jakeywu / ocr_torchLinks
ocr_torch是基于Torch1.8实现的DBNet(2.2M) + CRNN(3.8M)实现的轻量级文字检测识别项目(支持onnx推理).
☆29Updated 4 years ago
Alternatives and similar repositories for ocr_torch
Users that are interested in ocr_torch are comparing it to the libraries listed below
Sorting:
- you can use dbnet to detect word or bar code,Knowledge Distillation is provided,also python tensorrt inference is provided.☆46Updated 4 years ago
- A pytorch re-implementation of Real-time Scene Text Detection with Differentiable Binarization☆110Updated 4 years ago
- 将原本Keras版本的AdvancedEAST改写成PyTorch版，将数据集由.npy文件改成一个LMDB文件，加入Precision，Recall, F1 score方便训练以及调试，底层网络仍然用VGG16。☆38Updated 4 years ago
- 身份证全卡面文字识别：Faster-rcnn检测图片里的证件照，DBNet检测证件照里的文字，CRNN识别证件照里的文字☆43Updated 4 years ago
- 带有位置信息的中文文本识别数据生成器☆11Updated 4 years ago
- end2end layout analysis based seq2seq☆132Updated 4 years ago
- 中文文本合成 for OCR☆12Updated 2 years ago
- DBNet on onnx and tensorRT☆20Updated 4 years ago
- ocr with yolo3 as feature extractor, implemented by keras, and accelerated by tensorrt☆34Updated 4 years ago
- ☆35Updated 4 years ago
- UNet实现文档印章消除☆28Updated 5 years ago
- ☆18Updated 4 years ago
- 从NLP出发对于OCR的深度实践集锦，重在实战☆89Updated 4 years ago
- 表格结构解析新思路（表格识别新思路）☆125Updated 4 years ago
- Re-implementation of MASTER by mmocr☆89Updated 3 years ago
- dbnet文字检测，添加文本框分类☆15Updated 2 years ago
- crnn实现水平和垂直方向中文文字识别, 提供在3w多个中文字符训练的水平识别和垂直识别的预训练模型; 欢迎关注,试用和反馈问题... ...☆250Updated 4 years ago
- 本项目旨在以CRAFT提供的预训练模型为基础，进行迁移学习以用于检测自己数据集中的文本。☆44Updated 5 years ago
- Papers, Datasets, Algorithms, SOTA for STR. Long-time Maintaining☆102Updated 3 years ago
- synthesize the OCR training data☆38Updated 4 years ago
- pytorch, ctpn ,text detection ,ocr,文本检测☆141Updated 4 years ago
- A pytorch re-implementation of Real-time Scene Text Detection with Differentiable Binarization☆23Updated 4 years ago
- text_recognition_toolbox: The reimplementation of a series of classical scene text recognition papers with Pytorch in a uniform way.☆178Updated 3 years ago
- ☆26Updated 4 years ago
- ctcloss + centerloss crnn text recognition☆200Updated 4 years ago
- ☆152Updated 4 years ago
- Document photo perspective transformation correction，利用unet网络进行 文档照片透视纠偏☆49Updated 4 years ago
- (WIP)The deployment framework aims to provide a simple, lightweight, fast integrated, pipelined deployment framework for algorithm servic…☆137Updated 3 years ago
- Using deep-leaning detect tables in the documet image☆26Updated 5 years ago
- pytorch version of svtr model☆24Updated 3 years ago