forgetest5
/
PaddleOCR
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

update inference result

This commit is contained in:
WenmuZhou 2020-12-12 13:28:33 +08:00
parent 8ddeec8428
commit d3ca2e426e
5 changed files with 25 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
doc/doc_ch/inference.md
View File

@ -186,7 +186,7 @@ python3 tools/infer/predict_det.py --det_algorithm="EAST" --image_dir="./doc/img
``` ```
可视化文本检测结果默认保存到`./inference_results`文件夹里面，结果文件的名称前缀为'det_res'。结果示例如下： 可视化文本检测结果默认保存到`./inference_results`文件夹里面，结果文件的名称前缀为'det_res'。结果示例如下：
![](../imgs_results/det_res_img_10_east.jpg) (coming soon)
**注意**：本代码库中，EAST后处理Locality-Aware NMS有python和c++两种版本，c++版速度明显快于python版。由于c++版本nms编译版本问题，只有python3.5环境下会调用c++版nms，其他情况将调用python版nms。 **注意**：本代码库中，EAST后处理Locality-Aware NMS有python和c++两种版本，c++版速度明显快于python版。由于c++版本nms编译版本问题，只有python3.5环境下会调用c++版nms，其他情况将调用python版nms。
@ -205,7 +205,7 @@ python3 tools/infer/predict_det.py --det_algorithm="SAST" --image_dir="./doc/img
``` ```
可视化文本检测结果默认保存到`./inference_results`文件夹里面，结果文件的名称前缀为'det_res'。结果示例如下： 可视化文本检测结果默认保存到`./inference_results`文件夹里面，结果文件的名称前缀为'det_res'。结果示例如下：
![](../imgs_results/det_res_img_10_sast.jpg) (coming soon)
#### (2). 弯曲文本检测模型（Total-Text） #### (2). 弯曲文本检测模型（Total-Text）
首先将SAST文本检测训练过程中保存的模型，转换成inference model。以基于Resnet50_vd骨干网络，在Total-Text英文数据集训练的模型为例（[模型下载地址(coming soon)](link))，可以使用如下命令进行转换： 首先将SAST文本检测训练过程中保存的模型，转换成inference model。以基于Resnet50_vd骨干网络，在Total-Text英文数据集训练的模型为例（[模型下载地址(coming soon)](link))，可以使用如下命令进行转换：
@ -221,7 +221,7 @@ python3 tools/infer/predict_det.py --det_algorithm="SAST" --image_dir="./doc/img
``` ```
可视化文本检测结果默认保存到`./inference_results`文件夹里面，结果文件的名称前缀为'det_res'。结果示例如下： 可视化文本检测结果默认保存到`./inference_results`文件夹里面，结果文件的名称前缀为'det_res'。结果示例如下：
![](../imgs_results/det_res_img623_sast.jpg) (coming soon)
**注意**：本代码库中，SAST后处理Locality-Aware NMS有python和c++两种版本，c++版速度明显快于python版。由于c++版本nms编译版本问题，只有python3.5环境下会调用c++版nms，其他情况将调用python版nms。 **注意**：本代码库中，SAST后处理Locality-Aware NMS有python和c++两种版本，c++版速度明显快于python版。由于c++版本nms编译版本问题，只有python3.5环境下会调用c++版nms，其他情况将调用python版nms。
@ -245,8 +245,9 @@ python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/ch/word_4.jpg"
执行命令后，上面图像的预测结果（识别的文本和得分）会打印到屏幕上，示例如下： 执行命令后，上面图像的预测结果（识别的文本和得分）会打印到屏幕上，示例如下：
Predicts of ./doc/imgs_words/ch/word_4.jpg:['实力活力', 0.89552695] ```bash
Predicts of ./doc/imgs_words/ch/word_4.jpg:('实力活力', 0.98458153)
```
<a name="基于CTC损失的识别模型推理"></a> <a name="基于CTC损失的识别模型推理"></a>
### 2. 基于CTC损失的识别模型推理 ### 2. 基于CTC损失的识别模型推理
@ -281,7 +282,9 @@ python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png
执行命令后，上面图像的识别结果如下： 执行命令后，上面图像的识别结果如下：
Predicts of ./doc/imgs_words_en/word_336.png:['super', 0.9999555] ```bash
Predicts of ./doc/imgs_words_en/word_336.png:('super', 0.9999073)
```
**注意**：由于上述模型是参考[DTRB](https://arxiv.org/abs/1904.01906)文本识别训练和评估流程，与超轻量级中文识别模型训练有两方面不同： **注意**：由于上述模型是参考[DTRB](https://arxiv.org/abs/1904.01906)文本识别训练和评估流程，与超轻量级中文识别模型训练有两方面不同：
@ -313,9 +316,7 @@ python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/korean/1.jpg" -
执行命令后，上图的预测结果为： 执行命令后，上图的预测结果为：
``` text ``` text
2020-09-19 16:15:05,076-INFO: index: [205 206 38 39] Predicts of ./doc/imgs_words/korean/1.jpg:('바탕으로', 0.9948904)
2020-09-19 16:15:05,077-INFO: word : 바탕으로
2020-09-19 16:15:05,077-INFO: score: 0.9171358942985535
``` ```
<a name="方向分类模型推理"></a> <a name="方向分类模型推理"></a>
@ -378,4 +379,4 @@ python3 tools/infer/predict_system.py --image_dir="./doc/imgs_en/img_10.jpg" --d
执行命令后，识别结果图像如下： 执行命令后，识别结果图像如下：
![](../imgs_results/img_10.jpg) (coming soon)

25
doc/doc_en/inference_en.md
View File

@ -192,7 +192,7 @@ python3 tools/infer/predict_det.py --image_dir="./doc/imgs_en/img_10.jpg" --det_
The visualized text detection results are saved to the `./inference_results` folder by default, and the name of the result file is prefixed with 'det_res'. Examples of results are as follows: The visualized text detection results are saved to the `./inference_results` folder by default, and the name of the result file is prefixed with 'det_res'. Examples of results are as follows:
