inference_en.md 24.5 KB
Newer Older
K
Khanh Tran 已提交
1

2
# Inference Based on Python Prediction Engine
K
Khanh Tran 已提交
3

W
WenmuZhou 已提交
4
The inference model (the model saved by `paddle.jit.save`) is generally a solidified model saved after the model training is completed, and is mostly used to give prediction in deployment.
K
Khanh Tran 已提交
5 6 7

The model saved during the training process is the checkpoints model, which saves the parameters of the model and is mostly used to resume training.

L
LDOUBLEV 已提交
8
Compared with the checkpoints model, the inference model will additionally save the structural information of the model. Therefore, it is easier to deploy because the model structure and model parameters are already solidified in the inference model file, and is suitable for integration with actual systems.
L
LDOUBLEV 已提交
9
For more details, please refer to the document [Classification Framework](https://github.com/PaddlePaddle/PaddleClas/blob/release%2F2.0/docs/zh_CN/extension/paddle_mobile_inference.md).
K
Khanh Tran 已提交
10

W
WenmuZhou 已提交
11
Next, we first introduce how to convert a trained model into an inference model, and then we will introduce text detection, text recognition, angle class, and the concatenation of them based on inference model.
K
Khanh Tran 已提交
12

13 14 15 16
- [1. Convert Training Model to Inference Model](#CONVERT)
    - [1.1 Convert Detection Model to Inference Model](#Convert_detection_model)
    - [1.2 Convert Recognition Model to Inference Model](#Convert_recognition_model)
    - [1.3 Convert Angle Classification Model to Inference Model](#Convert_angle_class_model)
W
WenmuZhou 已提交
17 18


19 20 21 22 23
- [2. Text Detection Model Inference](#DETECTION_MODEL_INFERENCE)
    - [2.1 Lightweight Chinese Detection Model Inference](#LIGHTWEIGHT_DETECTION)
    - [2.2 DB Text Detection Model Inference](#DB_DETECTION)
    - [2.3 East Text Detection Model Inference](#EAST_DETECTION)
    - [2.4 Sast Text Detection Model Inference](#SAST_DETECTION)
T
tink2123 已提交
24

25 26 27 28 29 30
- [3. Text Recognition Model Inference](#RECOGNITION_MODEL_INFERENCE)
    - [3.1 Lightweight Chinese Text Recognition Model Reference](#LIGHTWEIGHT_RECOGNITION)
    - [3.2 CTC-Based Text Recognition Model Inference](#CTC-BASED_RECOGNITION)
    - [3.3 SRN-Based Text Recognition Model Inference](#SRN-BASED_RECOGNITION)
    - [3.4 Text Recognition Model Inference Using Custom Characters Dictionary](#USING_CUSTOM_CHARACTERS)
    - [3.5 Multilingual Model Inference](#MULTILINGUAL_MODEL_INFERENCE)
W
WenmuZhou 已提交
31

32
- [4. Angle Classification Model Inference](#ANGLE_CLASS_MODEL_INFERENCE)
W
WenmuZhou 已提交
33

34 35 36
- [5. Text Detection Angle Classification And Recognition Inference Concatenation](#CONCATENATION)
    - [5.1 Lightweight Chinese Model](#LIGHTWEIGHT_CHINESE_MODEL)
    - [5.2 Other Models](#OTHER_MODELS)
W
WenmuZhou 已提交
37

L
licx 已提交
38
<a name="CONVERT"></a>
39
## 1. Convert Training Model to Inference Model
L
licx 已提交
40
<a name="Convert_detection_model"></a>
41 42

### 1.1 Convert Detection Model to Inference Model
K
Khanh Tran 已提交
43

X
xxxpsyduck 已提交
44
Download the lightweight Chinese detection model:
K
Khanh Tran 已提交
45
```
W
WenmuZhou 已提交
46
wget -P ./ch_lite/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar && tar xf ./ch_lite/ch_ppocr_mobile_v2.0_det_train.tar -C ./ch_lite/
K
Khanh Tran 已提交
47
```
W
WenmuZhou 已提交
48

