shengzhang90's repositories
PaddleOCR
基于飞桨的OCR工具库，包含总模型仅8.6M的超轻量级中文OCR，单模型支持中英文数字组合识别、竖排文本识别、长文本识别。同时支持多种文本检测、文本识别的训练算法。
imgaug
Image augmentation for machine learning experiments.
convolutional-handwriting-gan
ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation (CVPR20)
detr
End-to-End Object Detection with Transformers
PaddleDetection
Object detection and instance segmentation toolkit based on PaddlePaddle.
Disout
Code for AAAI 2020 paper, Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks (Disout).
bisenetv2-tensorflow
Unofficial tensorflow implementation of real-time scene image segmentation model "BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation"
ContourNet
ContourNet
reformer-pytorch
Reformer, the efficient Transformer, in Pytorch
SCNet
The official PyTorch implementation of CVPR 2020 paper "Improving Convolutional Networks with Self-Calibrated Convolutions"
SAN
Exploring Self-attention for Image Recognition, CVPR2020.
lite-transformer
[ICLR 2020] Lite Transformer with Long-Short Range Attention
awesome-imbalanced-learning
A curated list of awesome imbalanced learning papers, codes, frameworks and libraries. | 类别不平衡学习：论文/代码/框架/库
SEPC
Scale-equalizing Pyramid Convolution for object detection
ATSS
Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection, CVPR, Oral, 2020
dataset
Textual Visual Semantic Dataset for Text Spotting
PCDet
PCDet Toolbox in PyTorch for 3D Object Detection from Point Cloud
Yet-Another-EfficientDet-Pytorch
The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.
DynamicReLU
Implementation of Dynamic ReLU on Pytorch
AdelaiDet
AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.
GFTE
A GCN-based table structure recognition method
Company-Names-Corpus
公司名语料库。机构名语料库。公司简称,缩写,品牌词,企业名。可用于中文分词、机构名实体识别。
VL-BERT
Code for ICLR 2020 paper "VL-BERT: Pre-training of Generic Visual-Linguistic Representations".
electra
ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
CentripetalNet
Source codes of "CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection"
moco
PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722
UnrealText
Synthetic Scene Text from 3D Engines
TE141K
Project website of TE141K.