File tree Expand file tree Collapse file tree 1 file changed +11
-2
lines changed
Expand file tree Collapse file tree 1 file changed +11
-2
lines changed Original file line number Diff line number Diff line change 1+ <div align =" center " >
12
23# MindOCR
34
4- <!--
5+ [ ![ CI ] ( https://github.com/mindspore-lab/mindocr/actions/workflows/ci.yml/badge.svg )] ( https://github.com/mindspore-lab/mindocr/actions/workflows/ci.yml )
56[ ![ license] ( https://img.shields.io/github/license/mindspore-lab/mindocr.svg )] ( https://github.com/mindspore-lab/mindocr/blob/main/LICENSE )
67[ ![ open issues] ( https://img.shields.io/github/issues/mindspore-lab/mindocr )] ( https://github.com/mindspore-lab/mindocr/issues )
78[ ![ PRs] ( https://img.shields.io/badge/PRs-welcome-pink.svg )] ( https://github.com/mindspore-lab/mindocr/pulls )
8- -->
9+ [ ![ Code style: black] ( https://img.shields.io/badge/code%20style-black-000000.svg )] ( https://github.com/psf/black )
10+
11+
912[ English] ( README.md ) | 中文
1013
1114[ 概述] ( #introduction ) |
1417[ 模型列表] ( #supported-models-and-performance ) |
1518[ 注释] ( #notes )
1619
20+ </div >
1721
1822## 概述
1923MindOCR是一个基于[ MindSpore] ( https://www.mindspore.cn/en ) 框架的OCR开发及应用的开源工具箱,可以帮助用户训练、应用业界最有优的文本检测、文本识别模型,例如DBNet/DBNet++和CRNN/SVTR,以实现图像文本理解的需求。
@@ -245,10 +249,15 @@ python tools/eval.py --config configs/rec/crnn/crnn_resnet34.yaml
245249| CRNN | VGG7 | 82.03% | [YAML](configs/rec/crnn/crnn_vgg7.yaml) |
246250| CRNN | Resnet34_vd | 84.45% | [YAML](configs/rec/crnn/crnn_resnet34.yaml) |
247251
252+ 模型配置及性能详细介绍请见[configs](./configs).
248253
249254# # 注释
250255
251256# ## 变更日志
257+ - 2023/03/23
258+ 1. 增加dynamic loss scaler支持, 且与drop overflow update兼容。如需使用, 请在配置文件中增加`loss_scale`字段并将`type`参数设为`dynamic`,参考例子请见`configs/rec/crnn/crnn_icdar15.yaml`
259+
260+
252261- 2023/03/20
2532621. 参数名修改:`output_keys` -> `output_columns`;`num_keys_to_net` -> `num_columns_to_net`;
2542632. 更新数据流程。
You can’t perform that action at this time.
0 commit comments