K
Khanh Tran 已提交
49 50
The above model is a DB algorithm trained with MobileNetV3 as the backbone. To convert the trained model into an inference model, just run the following command:
```
W
WenmuZhou 已提交
51 52
# -c Set the training algorithm yml configuration file
# -o Set optional parameters
W
WenmuZhou 已提交
53
# Global.pretrained_model parameter Set the training model address to be converted without adding the file suffix .pdmodel, .pdopt or .pdparams.
W
WenmuZhou 已提交
54
# Global.save_inference_dir Set the address where the converted model will be saved.
T
tink2123 已提交
55

56
python3 tools/export_model.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml -o Global.pretrained_model=./ch_lite/ch_ppocr_mobile_v2.0_det_train/best_accuracy  Global.save_inference_dir=./inference/det_db/
K
Khanh Tran 已提交
57
```
W
WenmuZhou 已提交
58

W
WenmuZhou 已提交
59
When converting to an inference model, the configuration file used is the same as the configuration file used during training. In addition, you also need to set the `Global.pretrained_model` parameter in the configuration file.
W
WenmuZhou 已提交
60
After the conversion is successful, there are three files in the model save directory:
K
Khanh Tran 已提交
61 62
```
inference/det_db/
63 64 65
    ├── inference.pdiparams         # The parameter file of detection inference model
    ├── inference.pdiparams.info    # The parameter information of detection inference model, which can be ignored
    └── inference.pdmodel           # The program file of detection inference model
K
Khanh Tran 已提交
66 67
```

L
licx 已提交
68
<a name="Convert_recognition_model"></a>
69
### 1.2 Convert Recognition Model to Inference Model
K
Khanh Tran 已提交
70

X
xxxpsyduck 已提交
71
Download the lightweight Chinese recognition model:
K
Khanh Tran 已提交
72
```
W
WenmuZhou 已提交
73
wget -P ./ch_lite/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar && tar xf ./ch_lite/ch_ppocr_mobile_v2.0_rec_train.tar -C ./ch_lite/
K
Khanh Tran 已提交
74 75 76 77
```

The recognition model is converted to the inference model in the same way as the detection, as follows:
```
W
WenmuZhou 已提交
78 79
# -c Set the training algorithm yml configuration file
# -o Set optional parameters
W
WenmuZhou 已提交
80
# Global.pretrained_model parameter Set the training model address to be converted without adding the file suffix .pdmodel, .pdopt or .pdparams.
W
WenmuZhou 已提交
81
# Global.save_inference_dir Set the address where the converted model will be saved.
T
tink2123 已提交
82

83
python3 tools/export_model.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.pretrained_model=./ch_lite/ch_ppocr_mobile_v2.0_rec_train/best_accuracy  Global.save_inference_dir=./inference/rec_crnn/
K
Khanh Tran 已提交
84 85 86 87
```

If you have a model trained on your own dataset with a different dictionary file, please make sure that you modify the `character_dict_path` in the configuration file to your dictionary file path.

W
WenmuZhou 已提交
88
After the conversion is successful, there are three files in the model save directory:
K
Khanh Tran 已提交
89
```
W
WenmuZhou 已提交
90
inference/det_db/
91 92 93
    ├── inference.pdiparams         # The parameter file of recognition inference model
    ├── inference.pdiparams.info    # The parameter information of recognition inference model, which can be ignored
    └── inference.pdmodel           # The program file of recognition model
K
Khanh Tran 已提交
94 95
```

W
WenmuZhou 已提交
96
<a name="Convert_angle_class_model"></a>
97
### 1.3 Convert Angle Classification Model to Inference Model
W
WenmuZhou 已提交
98 99 100

Download the angle classification model:
```
W
WenmuZhou 已提交
101
wget -P ./ch_lite/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar && tar xf ./ch_lite/ch_ppocr_mobile_v2.0_cls_train.tar -C ./ch_lite/
W
WenmuZhou 已提交
102 103 104 105
```

