fireae's repositories
aim
Aim — an easy-to-use and performant open-source experiment tracker.
AugLy
A data augmentations library for audio, image, text, and video.
Awesome-Table-Recognition
A curated list of resources dedicated to table recognition
breeze
Deploy a Production Ready Kubernetes Cluster with graphical interface
calamares
Distribution-independent installer framework
CDistNet
Official Pytorch implementations of CDistNet
CIoU
Complete-IoU (CIoU) Loss and Cluster-NMS for Object Detection and Instance Segmentation (YOLACT)
deepdoctection
A Repo For Document Analysis Pipelines
doccano
Open source annotation tool for machine learning practitioners.
ExecutionNodes
A graph-based reuse system brings flow-based programming to C++
GTR
Scene text recognition
json
JSON for Modern C++
json2cpp
interconverting json string and c++ class(convert json string to c++ class, and convert c++ class to json string)
LaTeX-OCR
pix2tex: Using a ViT to convert images of equations into LaTeX code.
latex2image-web
LaTeX to image converter with web UI using Node.js / Docker
Leaderboard
SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.
LEBERT
Code for the ACL2021 paper "Lexicon Enhanced Chinese Sequence Labelling Using BERT Adapter"
marian
Fast Neural Machine Translation in C++
MASR
Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持DeepSpeech2模型，支持多种数据增强方法。
MobilePose
Light-weight Single Person Pose Estimator
R-YOLOv4
This is a PyTorch-based R-YOLOv4 implementation which combines YOLOv4 model and loss function from R3Det for arbitrary oriented object detection.
swin-transformer-ocr
swin-transformer custom for OCR
SwinTextSpotter
Pytorch re-implementation of Paper: SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition (CVPR 2022)
table-transformer
Model training and evaluation code for our dataset PubTables-1M, developed to support the task of table extraction from unstructured documents.
TextGenerator
OCR dataset Text-Detection dataset Font-Classification dataset generator
torchlm
💎A high level pipeline for face landmarks detection, supports training, evaluating, exporting, inference and 100+ data augmentations, compatible with torchvision and albumentations, can easily install with pip.
ttskit
text to speech toolkit. 好用的中文语音合成工具箱，包含语音编码器、语音合成器、声码器和可视化模块。
vxl
A multi-platform collection of C++ software libraries for Computer Vision and Image Understanding.
yolov5-rt-stack
yolort is a runtime stack for yolov5 on specialized accelerators such as libtorch, onnxruntime, tensorrt, tvm and ncnn.