opensource/PaddleOCR
3
0
Fork 0
mirror of https://github.com/PaddlePaddle/PaddleOCR.git synced 2026-09-24 23:33:08 +08:00
Code Issues Packages Projects Releases Wiki Activity

add svtr and nrtr docs

Browse Source
This commit is contained in:
Topdu
2022-04-28 06:25:47 +00:00
parent 0b4106a6de
commit dd093c4e8d
1 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/doc_ch/algorithm_rec_svtr.md
+7 -7
View File
@@ -33,10 +33,10 @@
| SVTR |IC13<br/>857 | SVT |IIIT5k<br/>3000 |IC15<br/>1811| SVTP |CUTE80 | Avg_6 |IC15<br/>2077 |IC13<br/>1015 |IC03<br/>867|IC03<br/>860|Avg_10 |Chinese| 英文<br/>链接 | 中文<br/>链接 |
|:-----:|:------:|:-----:|:---------:|:------:|:-----:|:-----:|:-----:|:-------:|:-------:|:-----:|:-----:|:-----:|:-----:|:---------:|:---------:|
| Large | 97.20 | 91.65 | 96.30 | 86.58 | 88.37 | 95.14 | 92.82 | 84.54 | 96.35 | 96.54 | 96.74 | 92.24 | 72.10 | [模型&配置](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_svtr_large_en_train/.tar) | [模型&配置](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_svtr_large_ch_train/.tar) |
| Base | 97.08 | 91.50 | 96.03 | 85.20 | 89.92 | 91.67 | 92.33 | 83.73 | 95.66 | 95.62 | 95.81 | 91.61 | 71.40 | [模型&配置](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_r31_sar_train.tar) | [TODO]() |
| Small | 95.92 | 93.04 | 95.03 | 84.70 | 87.91 | 92.01 | 91.63 | 82.72 | 94.88 | 96.08 | 96.28 | 91.02 | 69.00 | [模型&配置](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_svtr_small_en_train/.tar) | [模型&配置](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_svtr_small_ch_train/.tar) |
| Tiny | 96.85 | 91.34 | 94.53 | 83.99 | 85.43 | 89.24 | 90.87 | 80.55 | 95.37 | 95.27 | 95.70 | 90.13 | 67.90 | [模型&配置](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_svtr_tiny_en_train/.tar) | [模型&配置](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_svtr_tiny_ch_train/.tar) |
| Large | 97.20 | 91.65 | 96.30 | 86.58 | 88.37 | 95.14 | 92.82 | 84.54 | 96.35 | 96.54 | 96.74 | 92.24 | 72.10 | [模型&配置](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/rec_svtr_large_none_ctc_en_train/.tar) | [模型&配置](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/rec_svtr_large_none_ctc_ch_train/.tar) |
| Base | 97.08 | 91.50 | 96.03 | 85.20 | 89.92 | 91.67 | 92.33 | 83.73 | 95.66 | 95.62 | 95.81 | 91.61 | 71.40 | [模型&配置](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/rec_svtr_base_none_ctc_en_train.tar) | - |
| Small | 95.92 | 93.04 | 95.03 | 84.70 | 87.91 | 92.01 | 91.63 | 82.72 | 94.88 | 96.08 | 96.28 | 91.02 | 69.00 | [模型&配置](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/rec_svtr_small_none_ctc_en_train/.tar) | [模型&配置](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/rec_svtr_small_none_ctc_ch_train/.tar) |
| Tiny | 96.85 | 91.34 | 94.53 | 83.99 | 85.43 | 89.24 | 90.87 | 80.55 | 95.37 | 95.27 | 95.70 | 90.13 | 67.90 | [模型&配置](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/rec_svtr_tiny_none_ctc_en_train/.tar) | [模型&配置](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/rec_svtr_tiny_none_ctc_ch_train/.tar) |
@@ -71,7 +71,7 @@
```shell
# 注意将pretrained_model的路径设置为本地路径。
python3 tools/eval.py -c ./rec_svtr_tiny_en_train/rec_svtr_tiny_6local_6global_stn_en.yml -o Global.pretrained_model=./rec_svtr_tiny_en_train/best_accuracy
python3 tools/eval.py -c ./rec_svtr_tiny_en_train/rec_svtr_tiny_6local_6global_stn_en.yml -o Global.pretrained_model=./rec_svtr_tiny_none_ctc_en_train/best_accuracy
# 测试中文数据集时，需将`scene_val`数据集修改为`scene_test`，才能得到论文中的结果。
```
@@ -81,7 +81,7 @@ python3 tools/eval.py -c ./rec_svtr_tiny_en_train/rec_svtr_tiny_6local_6global_s
使用如下命令进行单张图片预测：
```shell
# 注意将pretrained_model的路径设置为本地路径。
python3 tools/infer_rec.py -c ./rec_svtr_tiny_en_train/rec_svtr_tiny_6local_6global_stn_en.yml -o Global.infer_img='./doc/imgs_words_en/word_10.png' Global.pretrained_model=./rec_svtr_tiny_en_train/best_accuracy Global.load_static_weights=false
python3 tools/infer_rec.py -c ./rec_svtr_tiny_en_train/rec_svtr_tiny_6local_6global_stn_en.yml -o Global.infer_img='./doc/imgs_words_en/word_10.png' Global.pretrained_model=./rec_svtr_tiny_none_ctc_en_train/best_accuracy Global.load_static_weights=false
# 预测文件夹下所有图像时，可修改infer_img为文件夹，如 Global.infer_img='./doc/imgs_words_en/'。
```
@@ -95,7 +95,7 @@ python3 tools/infer_rec.py -c ./rec_svtr_tiny_en_train/rec_svtr_tiny_6local_6glo
```shell
# 注意将pretrained_model的路径设置为本地路径。
python3 tools/export_model.py -c ./rec_svtr_tiny_en_train/rec_svtr_tiny_6local_6global_stn_en.yml -o Global.pretrained_model=./rec_svtr_tiny_en_train/best_accuracy Global.save_inference_dir=./inference/rec_svtr_tiny_stn_en/ Global.load_static_weights=False
python3 tools/export_model.py -c ./rec_svtr_tiny_en_train/rec_svtr_tiny_6local_6global_stn_en.yml -o Global.pretrained_model=./rec_svtr_tiny_none_ctc_en_train/best_accuracy Global.save_inference_dir=./inference/rec_svtr_tiny_stn_en/ Global.load_static_weights=False
```
执行如下命令进行模型推理：