The angle classification model is converted to the inference model in the same way as the detection, as follows:
```
W
WenmuZhou 已提交
106 107
# -c Set the training algorithm yml configuration file
# -o Set optional parameters
W
WenmuZhou 已提交
108
# Global.pretrained_model parameter Set the training model address to be converted without adding the file suffix .pdmodel, .pdopt or .pdparams.
W
WenmuZhou 已提交
109
# Global.save_inference_dir Set the address where the converted model will be saved.
W
WenmuZhou 已提交
110

111
python3 tools/export_model.py -c configs/cls/cls_mv3.yml -o Global.pretrained_model=./ch_lite/ch_ppocr_mobile_v2.0_cls_train/best_accuracy  Global.save_inference_dir=./inference/cls/
W
WenmuZhou 已提交
112 113 114 115
```

After the conversion is successful, there are two files in the directory:
```
W
WenmuZhou 已提交
116
inference/det_db/
117 118 119
    ├── inference.pdiparams         # The parameter file of angle class inference model
    ├── inference.pdiparams.info    # The parameter information of  angle class inference model, which can be ignored
    └── inference.pdmodel           # The program file of angle class model
W
WenmuZhou 已提交
120 121 122
```


L
licx 已提交
123
<a name="DETECTION_MODEL_INFERENCE"></a>
124
## 2. Text Detection Model Inference
K
Khanh Tran 已提交
125

T
tink2123 已提交
126 127
The following will introduce the lightweight Chinese detection model inference, DB text detection model inference and EAST text detection model inference. The default configuration is based on the inference setting of the DB text detection model.
Because EAST and DB algorithms are very different, when inference, it is necessary to **adapt the EAST text detection algorithm by passing in corresponding parameters**.
K
Khanh Tran 已提交
128

L
licx 已提交
129
<a name="LIGHTWEIGHT_DETECTION"></a>
130
### 2.1 Lightweight Chinese Detection Model Inference
K
Khanh Tran 已提交
131

X
xxxpsyduck 已提交
132
For lightweight Chinese detection model inference, you can execute the following commands:
K
Khanh Tran 已提交
133 134

```
L
LDOUBLEV 已提交
135 136 137 138
# download DB text detection inference model
wget  https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar
tar xf ch_ppocr_mobile_v2.0_det_infer.tar
# predict
L
LDOUBLEV 已提交
139
python3 tools/infer/predict_det.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./inference/det_db/"
K
Khanh Tran 已提交
140 141
```

fanruinet's avatar
fanruinet 已提交
142
The visual 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:
K
Khanh Tran 已提交
143

L
LDOUBLEV 已提交
144
![](../imgs_results/det_res_00018069.jpg)
K
Khanh Tran 已提交
145

L
LDOUBLEV 已提交
146
You can use the parameters `limit_type` and `det_limit_side_len` to limit the size of the input image,
M
MissPenguin 已提交
147
The optional parameters of `limit_type` are [`max`, `min`], and
L
LDOUBLEV 已提交
148
`det_limit_size_len` is a positive integer, generally set to a multiple of 32, such as 960.
K
Khanh Tran 已提交
149

L
LDOUBLEV 已提交
150 151 152 153 154
The default setting of the parameters is `limit_type='max', det_limit_side_len=960`. Indicates that the longest side of the network input image cannot exceed 960,
If this value is exceeded, the image will be resized with the same width ratio to ensure that the longest side is `det_limit_side_len`.
Set as `limit_type='min', det_limit_side_len=960`, it means that the shortest side of the image is limited to 960.

If the resolution of the input picture is relatively large and you want to use a larger resolution prediction, you can set det_limit_side_len to the desired value, such as 1216:
K
Khanh Tran 已提交
155
```
W
WenmuZhou 已提交
156
python3 tools/infer/predict_det.py --image_dir="./doc/imgs/1.jpg" --det_model_dir="./inference/det_db/" --det_limit_type=max --det_limit_side_len=1216
K
Khanh Tran 已提交
157 158 159 160
```

If you want to use the CPU for prediction, execute the command as follows
```
W
WenmuZhou 已提交
161
python3 tools/infer/predict_det.py --image_dir="./doc/imgs/1.jpg" --det_model_dir="./inference/det_db/" --use_gpu=False
K
Khanh Tran 已提交
162 163
```

