未验证 提交 86a812e5 编写于 作者: D Double_V 提交者: GitHub

Merge pull request #11 from tink2123/update_doc

Update doc
......@@ -58,10 +58,10 @@ PaddleOCR开源的文本检测算法列表:
算法效果:
|模型|骨干网络|Hmean|
|-|-|-|
|EAST|[ResNet50_vd](https://paddleocr.bj.bcebos.com/det_r50_vd_east.tar)|85.85%|
|EAST|[MobileNetV3](https://paddleocr.bj.bcebos.com/det_mv3_east.tar)|79.08%|
|DB|[ResNet50_vd](https://paddleocr.bj.bcebos.com/det_r50_vd_db.tar)|83.30%|
|DB|[MobileNetV3](https://paddleocr.bj.bcebos.com/det_mv3_db.tar)|73.00%|
|[EAST](https://paddleocr.bj.bcebos.com/det_r50_vd_east.tar)|ResNet50_vd|85.85%|
|[EAST](https://paddleocr.bj.bcebos.com/det_mv3_east.tar)|MobileNetV3|79.08%|
|[DB](https://paddleocr.bj.bcebos.com/det_r50_vd_db.tar)|ResNet50_vd|83.30%|
|[DB](https://paddleocr.bj.bcebos.com/det_mv3_db.tar)|MobileNetV3|73.00%|
PaddleOCR文本检测算法的训练与使用请参考[文档](./doc/detection.md)
......@@ -78,14 +78,14 @@ PaddleOCR开源的文本识别算法列表:
|模型|骨干网络|ACC|
|-|-|-|
|Rosetta|[Resnet34_vd](https://paddleocr.bj.bcebos.com/rec_r34_vd_none_none_ctc.tar)|80.24%|
|Rosetta|[MobileNetV3](https://paddleocr.bj.bcebos.com/rec_mv3_none_none_ctc.tar)|78.16%|
|CRNN|[Resnet34_vd](https://paddleocr.bj.bcebos.com/rec_r34_vd_none_bilstm_ctc.tar)|82.20%|
|CRNN|[MobileNetV3](https://paddleocr.bj.bcebos.com/rec_mv3_none_bilstm_ctc.tar)|79.37%|
|STAR-Net|[Resnet34_vd](https://paddleocr.bj.bcebos.com/rec_r34_vd_tps_bilstm_ctc.tar)|83.93%|
|STAR-Net|[MobileNetV3](https://paddleocr.bj.bcebos.com/rec_mv3_tps_bilstm_ctc.tar)|81.56%|
|RARE|[Resnet34_vd](https://paddleocr.bj.bcebos.com/rec_r34_vd_tps_bilstm_attn.tar)|84.90%|
|RARE|[MobileNetV3](https://paddleocr.bj.bcebos.com/rec_mv3_tps_bilstm_attn.tar)|83.32%|
|[Rosetta](https://paddleocr.bj.bcebos.com/rec_r34_vd_none_none_ctc.tar)|Resnet34_vd|80.24%|
|[Rosetta](https://paddleocr.bj.bcebos.com/rec_mv3_none_none_ctc.tar)|MobileNetV3|78.16%|
|[CRNN](https://paddleocr.bj.bcebos.com/rec_r34_vd_none_bilstm_ctc.tar)|Resnet34_vd|82.20%|
|[CRNN](https://paddleocr.bj.bcebos.com/rec_mv3_none_bilstm_ctc.tar)|MobileNetV3|79.37%|
|[STAR-Net](https://paddleocr.bj.bcebos.com/rec_r34_vd_tps_bilstm_ctc.tar)|Resnet34_vd|83.93%|
|[STAR-Net](https://paddleocr.bj.bcebos.com/rec_mv3_tps_bilstm_ctc.tar)|MobileNetV3|81.56%|
|[RARE](https://paddleocr.bj.bcebos.com/rec_r34_vd_tps_bilstm_attn.tar)|Resnet34_vd|84.90%|
|[RARE](https://paddleocr.bj.bcebos.com/rec_mv3_tps_bilstm_attn.tar)|MobileNetV3|83.32%|
PaddleOCR文本识别算法的训练与使用请参考[文档](./doc/recognition.md)
......
......@@ -12,7 +12,6 @@ Global:
image_shape: [3, 32, 100]
max_text_length: 25
character_type: en
character_dict_path: /workspace/PaddleOCR/train_data/ic15_dict.txt
loss_type: ctc
reader_yml: ./configs/rec/rec_icdar15_reader.yml
pretrain_weights: ./pretrain_models/CRNN/best_accuracy
......
......@@ -3,7 +3,7 @@
### 数据准备
PaddleOCR 支持两种数据格式: `lmdb` 用于训练公开数据,调试算法, `通用数据` 训练自己的数据:
PaddleOCR 支持两种数据格式: `lmdb` 用于训练公开数据,调试算法; `通用数据` 训练自己的数据:
请按如下步骤设置数据集:
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册