Deep Learning

Frameworks for Neural Networks and Deep Learning.

Newest releases

vladmandic 3D Face Detection, Body Pose, Hand & Finger Tracking, Iris Tracking, Age & Gender Prediction & Emotion Prediction
 

pairlab Official PyTorch code for D2RL: Deep Dense Architectures in Reinforcement Learning
 

HKUST-Aerial-Robotics FUEL is a hierarchical framework for Fast UAV ExpLoration. It contains a Frontier Information Structure (FIS), which can be incrementally updated with the online built map and facilitate exploration planning in high frequency. Bas
 

yogeshbalaji This is the official codebase of our NeurIPS 2020 paper "Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation".
 

john-light This project attempts to create a comprehensive list of resources related to sidechain design and development.
 

PINTO0309 This script converts the OpenVINO IR model to Tensorflow's saved_model, tflite, h5 and pb. PyTorch (NCHW) -> ONNX (NCHW) -> OpenVINO (NCHW) -> openvino2tensorflow -> Tensorflow/Keras (NHWC) -> TFLite (NHWC)
 

tencent-ailab Code and data for our paper "High-Fidelity 3D Digital Human Creation from RGB-D Selfies".
 

lightly-ai Lightly is a computer vision framework for self-supervised learning.
 

sdv-dev The Synthetic Data Vault (SDV) is a Synthetic Data Generation ecosystem of libraries that allows users to easily learn single-table, multi-table and timeseries datasets to later on generate new Synthetic Data that has the same for
 

Bartzi Code for Paper "One Model to Reconstruct Them All: A Novel Way to Use the Stochastic Noise in StyleGAN"
 

abhinavsagar Code for the paper Generate High Resolution Images With Generative Variational Autoencoder
 

googleinterns A simple consistency training framework for semi-supervised image semantic segmentation
 

wenbowen123 [IROS 2020] se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains
 

zhumeiqiBUPT AM-GCN: Adaptive Multi-channel Graph Convolutional Networks
 

stefanopini This is an unofficial implementation of the paper HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation.
 

FrancoisGrondin BIRD is an open dataset that consists of 100,000 multichannel room impulse responses generated using the image method. This makes it the largest multichannel open dataset currently available. We provide some Python code that shows
 

alexeygrigorev Closing dataset, all classes
 

weimingwill This repository maintains a collection of papers, articles, videos, frameworks, etc of federated learing, for the purpose of learning and research.
 

DataXujing 🎨 Pytorch YOLO v5 训练自己的数据集超详细教程!!! 🎨 (提供PDF训练教程下载)
 

kuixu Reproducing the Linear Multihead Attention introduced in Linformer paper (Linformer: Self-Attention with Linear Complexity)
 

jik876 In our paper, we proposed HiFi-GAN: a GAN-based model capable of generating high fidelity speech efficiently. We provide our implementation and pretrained models as open source in this repository.
 

mzhang367 PyTorch Implementation of Deep Center-Based Dual-Constrained Hashing for Discriminative Face Image Retrieval
 

jiupinjia Pytorch implementation of the preprint paper "Castle in the Sky: Dynamic Sky Replacement and Harmonization in Videos"
 

haantran96 Code base for WaveTransformer: A novel architecture for automated audio captioning
 

google-research Multilingual T5 (mT5) is a massively multilingual pretrained text-to-text transformer model, trained following a similar recipe as T5. This repo can be used to reproduce the experiments in the mT5 paper.
 

google-research In this repository we release models from the paper An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale that were pre-trained on the ImageNet-21k (imagenet21k) dataset. We provide the code for fine-tuning th
 

shunithaviv Code for BebopNet: Deep Neural Models for Personalized Jazz Improvisations
 

xcppy Hierarchical Fashion Graph Network for Personalized Outfit Recommendation, SIGIR 2020
 

mengyuest AR-Net: Adaptive Resolution Network for Efficient Video Understanding
 

aimhubio Aim — a super-easy way to record, search and compare AI experiments
 

OvidijusParsiunas MyVision is a free online image annotation tool used for generating computer vision based ML training data. It is designed with the user in mind, offering features to speed up the labelling process and help maintain workflows with
 

juntang-zhuang NeurIPS 2020 Spotlight, trains fast as Adam, generalizes well as SGD, and is stable to train GANs.
 

xcfcode This repo contains a list of summarization papers including various topics.