L
licx 已提交
164
<a name="DB_DETECTION"></a>
165
### 2.2 DB Text Detection Model Inference
K
Khanh Tran 已提交
166

W
WenmuZhou 已提交
167
First, convert the model saved in the DB text detection training process into an inference model. Taking the model based on the Resnet50_vd backbone network and trained on the ICDAR2015 English dataset as an example ([model download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_db_v2.0_train.tar)), you can use the following command to convert:
K
Khanh Tran 已提交
168 169

```
170
python3 tools/export_model.py -c configs/det/det_r50_vd_db.yml -o Global.pretrained_model=./det_r50_vd_db_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/det_db
K
Khanh Tran 已提交
171 172 173 174 175 176 177 178 179 180
```

DB text detection model inference, you can execute the following command:

```
python3 tools/infer/predict_det.py --image_dir="./doc/imgs_en/img_10.jpg" --det_model_dir="./inference/det_db/"
```

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:

181
![](../imgs_results/det_res_img_10_db.jpg)
K
Khanh Tran 已提交
182 183 184

**Note**: Since the ICDAR2015 dataset has only 1,000 training images, mainly for English scenes, the above model has very poor detection result on Chinese text images.

L
licx 已提交
185
<a name="EAST_DETECTION"></a>
186
### 2.3 EAST TEXT DETECTION MODEL INFERENCE
K
Khanh Tran 已提交
187

M
MissPenguin 已提交
188
First, convert the model saved in the EAST text detection training process into an inference model. Taking the model based on the Resnet50_vd backbone network and trained on the ICDAR2015 English dataset as an example ([model download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar)), you can use the following command to convert:
K
Khanh Tran 已提交
189 190

```
191
python3 tools/export_model.py -c configs/det/det_r50_vd_east.yml -o Global.pretrained_model=./det_r50_vd_east_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/det_east
K
Khanh Tran 已提交
192
```
L
licx 已提交
193
**For EAST text detection model inference, you need to set the parameter ``--det_algorithm="EAST"``**, run the following command:
K
Khanh Tran 已提交
194 195 196 197

```
python3 tools/infer/predict_det.py --image_dir="./doc/imgs_en/img_10.jpg" --det_model_dir="./inference/det_east/" --det_algorithm="EAST"
```
L
licx 已提交
198

K
Khanh Tran 已提交
199 200
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:

M
MissPenguin 已提交
201
![](../imgs_results/det_res_img_10_east.jpg)
K
Khanh Tran 已提交
202

L
licx 已提交
203 204 205 206
**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.


<a name="SAST_DETECTION"></a>
207
### 2.4 Sast Text Detection Model Inference
L
licx 已提交
208
#### (1). Quadrangle text detection model (ICDAR2015)  
M
MissPenguin 已提交
209
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 ICDAR2015 English dataset as an example ([model download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_icdar15_v2.0_train.tar)), you can use the following command to convert:
L
licx 已提交
210 211

```
212
python3 tools/export_model.py -c configs/det/det_r50_vd_sast_icdar15.yml -o Global.pretrained_model=./det_r50_vd_sast_icdar15_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/det_sast_ic15
L
licx 已提交
213 214 215
```

**For SAST quadrangle text detection model inference, you need to set the parameter `--det_algorithm="SAST"`**, run the following command:
K
Khanh Tran 已提交
216

L
licx 已提交
217 218 219 220 221
```
python3 tools/infer/predict_det.py --det_algorithm="SAST" --image_dir="./doc/imgs_en/img_10.jpg" --det_model_dir="./inference/det_sast_ic15/"
```

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:
K
Khanh Tran 已提交
222

M
MissPenguin 已提交
223
![](../imgs_results/det_res_img_10_sast.jpg)
L
licx 已提交
224 225

