gujiuxiang

mellea. Mellea is a library for writing generative programs.

al-folio. A beautiful, simple, clean, and responsive Jekyll theme for academics

fiftyone. Refine high-quality datasets and visual AI models

Transformers-Tutorials. This repository contains demos I made with the Transformers library by HuggingFace.

yanmtt. Yet Another Neural Machine Translation Toolkit

Spurious_OOD. Python

sim2real-docs. Synthesize image datasets of documents in natural scenes with Python+Blender3D

lightseq. LightSeq: A High Performance Library for Sequence Processing and Generation

genalog. Genalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and text alignment capabilities.

PrefixTuning. Prefix-Tuning: Optimizing Continuous Prompts for Generation

TextRecognitionDataGenerator. A synthetic data generator for text recognition

cuad. CUAD (NeurIPS 2021)

bbox-visualizer. Make drawing and labeling bounding boxes a piece of cake

PrivateDeepLearning. Differential Privacy Preservation in Deep Learning under Model Attacks

simple-faster-rcnn-pytorch. A simplified implemention of Faster R-CNN that replicate performance from origin paper

bottom-up-attention.pytorch. A PyTorch reimplementation of bottom-up-attention models

ark-funds-monitor. A small React app to monitor ARK funds daily transactions

Control_3D_Objects_with_Camera. Limbo

Split_Merge_table_recognition. An implementation of the Splitting and Merging table recognition method.

fairseq. Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

kit. 🧱 Describe your site, AI builds it, you own it as Markdown. Snap together Tailwind blocks like Lego — landing pages, blogs, portfolios, docs & more. No AI slop. Free to deploy anywhere 👇

injecting_numeracy. The accompanying code for "Injecting Numerical Reasoning Skills into Language Models" (Mor Geva*, Ankit Gupta* and Jonathan Berant, ACL 2020).

Integrated-Gradients. Attributing predictions made by the Inception network using the Integrated Gradients method

hiersumm. Code for paper Hierarchical Transformers for Multi-Document Summarization in ACL2019

tokenizers. 💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

fast-transformers. Pytorch library for fast transformer implementations

reformer-pytorch. Reformer, the efficient Transformer, in Pytorch

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Awesome-Visual-Captioning. This repository focus on Image Captioning & Video Captioning & Seq-to-Seq Learning & NLP

SAN. Exploring Self-attention for Image Recognition, CVPR2020.

CMC. [arXiv 2019] "Contrastive Multiview Coding", also contains implementations for MoCo and InstDis

hyperbolic-image-embeddings. Supplementary code for the paper "Hyperbolic Image Embeddings".

fourier-feature-networks. Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains

CVPR2026-Papers-with-Code. CVPR 2026 论文和开源项目合集

detr. End-to-End Object Detection with Transformers

GoogleConceptualCaptioning. Python

Amazon-Fresh-Whole-Foods-delivery-slot-finder. A Mac tool that finds available delivery slots for Amazon's Whole Foods delivery and Amazon Fresh services

Class-balanced-loss-pytorch. Pytorch implementation of the paper "Class-Balanced Loss Based on Effective Number of Samples"

SimCLR. PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations

NLP-Cube. Natural Language Processing Pipeline - Sentence Splitting, Tokenization, Lemmatization, Part-of-speech Tagging and Dependency Parsing

udify. A single model that parses Universal Dependencies across 75 languages. Given a sentence, jointly predicts part-of-speech tags, morphology tags, lemmas, and dependency trees.

UNITER. Research code for ECCV 2020 paper "UNITER: UNiversal Image-TExt Representation Learning"

py-bottom-up-attention. PyTorch bottom-up attention with Detectron2

ContrastiveLosses4VRD. Implementation for the CVPR2019 paper "Graphical Contrastive Losses for Scene Graph Generation"

pytorch-privacy. simple Differential Privacy in PyTorch

layout2im. Official PyTorch Implementation of Image Generation from Layout - CVPR 2019

GatedConvolution_pytorch. A modified reimplemented in pytorch of inpainting model in Free-Form Image Inpainting with Gated Convolution [http://jiahuiyu.com/deepfill2/]

vilbert_beta. Jupyter Notebook

structural-probes. Codebase for testing whether hidden states of neural networks encode discrete structures.

bertviz. BertViz: Visualize Attention in Transformer Models

ctrl. Conditional Transformer Language Model for Controllable Generation

GMNN. Graph Markov Neural Networks

OpenCat-Old. A programmable and highly maneuverable robotic cat for STEM education and AI-enhanced services.

