNIST on Raspberry Pi Pico + TensorFlow Lite for Microcontrollers

3D Point Cloud Annotation Platform for Autonomous Driving

Quickvision - An Easy To Use PyTorch Computer Vision Library

We based our work on the Keras EfficientDet implementation xuannianz/EfficientDet which again builds up on the great Keras RetinaNet implementation fizyr/keras-retinanet, the official EfficientDet implementation google/automl and

A datasets and methods survey about task-oriented dialogue, including recent datasets and SOTA leaderboards.

In this work, we are focusing on reconstructing scenes from a single image. We make the use of IF-Net which focuses on shape completion from an incomplete 3D input.

The Research Tree - A playground for research at the intersection of Continual, Reinforcement, and Self-Supervised Learning.

Sparsify is a deep learning autoML tool that simplifies the model optimization process to rapidly achieve the best combination of size, speed, and accuracy on any deep learning model.

Code for the book Deep Learning From Scratch, from O'Reilly September 2019

A hyperparameter optimization and meta-learning toolbox for convenient and fast prototyping of machine-/deep-learning models.

CPU inference engine that delivers unprecedented performance for sparse models

Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals.

Upsampling Artifacts in Neural Audio Synthesis

NFNets and Adaptive Gradient Clipping for SGD implemented in PyTorch

Implementation of TimeSformer, a pure and simple attention-based solution for reaching SOTA on video classification.

Learning to ground explanations of affect for visual art.

DeepRL algorithms implementation easy for understanding and reading with Pytorch and Tensorflow 2(DQN, REINFORCE, VPG, A2C, TRPO, PPO, DDPG, TD3, SAC)

Where2Act: From Pixels to Actions for Articulated 3D Objects

A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning