XYZ's repositories
ActivityNet
This repository is intended to host tools and demos for ActivityNet
albert
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
Chinese-XLNet
Pre-Trained Chinese XLNet（中文XLNet预训练模型）
ClipBERT
[CVPR 2021 Best Student Paper Honorable Mention, Oral] Official PyTorch code for ClipBERT, an efficient framework for end-to-end learning on image-text and video-text tasks.
darknet
Windows and Linux version of Darknet Yolo v4 (v3/v2) Neural Networks for object detection (Tensor Cores are used)
DeepSpeechRecognition
A Chinese Deep Speech Recognition System 包括基于深度学习的声学模型和基于深度学习的语言模型
DiverseBranchBlock
Diverse Branch Block: Building a Convolution as an Inception-like Unit
docs
Documentations for PaddlePaddle
edge-connect
EdgeConnect: Structure Guided Image Inpainting using Edge Prediction, ICCVW 2019 https://arxiv.org/abs/1901.00212
iterm2-zmodem
在 Mac 下，实现与服务器进行便捷的文件上传和下载操作
keras-retinanet
Keras implementation of RetinaNet object detection.
MeshNet
MeshNet: Mesh Neural Network for 3D Shape Representation (AAAI 2019)
ML-NLP
此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。
mmaction2
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
multi_task_test
Use tensorflow.contrib.slim to training a simple CNN classification model for multi task
ODConv
The code of Omni-Dimensional Dynamic Convolution (ODConv for short, Spotlight in ICLR2022) is now released, enjoy!
PaConvert
Code Convert to PaddlePaddle Toolkit
Paddle
PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）
Paddle-Lite
Multi-platform high performance deep learning inference engine (飞桨多端多平台高性能深度学习推理引擎）
PaddleDetection
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
PaddleSlim
PaddleSlim is an open-source library for deep model compression and architecture search.
PaddleUtils
Some tools to operate PaddlePaddle model
PaddleVideo
Comprehensive, latest, and deployable video deep learning algorithm, including video recognition, action localization, and temporal action detection tasks. It's a high-performance, light-weight codebase provides practical models for video understanding research and application
pkuseg-python
pkuseg多领域中文分词工具; The pkuseg toolkit for multi-domain Chinese word segmentation
pysot
SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.
SiamMask
[CVPR2019] Fast Online Object Tracking and Segmentation: A Unifying Approach
SlowFast
PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.
vrn
:man: Code for "Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression"