hjgw's repositories
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
CurricularFace
CurricularFace(CVPR2020)
CV-Backbones
CV backbones including GhostNet, TinyNet and TNT, developed by Huawei Noah's Ark Lab.
DeepLearning-500-questions
深度学习500问,以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述,以帮助自己及有需要的读者。 全书分为18个章节,50余万字。由于水平有限,书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作,联系scutjy2015@163.com 版权所有,违权必究 Tan 2018.06
efficientnetv2.pytorch
PyTorch implementation of EfficientNetV2 family
FudanOCR
FudanOCR: A modularized and extensible OCR framework for text detection and recognition.
gpu-stress-test
Small GPU / CUDA stress bundle as a Docker image
mobilenext
non-official PyTorch implementation of MobileNeXt from paper [Rethinking Bottleneck Structure for Efficient Mobile Network Design]
MSER
the MSER for text detection
PaddleOCR
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
ssdlite-pytorch-mobilenext
A PyTorch implementation of SSDLite on COCO
TextGenerator
OCR dataset Text-Detection dataset Font-Classification dataset generator
ultralytics
YOLOv8 🚀 in PyTorch > ONNX > CoreML > TFLite
XFUND
XFUND: A Multilingual Form Understanding Benchmark