Stars
Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models and so on.
基于Pytorch实现优秀的自然图像分割框架！(包括FCN、U-Net和Deeplab)
PyTorch implementation of SimSiam https//arxiv.org/abs/2011.10566
A Gated and Bifurcated Stacked U-Net Module for Document Image Dewarping
Real-time face detection and emotion/gender classification using fer2013/imdb datasets with a keras CNN model and openCV.
State-of-the-art 2D and 3D Face Analysis Project
Identifying numbers from bankcard, based on Deep Learning with Keras
2019CCF-BDCI大赛 最佳创新探索奖获得者 基于OCR身份证要素提取赛题冠军 天晨破晓团队 赛题源码
DeepLearningToys: Some deep learning toys implemented in pytorch.
The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."
Paper and implementation of UNet-related model.
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
Pytorch implementation of the ECCV 2020 paper: AtlantaNet: Inferring the 3D Indoor Layout from a Single 360 Image beyond the Manhattan World Assumption
😎 A list of awesome scene understanding papers.
Tensorflow implementation of our end-to-end model to recover 3D layouts. Also with equirectangular convolutions!
Tensorflow implementation of room layout paper: Roomnet: End-to-end Room Layout Estimation.
CnSTD: 基于 PyTorch/MXNet 的 中文/英文 场景文字检测（Scene Text Detection）、数学公式检测（Mathematical Formula Detection, MFD）、篇章分析（Layout Analysis）的Python3 包
TFRecord Viewer for browsing contents of TFRecords with object detection/classification annotations.
Ultra-lightweight human body posture key point CNN model. ModelSize:2.3MB HUAWEI P40 NCNN benchmark: 6ms/img,
🎉 A magical vue admin https://panjiachen.github.io/vue-element-admin
Python demo for ID card digitization using Nanonets
To speedup and simplify image labeling/ annotation process with multiple supported formats.
Keras implementation of Holistically-nested edge detection
Deep Speaker: an End-to-End Neural Speaker Embedding System.
超轻量级中文ocr，支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M
SOTA Re-identification Methods and Toolbox
An elegant PyTorch deep reinforcement learning library.