PoseEstimationForMobile. :dancer: Real-time single person pose estimation for Android and iOS.

SimGNN. A PyTorch implementation of "SimGNN: A Neural Network Approach to Fast Graph Similarity Computation" (WSDM 2019).

ChatterBot. ChatterBot is a machine learning, conversational dialog engine for creating chat bots

visual-chatbot. :cloud: :eyes: :speech_balloon: Visual Chatbot

sg2im-demo. A web based demo of Google's sg2im neural network to convert a scene graph to a photorealistic image.

grounded-video-description. Video Grounding and Captioning

AnyNet. (ICRA) Anytime Stereo Image Depth Estimation on Mobile Devices

Pi_Self_Driving_Car. 使用树莓派3b来实现无人驾驶汽车

Self-Driving-Car. HTML

Autopilot. A simple self-driving car module for humans 🚘 🛣️

unsupervised_captioning. Code for Unsupervised Image Captioning

easyquotation. 实时获取免费股票行情，支持新浪 / 腾讯(港股) / 集思录

pytorch-spectral-normalization-gan. Paper by Miyato et al. https://openreview.net/forum?id=B1QRgziT-

UNMT. Code inspired by Unsupervised Machine Translation Using Monolingual Corpora Only

MUSE. A library for Multilingual Unsupervised or Supervised word Embeddings

topic-rnn. Implementation (in progress) of Dieng et al.'s TopicRNN: a neural topic model & RNN hybrid.

transferlearning-tutorial. 《迁移学习简明手册》LaTex源码

Chatbot. Python ChatBot 💬

unsupervised-NMT. Unsupervised neural machine translation; weight sharing; GAN

UNIT. Unsupervised Image-to-Image Translation

maskrcnn-benchmark. Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

PerceptualSimilarity. LPIPS metric. pip install lpips

HDGan. Pytorch implementation of HDGan

introvae.pytorch. Python

AccSGD. Implements pytorch code for the Accelerated SGD algorithm.

mAP. mean Average Precision - This code evaluates the performance of your neural net for object recognition.

Object-Detection-Metrics. Most popular metrics used to evaluate object detection algorithms.

VQA-Chatbot. :eyes: A Chatbot based on VQA (Visual Question Answering)

AoAReader. PyTorch implementation of Attention-over-Attention Neural Networks for Reading Comprehension

PyTorch-AdaHAN. An unofficial PyTorch implementation of the HAN and AdaHAN models presented in the "Learning Visual Question Answering by Bootstrapping Hard Attention" research paper.

Differentiable-Hard-Attention-Module. A modified version of Spatial Transformer Networks to attend regions on the input image.

graph-rcnn.pytorch. [ECCV 2018] Official code for "Graph R-CNN for Scene Graph Generation"

motifs-test. Code for Neural Motifs: Scene Graph Parsing with Global Context (CVPR 2018)

neural-motifs. Code for Neural Motifs: Scene Graph Parsing with Global Context (CVPR 2018)

Dynamic-memory-networks-plus-Pytorch. Implementation of Dynamic memory networks plus in Pytorch

Relation-Networks-for-Object-Detection. Relation Networks for Object Detection

mobilefacenet-V2. 🔥improve the accuracy of mobilefacenet(insight face) reached 99.733 in the cfp-ff、 the 99.68+ in lfw,96.71+ in agedb30.🔥

DRIT. Learning diverse image-to-image translation from unpaired data

gconvRNN. Graph convolutional recurrent neural network

FactorizableNet. Factorizable Net (Multi-GPU version): An Efficient Subgraph-based Framework for Scene Graph Generation

MSDN. This is our PyTorch implementation of Multi-level Scene Description Network (MSDN) proposed in our ICCV 2017 paper.

Pytorch-TextureGAN. TextureGAN in Pytorch

commonsense-rc. Code for Yuanfudao at SemEval-2018 Task 11: Three-way Attention and Relational Knowledge for Commonsense Machine Comprehension

BicycleGAN. Toward Multimodal Image-to-Image Translation

human-pose-estimation.pytorch. The project is an official implement of our ECCV2018 paper "Simple Baselines for Human Pose Estimation and Tracking(https://arxiv.org/abs/1804.06208)"

GraphGAN. A tensorflow implementation of GraphGAN (Graph Representation Learning with Generative Adversarial Nets)

