BADBADBADBOY / Pytorchocr
基于pytorch的ocr算法库，包括 psenet, pan, dbnet, sast , crnn
Stars: ✭ 198
Projects that are alternatives of or similar to Pytorchocr
Ocr.pytorch
A pure pytorch implemented ocr project including text detection and recognition
Stars: ✭ 196 (-1.01%)
Mutual labels: crnn, ocr
Text renderer
Generate text images for training deep learning ocr model
Stars: ✭ 931 (+370.2%)
Mutual labels: crnn, ocr
CRNN.tf2
Convolutional Recurrent Neural Network(CRNN) for End-to-End Text Recognition - TensorFlow 2
Stars: ✭ 131 (-33.84%)
Mutual labels: ocr, crnn
Crnn.pytorch
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... ...
Stars: ✭ 145 (-26.77%)
Mutual labels: crnn, ocr
insightocr
MXNet OCR implementation. Including text recognition and detection.
Stars: ✭ 100 (-49.49%)
Mutual labels: ocr, crnn
Crnn With Stn
implement CRNN in Keras with Spatial Transformer Network
Stars: ✭ 83 (-58.08%)
Mutual labels: crnn, ocr
Deep Text Recognition Benchmark
Text recognition (optical character recognition) with deep learning methods.
Stars: ✭ 2,665 (+1245.96%)
Mutual labels: crnn, ocr
Easyocr
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
Stars: ✭ 13,379 (+6657.07%)
Mutual labels: crnn, ocr
crnn.mxnet
crnn in mxnet.can train with chinese characters
Stars: ✭ 47 (-76.26%)
Mutual labels: ocr, crnn
Crnn Mxnet Chinese Text Recognition
An implementation of CRNN (CNN+LSTM+warpCTC) on MxNet for chinese text recognition
Stars: ✭ 161 (-18.69%)
Mutual labels: crnn, ocr
BankCard-Recognizer
Identifying numbers from bankcard, based on Deep Learning with Keras [China Software Cup 2019]
Stars: ✭ 74 (-62.63%)
Mutual labels: ocr, crnn
Crnn attention ocr chinese
CRNN with attention to do OCR,add Chinese recognition
Stars: ✭ 315 (+59.09%)
Mutual labels: crnn, ocr
CRNN-OCR-lite
Lightweight CRNN for OCR (including handwritten text) with depthwise separable convolutions and spatial transformer module [keras+tf]
Stars: ✭ 130 (-34.34%)
Mutual labels: ocr, crnn
Sightseq
Computer vision tools for fairseq, containing PyTorch implementation of text recognition and object detection
Stars: ✭ 116 (-41.41%)
Mutual labels: crnn, ocr
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)
Stars: ✭ 18,084 (+9033.33%)
Mutual labels: crnn, ocr
Caffe Oneclick
Use caffe to train your own data in just one click
Stars: ✭ 187 (-5.56%)
Mutual labels: ocr
基于pytorch的OCR库
这里会有这个项目的代码详解和我的一些ocr经验和心得，我会慢慢更新，有兴趣可以看看，希望可以帮到新接触ocr的童鞋CSDN博客
最近跟新：
- 2021.03.06 更新CRNN backbone resnet 和 mobilev3 以及配置文件
- 2020.12.22 更新CRNN+CTCLoss+CenterLoss训练
- 2020.09.18 更新文本检测说明文档
- 2020.09.12 更新DB,pse,pan,sast,crnn训练测试代码和预训练模型
目前已完成:
接下来计划：
- [x] 模型转onnx及调用测试
- [x] 模型压缩（剪枝）
- [ ] 模型压缩（量化）
- [x] 模型蒸馏
- [x] tensorrt部署
- [ ] 训练通用化ocr模型
- [ ] 结合chinese_lite进行部署
- [ ] 手机端部署
检测模型效果(实验中)
训练只在ICDAR2015文本检测公开数据集上，算法效果如下： |模型|骨干网络|precision|recall|Hmean|下载链接| |-|-|-|-|-|-| |DB|ResNet50_77|85.88%|79.10%|82.35%|下载链接(code:fxw6)| |DB|ResNet50_33|86.51%|80.59%|83.44%|下载链接(code:fxw6)| |DB|MobileNetV3|82.89%|75.83%|79.20%|下载链接(code:fxw6)| |SAST|ResNet50_77|85.72%|78.38%|81.89%|下载链接(code:fxw6)| |SAST|ResNet50_33|86.67%|76.74%|81.40%|下载链接(code:fxw6)| |PSE|ResNet50_77|84.10%|80.01%|82.01%|下载链接(code:fxw6)| |PSE|ResNet50_33|82.56%|78.91%|80.69%|下载链接(code:fxw6)| |PAN|ResNet18_77|81.80%|77.08%|79.37%|下载链接(code:fxw6)| |PAN|ResNet18_33|83.78%|75.15%|79.23%|下载链接(code:fxw6)|
模型压缩剪枝效果
这里使用mobilev3作为backbone，在icdar2015上测试结果，未压缩模型初始大小为2.4M.
- 对backbone进行压缩
| 模型 | pruned method | ratio | model size(M) | precision | recall | Hmean |
|---|---|---|---|---|---|---|
| DB | no | 0 | 2.4 | 84.04% | 75.34% | 79.46% |
| DB | backbone | 0.5 | 1.9 | 83.74% | 73.18% | 78.10% |
| DB | backbone | 0.6 | 1.58 | 84.46% | 69.90% | 76.50% |
- 对整个模型进行压缩
| 模型 | pruned method | ratio | model size(M) | precision | recall | Hmean |
|---|---|---|---|---|---|---|
| DB | no | 0 | 2.4 | 85.70% | 74.77% | 79.86% |
| DB | total | 0.6 | 1.42 | 82.97% | 75.10% | 78.84% |
| DB | total | 0.65 | 1.15 | 85.14% | 72.84% | 78.51% |
模型蒸馏
| 模型 | teacher | student | model size(M) | precision | recall | Hmean | improve(%) |
|---|---|---|---|---|---|---|---|
| DB | no | mobilev3 | 2.4 | 85.70% | 74.77% | 79.86% | - |
| DB | resnet50 | mobilev3 | 2.4 | 86.37% | 77.22% | 81.54% | 1.68 |
| DB | no | mobilev3 | 1.42 | 82.97% | 75.10% | 78.84% | - |
| DB | resnet50 | mobilev3 | 1.42 | 85.88% | 76.16% | 80.73% | 1.89 |
| DB | no | mobilev3 | 1.15 | 85.14% | 72.84% | 78.51% | - |
| DB | resnet50 | mobilev3 | 1.15 | 85.60% | 74.72% | 79.79% | 1.28 |
文档教程
文本检测效果
有问题及交流加微信
微信号：-fxwispig-
参考
- https://github.com/PaddlePaddle/PaddleOCR
- https://github.com/whai362/PSENet
- https://github.com/whai362/pan_pp.pytorch
- https://github.com/WenmuZhou/PAN.pytorch
- https://github.com/xiaolai-sqlai/mobilenetv3
- https://github.com/BADBADBADBOY/DBnet-lite.pytorch
- https://github.com/BADBADBADBOY/Psenet_v2
- https://github.com/BADBADBADBOY/pse-lite.pytorch
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].