![](../imgs_results/det_res_img_10_east.jpg) (coming soon)
**Note**: EAST post-processing locality aware NMS has two versions: Python and C++. The speed of C++ version is obviously faster than that of Python version. Due to the compilation version problem of NMS of C++ version, C++ version NMS will be called only in Python 3.5 environment, and python version NMS will be called in other cases. **Note**: EAST post-processing locality aware NMS has two versions: Python and C++. The speed of C++ version is obviously faster than that of Python version. Due to the compilation version problem of NMS of C++ version, C++ version NMS will be called only in Python 3.5 environment, and python version NMS will be called in other cases.
@ -214,7 +214,7 @@ python3 tools/infer/predict_det.py --det_algorithm="SAST" --image_dir="./doc/img
The visualized text detection results are saved to the `./inference_results` folder by default, and the name of the result file is prefixed with 'det_res'. Examples of results are as follows: The visualized text detection results are saved to the `./inference_results` folder by default, and the name of the result file is prefixed with 'det_res'. Examples of results are as follows:
![](../imgs_results/det_res_img_10_sast.jpg) (coming soon)
#### (2). Curved text detection model (Total-Text) #### (2). Curved text detection model (Total-Text)
First, convert the model saved in the SAST text detection training process into an inference model. Taking the model based on the Resnet50_vd backbone network and trained on the Total-Text English dataset as an example ([model download link (coming soon)](https://paddleocr.bj.bcebos.com/SAST/sast_r50_vd_total_text.tar)), you can use the following command to convert: First, convert the model saved in the SAST text detection training process into an inference model. Taking the model based on the Resnet50_vd backbone network and trained on the Total-Text English dataset as an example ([model download link (coming soon)](https://paddleocr.bj.bcebos.com/SAST/sast_r50_vd_total_text.tar)), you can use the following command to convert:
@ -231,7 +231,7 @@ python3 tools/infer/predict_det.py --det_algorithm="SAST" --image_dir="./doc/img
The visualized text detection results are saved to the `./inference_results` folder by default, and the name of the result file is prefixed with 'det_res'. Examples of results are as follows: The visualized text detection results are saved to the `./inference_results` folder by default, and the name of the result file is prefixed with 'det_res'. Examples of results are as follows:
![](../imgs_results/det_res_img623_sast.jpg) (coming soon)
**Note**: SAST post-processing locality aware NMS has two versions: Python and C++. The speed of C++ version is obviously faster than that of Python version. Due to the compilation version problem of NMS of C++ version, C++ version NMS will be called only in Python 3.5 environment, and python version NMS will be called in other cases. **Note**: SAST post-processing locality aware NMS has two versions: Python and C++. The speed of C++ version is obviously faster than that of Python version. Due to the compilation version problem of NMS of C++ version, C++ version NMS will be called only in Python 3.5 environment, and python version NMS will be called in other cases.
@ -254,8 +254,9 @@ python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/ch/word_4.jpg"
After executing the command, the prediction results (recognized text and score) of the above image will be printed on the screen. After executing the command, the prediction results (recognized text and score) of the above image will be printed on the screen.