ReferringRelationships. Python

vrd-dsr. Code for Visual Relationship Detection with Deep Structural Ranking (AAAI2018)

e2e_dialog_challenge. End-To-End Task-Completion Dialogue Challenge

faster-rcnn.pytorch. A faster pytorch implementation of faster r-cnn

VQA-DataAugmentation. Data Augmentation for Visual Question Answering

PSLQA. An implementation of Probabilistic Soft Logic Engine using Python/Gurobi

Sparqly. Python API for SPARQL Endpoints

conceptnet5. Code for building ConceptNet from raw data.

conceptnet. ConceptNet: a semantic network of common sense knowledge

Image-OutPainting. 🏖 Keras Implementation of Painting outside the box

fact-extractor. Fact Extraction from Wikipedia Text

w2vv. Word2VisualVec : Predicting Visual Features from Text for Image and Video Caption Retrieval

vqa-counting. [ICLR 2018] Learning to Count Objects in Natural Images for Visual Question Answering

extraction-framework. The software used to extract structured data from Wikipedia

DeepVariationStructuredRL. A PyTorch implementation of the "Deep Variation-structured Reinforcement Learning for Visual Relationship and Attribute Detection" paper by Liang et. al.

pseudo-3d-pytorch. pytorch version of pseudo-3d-residual-networks(P-3D), pretrained model is supported

PyTorch-Encoding. A CV toolkit for my papers.

pytorch-openai-transformer-lm. 🐥A PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI

multimodal_vtt. Joint Embedding with Multimodal Cues for Cross-Modal Video-Text Retrieval

bist-parser. Scene Graph Parsing as Dependency Parsing

VAT-pytorch. Virtual Adversarial Training (VAT) implementation for PyTorch

NeurboParser. A neural TurboSemanticParser as described in "Deep Multitask Learning for Semantic Dependency Parsing", Peng et al., ACL 2017.

Switchable-Normalization. Code for Switchable Normalization from "Differentiable Learning-to-Normalize via Switchable Normalization", https://arxiv.org/abs/1806.10779

DQN-pytorch. A PyTorch implementation of Human-Level Control through Deep Reinforcement Learning

vrn-pytorch. PyTorch Code for "Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression"

MatchLSTM-PyTorch. a pytorch implementation of match lstm question answering model

sg2im. Code for "Image Generation from Scene Graphs", Johnson et al, CVPR 2018

mace. MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.

c3d-pytorch. Pytorch porting of C3D network, with Sports1M weights

fgvc5-cvpr2018-food-fashion. Fine Grained Visual Categorization

thor-iqa-cvpr-2018. Repository containing code for the paper "IQA: Visual Question Answering in Interactive Environments"

self-imitation-learning. ICML 2018 Self-Imitation Learning

EmbodiedQA. Train embodied agents that can answer questions in environments

coco-caption. Adds SPICE metric to coco-caption evaluation server codes

DCC. Implementation of CVPR 2016 paper

planetoid. Semi-supervised learning with graph embeddings

graph-generation. GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models

PyTorch-GAN. PyTorch implementations of Generative Adversarial Networks.

PPO-Pytorch. Implementation of PPO in Pytorch

pytorch-sentiment-analysis. Tutorials on getting started with PyTorch and TorchText for sentiment analysis.

Joint-GAN. Python

online_eval_tools. Human evaluation tool for image captioning

knowledge-distillation-pytorch. A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility

DiscCaptioning. Code for Discriminability objective for training descriptive captions(CVPR 2018)

Deep-Reinforcement-Learning-for-Dialogue-Generation-in-tensorflow. Deep-Reinforcement-Learning-for-Dialogue-Generation-in-tensorflow

zero-shot-gcn. Zero-Shot Learning with GCN (CVPR 2018)

Style_Migration_For_Artistic_Font_With_CNN. 基于卷积神经网络的风格迁移，制造出带有艺术风格的字体（艺术字），部分效果可达PS水平，可以辅助设计人员做设计；Convolutional neural network based style migration to create a font with artistic style (WordArt), some effects up to PhotoShop level, it can assist designers to do design

visdial-amt-chat. [CVPR 2017] AMT chat interface code used to collect the Visual Dialog dataset

DeepTracking. Source code of DeepTracking research project

StackNN. Experiments with differentiable stacks and queues in PyTorch

Detectron.pytorch. A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.

pytorch-maml. PyTorch implementation of MAML: https://arxiv.org/abs/1703.03400

joint-vae. Pytorch implementation of JointVAE, a framework for disentangling continuous and discrete factors of variation :star2:

naacl18tutorial. NAACL 2018 Tutorial: Modelling Natural Language, Programs, and their Intersection

