tonylin52 Goto Github PK

2021ccf_bdci_nair

2021 CCF BDCI基于飞桨实现花样滑冰选手骨骼点动作识别-第1名方案

additive-margin-softmax

This is the implementation of paper <Additive Margin Softmax for Face Verification>

augmentor

Image augmentation library in Python for machine learning.

bayesian-neural-network-blogpost

Building a Bayesian deep learning classifier

binarynet.pytorch

Binarized Neural Network (BNN) for pytorch

c-ocr

C-OCR是携程自研的OCR项目，主要包括身份证、护照、火车票、签证等旅游相关证件、材料的识别。 项目包含4个部分，拒识、检测、识别、后处理。

cascade-rcnn

Caffe implementation of multiple popular object detection frameworks

centerface

face detection

centernet-tf2

这是一个centernet-tf2的源码，可以用于训练自己的模型。

centernet2

Two-stage CenterNet

character-segmentation

Character Segmentation using TensorFlow

crnn_ctc_ocr_tf

Extremely simple implement for CRNN by Tensorflow

dataaugmentcollection

DataAugment for classification segmentation detection.

denoising-diffusion-pytorch

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

hand3dresearch

headpose

Head position capture to Unity (3d head model).

hyperlandmark

Deep Learning Based Free Mobile Real-Time Face Landmark Localization.

image2katex

公式图片ocr，输入图片输出对应的latex表达式

insightface

Face Analysis Project on MXNet

insightface_tf

Insight Face on TensorFlow

kaggle_image_caption_matching-

labelimg

:metal: LabelImg is a graphical image annotation tool and label object bounding boxes in images

lightllm

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

minimal-hand

A minimal solution to hand motion capture from a single color camera at over 100fps. Easy to use, plug to run.

minimal-hand-pytorch

PyTorch reimplementation of minimal-hand (CVPR2020)

mnn

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba

mtcnn

Repository for "Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks", implemented with Caffe, C++ interface.

nanodet

⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

nnie-lite

⚡️ Using NNIE as simple as using ncnn ⚡️

nnie-yolov3

nnie-yolov3 VS2017 solution and HISI3516CV500