Deep Learning

TensorRTx aims to implement popular deep learning networks with tensorrt network definition APIs. As we know, tensorrt has builtin parsers, including caffeparser, uffparser, onnxparser, etc. But when we use these parsers, we often

Open3D-ML is an extension of Open3D for 3D machine learning tasks. It builds on top of the Open3D core library and extends it with machine learning tools for 3D data processing. This repo focuses on applications such as semantic p

FoldsCUDA.jl provides Transducers.jl-compatible fold (reduce) implemented using CUDA.jl. This brings the transducers and reducing function combinators implemented in Transducers.jl to GPU. Furthermore, using FLoops.jl, you can wri

This repo contains the inference code for two neural networks that were pre-trained on millions of videos. Both neural networks are rather small and should smoothly run in real time on a CPU.

GRF: Learning a General Radiance Field for 3D Scene Representation and Rendering

Code for the paper "Deep Entity Matching with Pre-trained Language Models"

This is the repository containing the solution for FG-2020 ABAW Competition

This is the official Pytorch implementation of Length-Adaptive Transformer

Training and evaluation code for Re-MOVE models with embedding distillation

[ACCV2020] Localize to Classify and Classify to Localize: Mutual Guidance in Object Detection

On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them [NeurIPS 2020]

Attacks Which Do Not Kill Training Make Adversarial Learning Stronger (ICML2020 Paper)

PyTorch implementation for EMNLP 2020 paper: Double Graph Based Reasoning for Document-level Relation Extraction

PyTorch code for EMNLP 2020 Paper "Vokenization: Improving Language Understanding with Visual Supervision"

This is the official implementation of AE TextSpotter, which introduces linguistic information to eliminate the ambiguity in text detection. This code is based on MMDetection v1.0rc1.

Demonstration using Google Colab to show how U-2-NET can be used for Background Removal, Bounding Box Creation and Salient Feature Highlighting

A modeltime extension that implements ensemble forecasting methods including model averaging, weighted averaging, and stacking.

Modeltime unlocks time series models and machine learning in one framework

ONNX-TensorRT: TensorRT backend for ONNX

GridRoyale is a life simulation. It's a tool for machine learning researchers to explore social dynamics.

This is the implementation of NeurIPS 2020 paper "Generative 3D Part Assembly via Dynamic Graph Learning" created by Jialei Huang*, Guanqi Zhan*, Qingnan Fan, Kaichun Mo, Lin Shao, Baoquan Chen, Leonidas Guibas and Hao Dong.

High Performance Tensorflow Data Pipeline with State of Art Augmentations and low level optimizations.

Sample code and documentation for using the Microsoft HoloLens 2 for Computer Vision research.

Photo-realistic free-viewpoint rendering of real-world scenes using classical computer graphics techniques is a challenging problem because it requires the difficult step of capturing detailed appearance and geometry models.

LI-Calib is a toolkit for calibrating the 6DoF rigid transformation and the time offset between a 3D LiDAR and an IMU. It's based on continuous-time batch optimization. IMU-based cost and LiDAR point-to-surfel distance are minimiz

Tutorial covering Open Source tools for Source Separation.

Towards hot directions in industrial speech recognition

Use Unity 3D character and Python deep learning algorithms to stream as a VTuber!

This is an official implementation of Unfolding the Alternating Optimization for Blind Super Resolution

[CVPR'19, ICLR'20] A Python toolbox for modeling and optimization of photo acquisition & distribution pipelines (camera ISP, compression, forensics, manipulation detection)

Question answering for event extraction (trigger detection and argument extraction with various questioning strategies).

Source code for Context-aware RCNN: a Baseline for Action Detection in Videos

Domain Adaptation for Image Dehazing, CVPR2020