XiaoZhang's repositories
DRL4SnakeGame
Using deep reinforcement learning to play Snake game(贪吃蛇).
named_entity_recognition
中文命名实体识别（包括多种模型：HMM，CRF，BiLSTM，BiLSTM+CRF的具体实现）
MobileStyleGAN.pytorch
An official implementation of MobileStyleGAN in PyTorch
CCPD_Plus
Chinese City Parking Dataset（with Blue and Green add Yellow）
DeepFaceLab
DeepFaceLab is the leading software for creating deepfakes.
PaddleOCR
Awesome multilingual OCR toolkits based on PaddlePaddle （practical ultra lightweight OCR system, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices）
PaddleDetection
Object detection and instance segmentation toolkit based on PaddlePaddle.
SOLO
SOLO and SOLOv2 for instance segmentation, ECCV 2020 & NeurIPS 2020.
detectron2
Detectron2 is FAIR's next-generation platform for object detection and segmentation.
yolact
A simple, fully convolutional model for real-time instance segmentation.
MASTER-TF
MASTER
yolov5
YOLOv5 in PyTorch > ONNX > CoreML > TFLite
yolov3
YOLOv3 in PyTorch > ONNX > CoreML > TFLite
CCPD
[ECCV 2018] CCPD: a diverse and well-annotated dataset for license plate detection and recognition
wdsr_pytroch
wdsr, 超分辨，低分辨率提升高分辨率图像
SAR_TF
This is an implementation of Show, Attend and Read with tensorflow
chineseocr-onnx
chineres ocr from picture, 中英文本检测与文本识别，dense-ctc，dbnet，crnn，pse，unet等模型
Formula_Image_To_Latex
chineseocr, ctc, ocr
DenseCTC-Keras
chinese ocr, crnn, densectc, for rec text, 中英文文字识别OCR
DeNoise-tensorflow
图像增强与去噪
PytorchOCR
基于Pytorch的OCR工具库，支持常用的文字检测和识别算法
ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
DBNet.pytorch
A pytorch re-implementation of Real-time Scene Text Detection with Differentiable Binarization
OCR_DataSet
收集并整理有关OCR的数据集并统一标注格式，以便实验需要
Table-OCR-1
Recognize tables from images and restore them into word.
onnx-coreml
ONNX to Core ML Converter
DB
A PyToch implementation of "Real-time Scene Text Detection with Differentiable Binarization".
wdsr
Wide Activation for Efficient Image and Video Super-Resolution