记录对nerf各种算法、应用、软件等等的学习过程

Natural Language for Optimization Modelling

1st Solution For ICDAR 2021 Competition on Mathematical Formula Detection（公式检测冠军方案）

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

2nd solution of ICDAR 2021 Competition on Scientific Literature Parsing, Task B.

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

A flexible, high-performance carrier for machine learning models（『飞桨』服务化部署框架）

💎1MB lightweight face detection model (1MB轻量级人脸检测模型)

Pre-trained and Reproduced Deep Learning Models （『飞桨』官方模型库，包含多种学术前沿和工业场景验证的深度学习模型）

This is a novel and easy method for annotation uncertainties.

Efficient Facial Feature Learning with Wide Ensemble-based Convolutional Neural Networks

Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph Convolution (AAAI-2020)

Using BERT to calculate perplexity

A Pytorch implementation of MobileNet V3.

The squeezenet image classification android example

an personal implementation about randaugment

🎨 数学公式识别增强版：中英文手写印刷公式、支持初级符号推导（数据结构基于 LaTeX 抽象语法树）

EnsNet: Ensconce Text in the Wild

PaddlePaddle Fluid 版本系列教程，CSDN博客专栏：https://blog.csdn.net/qq_33200967/column/info/28685

PKU Team Zero's code for participation in ICDAR2019 ArT Recognition track (Champion)

Deep Learning for humans

MobileNetV3 in pytorch and ImageNet pretrained models

Aggregation Cross-Entropy for Sequence Recognition. CVPR 2019.

E2E-MLT - an Unconstrained End-to-End Method for Multi-Language Scene Text

Imaging Biomarkers and Computer-Aided Diagnosis Laboratory

Implemention of Baidu's DenseBox used for multi-task learning of object detection and landmark(key-point) localization 用PyTorch实现了百度的DenseBox并针对任意宽高比矩形(不仅限于方形)的目标检测做了优化，不仅可以输出关键点的热力图(heatmap)而且可以输…

AI Challenger -- 农作物病害识别

PyTorch implementation of image classification models for CIFAR-10/CIFAR-100/MNIST/FashionMNIST/Kuzushiji-MNIST