#### (2). Curved text detection model (Total-Text)  
M
MissPenguin 已提交
226
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](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_totaltext_v2.0_train.tar)), you can use the following command to convert:
L
licx 已提交
227 228

```
229
python3 tools/export_model.py -c configs/det/det_r50_vd_sast_totaltext.yml -o Global.pretrained_model=./det_r50_vd_sast_totaltext_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/det_sast_tt
L
licx 已提交
230 231
```

W
opt doc  
WenmuZhou 已提交
232
For SAST curved text detection model inference, you need to set the parameter `--det_algorithm="SAST"` and `--det_sast_polygon=True`, run the following command:
L
licx 已提交
233 234 235 236 237 238 239

```
python3 tools/infer/predict_det.py --det_algorithm="SAST" --image_dir="./doc/imgs_en/img623.jpg" --det_model_dir="./inference/det_sast_tt/" --det_sast_polygon=True
```

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:

M
MissPenguin 已提交
240
![](../imgs_results/det_res_img623_sast.jpg)
L
licx 已提交
241 242 243 244

**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.

<a name="RECOGNITION_MODEL_INFERENCE"></a>
245
## 3. Text Recognition Model Inference
K
Khanh Tran 已提交
246

fanruinet's avatar
fanruinet 已提交
247
The following will introduce the lightweight Chinese recognition model inference, other CTC-based and Attention-based text recognition models inference. For Chinese text recognition, it is recommended to choose the recognition model based on CTC loss. In practice, it is also found that the result of the model based on Attention loss is not as good as the one based on CTC loss. In addition, if the characters dictionary is modified during training, make sure that you use the same characters set during inference. Please check below for details.
K
Khanh Tran 已提交
248 249


L
licx 已提交
250
<a name="LIGHTWEIGHT_RECOGNITION"></a>
251
### 3.1 Lightweight Chinese Text Recognition Model Reference
K
Khanh Tran 已提交
252

X
xxxpsyduck 已提交
253
For lightweight Chinese recognition model inference, you can execute the following commands:
K
Khanh Tran 已提交
254 255

```
W
WenmuZhou 已提交
256 257 258 259
# download CRNN text recognition inference model
wget  https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar
tar xf ch_ppocr_mobile_v2.0_rec_infer.tar
python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_10.png" --rec_model_dir="ch_ppocr_mobile_v2.0_rec_infer"
K
Khanh Tran 已提交
260 261
```

W
WenmuZhou 已提交
262
![](../imgs_words_en/word_10.png)
K
Khanh Tran 已提交
263 264 265

After executing the command, the prediction results (recognized text and score) of the above image will be printed on the screen.

W
WenmuZhou 已提交
266
```bash
W
WenmuZhou 已提交
267
Predicts of ./doc/imgs_words_en/word_10.png:('PAIN', 0.9897658)
W
WenmuZhou 已提交
268
```
K
Khanh Tran 已提交
269

L
licx 已提交
270
<a name="CTC-BASED_RECOGNITION"></a>
271
### 3.2 CTC-Based Text Recognition Model Inference
K
Khanh Tran 已提交
272

W
WenmuZhou 已提交
273
Taking CRNN as an example, we introduce the recognition model inference based on CTC loss. Rosetta and Star-Net are used in a similar way, No need to set the recognition algorithm parameter rec_algorithm.
K
Khanh Tran 已提交
274

W
WenmuZhou 已提交
275
First, convert the model saved in the CRNN text recognition training process into an inference model. Taking the model based on Resnet34_vd backbone network, using MJSynth and SynthText (two English text recognition synthetic datasets) for training, as an example ([model download address](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_none_bilstm_ctc_v2.0_train.tar)). It can be converted as follow:
K
Khanh Tran 已提交
276 277

```
278
python3 tools/export_model.py -c configs/det/rec_r34_vd_none_bilstm_ctc.yml -o Global.pretrained_model=./rec_r34_vd_none_bilstm_ctc_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/rec_crnn
K
Khanh Tran 已提交
279 280
```

W
WenmuZhou 已提交
281
For CRNN text recognition model inference, execute the following commands:
K
Khanh Tran 已提交
282 283

```
T
tink2123 已提交
284
python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./inference/starnet/" --rec_image_shape="3, 32, 100" --rec_char_dict_path="./ppocr/utils/ic15_dict.txt"
K
Khanh Tran 已提交
285
```
X
xxxpsyduck 已提交
286