Predicts of ./doc/imgs_words/ch/word_4.jpg:['实力活力', 0.89552695] ```bash
Predicts of ./doc/imgs_words/ch/word_4.jpg:('实力活力', 0.98458153)
```
<a name="CTC-BASED_RECOGNITION"></a> <a name="CTC-BASED_RECOGNITION"></a>
### 2. CTC-BASED TEXT RECOGNITION MODEL INFERENCE ### 2. CTC-BASED TEXT RECOGNITION MODEL INFERENCE
@ -276,7 +277,6 @@ python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png
<a name="ATTENTION-BASED_RECOGNITION"></a> <a name="ATTENTION-BASED_RECOGNITION"></a>
### 3. ATTENTION-BASED TEXT RECOGNITION MODEL INFERENCE ### 3. ATTENTION-BASED TEXT RECOGNITION MODEL INFERENCE
![](../imgs_words_en/word_336.png)
The recognition model based on Attention loss is different from ctc, and additional recognition algorithm parameters need to be set --rec_algorithm="RARE" The recognition model based on Attention loss is different from ctc, and additional recognition algorithm parameters need to be set --rec_algorithm="RARE"
After executing the command, the recognition result of the above image is as follows: After executing the command, the recognition result of the above image is as follows:
@ -284,8 +284,13 @@ After executing the command, the recognition result of the above image is as fol
python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./inference/rare/" --rec_image_shape="3, 32, 100" --rec_char_type="en" --rec_algorithm="RARE" python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./inference/rare/" --rec_image_shape="3, 32, 100" --rec_char_type="en" --rec_algorithm="RARE"
``` ```
Predicts of ./doc/imgs_words_en/word_336.png:['super', 0.9999555] ![](../imgs_words_en/word_336.png)
After executing the command, the recognition result of the above image is as follows:
```bash
Predicts of ./doc/imgs_words_en/word_336.png:('super', 0.9999073)
```
**Note**：Since the above model refers to [DTRB](https://arxiv.org/abs/1904.01906) text recognition training and evaluation process, it is different from the training of lightweight Chinese recognition model in two aspects: **Note**：Since the above model refers to [DTRB](https://arxiv.org/abs/1904.01906) text recognition training and evaluation process, it is different from the training of lightweight Chinese recognition model in two aspects:
- The image resolution used in training is different: the image resolution used in training the above model is [3，32，100], while during our Chinese model training, in order to ensure the recognition effect of long text, the image resolution used in training is [3, 32, 320]. The default shape parameter of the inference stage is the image resolution used in training phase, that is [3, 32, 320]. Therefore, when running inference of the above English model here, you need to set the shape of the recognition image through the parameter `rec_image_shape`. - The image resolution used in training is different: the image resolution used in training the above model is [3，32，100], while during our Chinese model training, in order to ensure the recognition effect of long text, the image resolution used in training is [3, 32, 320]. The default shape parameter of the inference stage is the image resolution used in training phase, that is [3, 32, 320]. Therefore, when running inference of the above English model here, you need to set the shape of the recognition image through the parameter `rec_image_shape`.
@ -318,9 +323,7 @@ python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/korean/1.jpg" -
After executing the command, the prediction result of the above figure is: After executing the command, the prediction result of the above figure is:
``` text ``` text
2020-09-19 16:15:05,076-INFO: index: [205 206 38 39] Predicts of ./doc/imgs_words/korean/1.jpg:('바탕으로', 0.9948904)
2020-09-19 16:15:05,077-INFO: word : 바탕으로
2020-09-19 16:15:05,077-INFO: score: 0.9171358942985535
``` ```
<a name="ANGLE_CLASSIFICATION_MODEL_INFERENCE"></a> <a name="ANGLE_CLASSIFICATION_MODEL_INFERENCE"></a>
@ -381,4 +384,4 @@ python3 tools/infer/predict_system.py --image_dir="./doc/imgs_en/img_10.jpg" --d
After executing the command, the recognition result image is as follows: After executing the command, the recognition result image is as follows:
![](../imgs_results/img_10.jpg) (coming soon)

BIN
doc/imgs_results/2.jpg
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 148 KiB

After

Width:  |  Height:  |  Size: 92 KiB

BIN
doc/imgs_results/det_res_2.jpg
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 80 KiB

After

Width:  |  Height:  |  Size: 77 KiB

BIN
doc/imgs_results/det_res_img_10_db.jpg
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 330 KiB

After

Width:  |  Height:  |  Size: 331 KiB