Deep Learning

Frameworks for Neural Networks and Deep Learning.

Newest releases

abhijithneilabraham Supports detection from multiple csvs Support FuzzyString implementation. i.e, incomplete csv values in query can be automatically detected and filled in the query. Open-Domain, No training required. Add manual schema for custo

yiakwy This is a sparse Monocular SLAM project merely for research in the realm of HDMap hibrid pipeline construction. Constrast to dense or recent popular semi-dense slam projects such as "DTAM", "LSD-SLAM", "DSO", this is an implementa

CODAIT This repository provides a set of Jupyter Notebooks that augment and analyze COVID-19 time series data.

OverLordGoldDragon RNN and general weights, gradients, & activations visualization in Keras & TensorFlow

torchexpo TorchExpo is a collection of models and extensions for mobile deployment in PyTorch

samuelbroscheit This repository contains the code for the CONLL 2019 paper "Investigating Entity Knowledge in BERT with Simple Neural End-To-End Entity Linking". The code is provided as a documentation for the paper and also for follow-up researc

samuelbroscheit This repository contains the code for the CONLL 2019 paper "Investigating Entity Knowledge in BERT with Simple Neural End-To-End Entity Linking". The code is provided as a documentation for the paper and also for follow-up researc

chrishokamp This repo contains the code for DynE: Dynamic Ensemble Decoding for Multi-Document Summarization.

hbaudhuin The aim of this thesis is to create a CNN capable of detecting new constructions in satellite imagery. More precisly, taking two satellite images taken at different times and output a segmentation mask with the contour of the new

P2333 Empirical tricks for training state-of-the-art robust models on CIFAR-10. A playground for fine-tuning the basic adversarial training settings.

dimkal89 The model proposed in the paper is a VAE with a Riemannian Brownian motion prior (RVAE) and the experimental baselines are (a) a vanilla VAE with a standard Gaussian prior and (b) a VAE with a VampPrior.

gabeur Our proposed Multi-Modal Transformer (MMT) aggregates sequences of multi-modal features (e.g. appearance, motion, audio, OCR, etc.) from a video. It then embeds the aggregated multi-modal feature to a shared space with text for re

LayneH Official implementation of the NeurIPS 2020 paper 'Self-Adaptive Training: beyond Empirical Risk Minimization'

thodan Code for "EPOS: Estimating 6D Pose of Objects with Symmetries", CVPR 2020.

sysu-imsl Code for paper "SketchyCOCO: Image Generation from Freehand Scene Sketches"

plusmultiply This repository contains the implementation of our CVPR2020 paper Multi Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Clouds(MPRM)(paper)

truthless11 Task-oriented Dialog Policy Learning with Multi-Agent Reinforcement Learning

abnerrjo Implementation of my article "A Robust Statistics Approach for Plane Detection in Unorganized Point Clouds"

fraunhoferportugal This repository hosts the TSFEL - Time Series Feature Extraction Library python package. TSFEL assists researchers on exploratory feature extraction tasks on time series without requiring significant programming effort.

google-research Sputnik is a library of sparse linear algebra kernels and utilities for deep learning.

facebookresearch GTN is a framework for automatic differentiation with weighted finite-state transducers. The framework is written in C++ and has bindings to Python.

Tom-Hardy-3D-Vision-Workshop 主要针对3D object相关算法进行了汇总,分为基于RGB图像、立体视觉、点云、融合四种方式

zdyshine RTC2020_EfficientSR FZU-CS510 冠军开源方案

YyzHarry [NeurIPS 2020] Semi-Supervision (Unlabeled Data) & Self-Supervision Improve Class-Imbalanced / Long-Tailed Learning

lmbxmu Pytorch implementation of our NeurIPS 2020 -- Rotated Binary Neural Network

gudgud96 Code accompanying ML4MD ICML 2020 paper - "Generative Modelling for Controllable Audio Synthesis of Expressive Piano Performance".

eric-yyjau Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints, IROS 2020

BachiLi Differentiable Vector Graphics Rasterization

GMvandeVen A brain-inspired version of generative replay for continual learning with deep neural networks (class-incremental learning on CIFAR-100; PyTorch code).

declare-lab This repository contains PyTorch implementation for the baseline models from the paper Utterance-level Dialogue Understanding: An Empirical Study

rlct1 This is the Pytorch implementation of our Deep Generative Inpainting Network (GIN) for Extreme Image Inpainting. We have participated in AIM 2020 ECCV Extreme Image Inpainting Challenge. Our GIN is used for reconstructing a comple

IBM The official Codes for NeurIPS 2019 paper. Quanfu Fan, Ricarhd Chen, Hilde Kuehne, Marco Pistoia, David Cox, "More Is Less: Learning Efficient Video Representations by Temporal Aggregation Modules"

QuantStack ipygany is an early developer preview. Features and implementation are subject to change.