W
WenmuZhou 已提交
287
![](../imgs_words_en/word_336.png)
K
Khanh Tran 已提交
288

W
WenmuZhou 已提交
289 290 291 292 293
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)
```
294

X
xxxpsyduck 已提交
295
**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:
K
Khanh Tran 已提交
296 297 298 299 300 301 302 303 304 305

- 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`.

- Character list: the experiment in the DTRB paper is only for 26 lowercase English characters and 10 numbers, a total of 36 characters. All upper and lower case characters are converted to lower case characters, and characters not in the above list are ignored and considered as spaces. Therefore, no characters dictionary file is used here, but a dictionary is generated by the below command. Therefore, the parameter `rec_char_type` needs to be set during inference, which is specified as "en" in English.

```
self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"
dict_character = list(self.character_str)
```

T
tink2123 已提交
306
<a name="SRN-BASED_RECOGNITION"></a>
307
### 3.3 SRN-Based Text Recognition Model Inference
T
tink2123 已提交
308 309 310 311 312 313 314 315 316

The recognition model based on SRN requires additional setting of the recognition algorithm parameter
--rec_algorithm="SRN". At the same time, it is necessary to ensure that the predicted shape is consistent
with the training, such as: --rec_image_shape="1, 64, 256"

```
python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" \
                                    --rec_model_dir="./inference/srn/" \
                                    --rec_image_shape="1, 64, 256" \
T
tink2123 已提交
317
                                    --rec_char_dict_path="./ppocr/utils/ic15_dict.txt" \
T
tink2123 已提交
318 319 320
                                    --rec_algorithm="SRN"
```

L
licx 已提交
321
<a name="USING_CUSTOM_CHARACTERS"></a>
322
### 3.4 Text Recognition Model Inference Using Custom Characters Dictionary
W
WenmuZhou 已提交
323
If the text dictionary is modified during training, when using the inference model to predict, you need to specify the dictionary path used by `--rec_char_dict_path`, and set `rec_char_type=ch`
L
LDOUBLEV 已提交
324 325

```
T
tink2123 已提交
326
python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./your inference model" --rec_image_shape="3, 32, 100"  --rec_char_dict_path="your text dict path"
L
LDOUBLEV 已提交
327 328
```

W
WenmuZhou 已提交
329
<a name="MULTILINGUAL_MODEL_INFERENCE"></a>
330 331

### 3.5 Multilingual Model Inference
W
WenmuZhou 已提交
332
If you need to predict other language models, when using inference model prediction, you need to specify the dictionary path used by `--rec_char_dict_path`. At the same time, in order to get the correct visualization results,
T
tink2123 已提交
333
You need to specify the visual font path through `--vis_font_path`. There are small language fonts provided by default under the `doc/fonts` path, such as Korean recognition:
W
WenmuZhou 已提交
334 335

```
T
tink2123 已提交
336
python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/korean/1.jpg" --rec_model_dir="./your inference model"  --rec_char_dict_path="ppocr/utils/dict/korean_dict.txt" --vis_font_path="doc/fonts/korean.ttf"
W
WenmuZhou 已提交
337 338 339 340 341 342
```
![](../imgs_words/korean/1.jpg)

After executing the command, the prediction result of the above figure is:

``` text
W
WenmuZhou 已提交
343
Predicts of ./doc/imgs_words/korean/1.jpg:('바탕으로', 0.9948904)
W
WenmuZhou 已提交
344 345 346
```

<a name="ANGLE_CLASSIFICATION_MODEL_INFERENCE"></a>
347
## 4. Angle Classification Model Inference
W
WenmuZhou 已提交
348 349 350 351

For angle classification model inference, you can execute the following commands:

```
W
WenmuZhou 已提交
352
python3 tools/infer/predict_cls.py --image_dir="./doc/imgs_words_en/word_10.png" --cls_model_dir="./inference/cls/"
W
WenmuZhou 已提交
353
```
W
WenmuZhou 已提交
354 355 356 357 358 359
```
# download text angle class inference model:
wget  https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar
tar xf ch_ppocr_mobile_v2.0_cls_infer.tar
python3 tools/infer/predict_cls.py --image_dir="./doc/imgs_words_en/word_10.png" --cls_model_dir="ch_ppocr_mobile_v2.0_cls_infer"
```
W
WenmuZhou 已提交
360
![](../imgs_words_en/word_10.png)
W
WenmuZhou 已提交
361 362 363

After executing the command, the prediction results (classification angle and score) of the above image will be printed on the screen.

W
WenmuZhou 已提交
364
```
W
WenmuZhou 已提交
365
 Predicts of ./doc/imgs_words_en/word_10.png:['0', 0.9999995]
W
WenmuZhou 已提交
366
```
W
WenmuZhou 已提交
367

L
licx 已提交
368
<a name="CONCATENATION"></a>
369
## 5. Text Detection Angle Classification and Recognition Inference Concatenation
K
Khanh Tran 已提交
370

L
licx 已提交
371
<a name="LIGHTWEIGHT_CHINESE_MODEL"></a>
372
### 5.1 Lightweight Chinese Model
K
Khanh Tran 已提交
373

littletomatodonkey's avatar
littletomatodonkey 已提交
374
When performing prediction, you need to specify the path of a single image or a folder of images through the parameter `image_dir`, the parameter `det_model_dir` specifies the path to detect the inference model, the parameter `cls_model_dir` specifies the path to angle classification inference model and the parameter `rec_model_dir` specifies the path to identify the inference model. The parameter `use_angle_cls` is used to control whether to enable the angle classification model. The parameter `use_mp` specifies whether to use multi-process to infer `total_process_num` specifies process number when using multi-process. The parameter . The visualized recognition results are saved to the `./inference_results` folder by default.
K
Khanh Tran 已提交
375

littletomatodonkey's avatar
littletomatodonkey 已提交
376
```shell
W
WenmuZhou 已提交
377
# use direction classifier
W
WenmuZhou 已提交
378
python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./inference/det_db/" --cls_model_dir="./inference/cls/" --rec_model_dir="./inference/rec_crnn/" --use_angle_cls=true
W
WenmuZhou 已提交
379 380

# not use use direction classifier
W
WenmuZhou 已提交
381
python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./inference/det_db/" --rec_model_dir="./inference/rec_crnn/"
littletomatodonkey's avatar
littletomatodonkey 已提交
382 383 384 385

# use multi-process
python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./inference/det_db/" --rec_model_dir="./inference/rec_crnn/" --use_angle_cls=false --use_mp=True --total_process_num=6
```
386

K
Khanh Tran 已提交
387 388 389

After executing the command, the recognition result image is as follows:

W
WenmuZhou 已提交
390
![](../imgs_results/system_res_00018069.jpg)
K
Khanh Tran 已提交
391

L
licx 已提交
392
<a name="OTHER_MODELS"></a>
393
### 5.2 Other Models
K
Khanh Tran 已提交
394

L
licx 已提交
395 396 397 398 399
If you want to try other detection algorithms or recognition algorithms, please refer to the above text detection model inference and text recognition model inference, update the corresponding configuration and model.

**Note: due to the limitation of rotation logic of detected box, SAST curved text detection model (using the parameter `det_sast_polygon=True`) is not supported for model combination yet.**

The following command uses the combination of the EAST text detection and STAR-Net text recognition:
K
Khanh Tran 已提交
400 401

```
T
tink2123 已提交
402
python3 tools/infer/predict_system.py --image_dir="./doc/imgs_en/img_10.jpg" --det_model_dir="./inference/det_east/" --det_algorithm="EAST" --rec_model_dir="./inference/starnet/" --rec_image_shape="3, 32, 100" --rec_char_dict_path="./ppocr/utils/ic15_dict.txt"
K
Khanh Tran 已提交
403 404 405 406
```

After executing the command, the recognition result image is as follows:

W
WenmuZhou 已提交
407
![](../imgs_results/img_10_east_starnet.jpg)