MSDNet-GCN. ICLR 2018 reproducibility challenge - Multi-Scale Dense Convolutional Networks for Efficient Prediction

brats17. Brain tumor segmentation for MICCAI 2017 BraTS challenge

pytorch-MNIST-CelebA-cGAN-cDCGAN. Pytorch implementation of conditional Generative Adversarial Networks (cGAN) and conditional Deep Convolutional Generative Adversarial Networks (cDCGAN) for MNIST dataset

deep_trader. This project uses reinforcement learning on stock market and agent tries to learn trading. The goal is to check if the agent can learn to read tape. The project is dedicated to hero in life great Jesse Livermore.

TradingGym. Trading and Backtesting environment for training reinforcement learning agent or simple rule base algo.

rl-portfolio-management. Attempting to replicate "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem" https://arxiv.org/abs/1706.10059 (and an openai gym environment)

visDial.pytorch. visual dialog model in pytorch

Transformer_Captioning. Use transformer for captioning

stock_market_reinforcement_learning. This project provides a stock market environment using OpenGym with Deep Q-learning and Policy Gradient.

deep_trader. This project uses reinforcement learning on stock market and agent tries to learn trading. The goal is to check if the agent can learn to read tape. The project is dedicated to hero in life great Jesse Livermore.

StockPricePrediction. Stock Price Prediction using Machine Learning Techniques

Unpaired-Sentiment-Translation. Code for "Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach" (ACL 2018)

QuestionGeneration. Python

CharadesDet. Charades Object Detection Dataset (ICCV 2017)

stylenet. A pytorch implemention of "StyleNet: Generating Attractive Visual Captions with Styles"

gancaption_iccv2017. Towards Diverse and Natural Image Descriptions via a Conditional GAN

extension-cpp. C++ extensions in PyTorch

higgsfield. Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

visual-attribution. Pytorch Implementation of recent visual attribution methods for model interpretability

text2shape.pytorch. This is the implementation of text2shape in pytorch

Facelet_Bank. Facelet-Bank for Fast Portrait Manipulation (pytorch)

pyGAT. Pytorch implementation of the Graph Attention Network model by Veličković et. al (2017, https://arxiv.org/abs/1710.10903)

binary-human-pose-estimation. This code implements a demo of the Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources paper by Adrian Bulat and Georgios Tzimiropoulos.

translate. Translate - a PyTorch Language Library

FC-DenseNet. Fully Convolutional DenseNets for semantic segmentation.

sbvqa. Python

videoqa. Unifying the Video and Question Attentions for Open-Ended Video Question Answering

neural-acoustic-word-embeddings. Shell

pytorch-dual-learning. Implementation of Dual Learning NMT on PyTorch

wavenet_vocoder. WaveNet vocoder

seg_every_thing. Code release for Hu et al., Learning to Segment Every Thing. in CVPR, 2018.

pytorch_compact_bilinear_pooling. Compact Bilinear Pooling for PyTorch

lstm-crf-pytorch. LSTM-CRF in PyTorch

REGAN. ReGAN: Sequence GAN using RE[INFORCE|LAX|BAR] based PG estimators

phrase-based_image_captioning. Torch implementation of ICML 2015 paper about image captioning

Structured-Self-Attention. A Structured Self-attentive Sentence Embedding

dirt-t. A DIRT-T Approach to Unsupervised Domain Adaptation (ICLR 2018)

nlp1-2017-projects. Info for NLP1 2017 projects

toward-controlled-generation-of-text-pytorch. A PyTorch Implementation of "Toward Controlled Generation of Text"

hred. Implements the paper " Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models" by Serban et al (currently on the MovieTriples dataset)

deep-learning-model-convertor. The convertor/conversion of deep learning models for different deep learning frameworks/softwares.

Realtime_Multi-Person_Pose_Estimation. Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

MegaDepth. Code of single-view depth prediction algorithm on Internet Photos described in "MegaDepth: Learning Single-View Depth Prediction from Internet Photos, Z. Li and N. Snavely, CVPR 2018".

light_head_rcnn. Light-Head R-CNN

spatial_graph_convnets. PyTorch implementation of residual gated graph ConvNets, ICLR’18

VIN_PyTorch_Visdom. PyTorch implementation of Value Iteration Networks (VIN): Clean, Simple and Modular. Visualization in Visdom.

Wasserstein-AutoEncoders. PyTorch implementation of Wasserstein Auto-Encoders