recognition_en.md 18.8 KB
Newer Older
1
# Text Recognition
K
Khanh Tran 已提交
2

3
- [1. Data Preparation](#DATA_PREPARATION)
W
WenmuZhou 已提交
4 5 6 7
    - [1.1 Costom Dataset](#Costom_Dataset)
    - [1.2 Dataset Download](#Dataset_download)
    - [1.3 Dictionary](#Dictionary)  
    - [1.4 Add Space Category](#Add_space_category)
W
WenmuZhou 已提交
8

9
- [2. Training](#TRAINING)
W
WenmuZhou 已提交
10
    - [2.1 Data Augmentation](#Data_Augmentation)
T
tink2123 已提交
11 12
    - [2.2 General Training](#Training)
    - [2.3 Multi-language Training](#Multi_language)
W
WenmuZhou 已提交
13

14
- [3. Evaluation](#EVALUATION)
W
WenmuZhou 已提交
15

16 17
- [4. Prediction](#PREDICTION)
- [5. Convert to Inference Model](#Inference)
W
WenmuZhou 已提交
18 19

<a name="DATA_PREPARATION"></a>
20
## 1. Data Preparation
K
Khanh Tran 已提交
21 22


W
WenmuZhou 已提交
23
PaddleOCR supports two data formats:
T
tink2123 已提交
24 25
- `LMDB` is used to train data sets stored in lmdb format(LMDBDataSet);
- `general data` is used to train data sets stored in text files(SimpleDataSet):
K
Khanh Tran 已提交
26 27 28 29 30 31

Please organize the dataset as follows:

The default storage path for training data is `PaddleOCR/train_data`, if you already have a dataset on your disk, just create a soft link to the dataset directory:

```
W
WenmuZhou 已提交
32
# linux and mac os
33
ln -sf <path/to/dataset> <path/to/paddle_ocr>/train_data/dataset
W
WenmuZhou 已提交
34 35
# windows
mklink /d <path/to/paddle_ocr>/train_data/dataset <path/to/dataset>
K
Khanh Tran 已提交
36 37
```

W
WenmuZhou 已提交
38
<a name="Costom_Dataset"></a>
39
### 1.1 Costom Dataset
K
Khanh Tran 已提交
40 41 42 43 44

If you want to use your own data for training, please refer to the following to organize your data.

- Training set

W
WenmuZhou 已提交
45
It is recommended to put the training images in the same folder, and use a txt file (rec_gt_train.txt) to store the image path and label. The contents of the txt file are as follows:
K
Khanh Tran 已提交
46 47 48 49 50 51

* Note: by default, the image path and image label are split with \t, if you use other methods to split, it will cause training error

```
" Image file name           Image annotation "

W
WenmuZhou 已提交
52 53
train_data/rec/train/word_001.jpg   简单可依赖
train_data/rec/train/word_002.jpg   用科技让复杂的世界更简单
W
WenmuZhou 已提交
54
...
K
Khanh Tran 已提交
55 56 57 58 59 60
```

The final training set should have the following file structure:

```
|-train_data
W
WenmuZhou 已提交
61
  |-rec
W
WenmuZhou 已提交
62 63 64 65 66 67
    |- rec_gt_train.txt
    |- train
        |- word_001.png
        |- word_002.jpg
        |- word_003.jpg
        | ...
K
Khanh Tran 已提交
68 69 70 71 72 73 74 75
```

- Test set

Similar to the training set, the test set also needs to be provided a folder containing all images (test) and a rec_gt_test.txt. The structure of the test set is as follows:

```
|-train_data
W
WenmuZhou 已提交
76
  |-rec
K
Khanh Tran 已提交
77 78 79 80 81 82 83 84
    |-ic15_data
        |- rec_gt_test.txt
        |- test
            |- word_001.jpg
            |- word_002.jpg
            |- word_003.jpg
            | ...
```
W
WenmuZhou 已提交
85 86

<a name="Dataset_download"></a>
87
### 1.2 Dataset Download
W
WenmuZhou 已提交
88

T
tink2123 已提交
89
- ICDAR2015
W
WenmuZhou 已提交
90

T
tink2123 已提交
91 92
If you do not have a dataset locally, you can download it on the official website [icdar2015](http://rrc.cvc.uab.es/?ch=4&com=downloads).
Also refer to [DTRB](https://github.com/clovaai/deep-text-recognition-benchmark#download-lmdb-dataset-for-traininig-and-evaluation-from-here) ,download the lmdb format dataset required for benchmark
W
WenmuZhou 已提交
93

94 95
If you want to reproduce the paper SAR, you need to download extra dataset [SynthAdd](https://pan.baidu.com/share/init?surl=uV0LtoNmcxbO-0YA7Ch4dg), extraction code: 627x. Besides, icdar2013, icdar2015, cocotext, IIIT5k datasets are also used to train. For specific details, please refer to the paper SAR.

W
WenmuZhou 已提交
96 97 98 99 100 101 102 103 104
PaddleOCR provides label files for training the icdar2015 dataset, which can be downloaded in the following ways:

```
# Training set label
wget -P ./train_data/ic15_data  https://paddleocr.bj.bcebos.com/dataset/rec_gt_train.txt
# Test Set Label
wget -P ./train_data/ic15_data  https://paddleocr.bj.bcebos.com/dataset/rec_gt_test.txt
```

T
tink2123 已提交
105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124
PaddleOCR also provides a data format conversion script, which can convert ICDAR official website label to a data format
supported by PaddleOCR. The data conversion tool is in `ppocr/utils/gen_label.py`, here is the training set as an example:

```
# convert the official gt to rec_gt_label.txt
python gen_label.py --mode="rec" --input_path="{path/of/origin/label}" --output_label="rec_gt_label.txt"
```

The data format is as follows, (a) is the original picture, (b) is the Ground Truth text file corresponding to each picture:

![](../datasets/icdar_rec.png)


- Multilingual dataset

The multi-language model training method is the same as the Chinese model. The training data set is 100w synthetic data. A small amount of fonts and test data can be downloaded using the following two methods.
* [Baidu Netdisk](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA) ,Extraction code:frgi.
* [Google drive](https://drive.google.com/file/d/18cSWX7wXSy4G0tbKJ0d9PuIaiwRLHpjA/view)


W
WenmuZhou 已提交
125
<a name="Dictionary"></a>
T
tink2123 已提交
126
### 1.3 Dictionary
K
Khanh Tran 已提交
127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142

Finally, a dictionary ({word_dict_name}.txt) needs to be provided so that when the model is trained, all the characters that appear can be mapped to the dictionary index.

Therefore, the dictionary needs to contain all the characters that you want to be recognized correctly. {word_dict_name}.txt needs to be written in the following format and saved in the `utf-8` encoding format:

```
l
d
a
d
r
n
```

In `word_dict.txt`, there is a single word in each line, which maps characters and numeric indexes together, e.g "and" will be mapped to [2 5 1]

W
WenmuZhou 已提交
143 144
PaddleOCR has built-in dictionaries, which can be used on demand.

K
Khanh Tran 已提交
145 146
`ppocr/utils/ppocr_keys_v1.txt` is a Chinese dictionary with 6623 characters.

W
WenmuZhou 已提交
147 148 149 150
`ppocr/utils/ic15_dict.txt` is an English dictionary with 63 characters

`ppocr/utils/dict/french_dict.txt` is a French dictionary with 118 characters

151
`ppocr/utils/dict/japan_dict.txt` is a Japanese dictionary with 4399 characters
W
WenmuZhou 已提交
152

T
tink2123 已提交
153
`ppocr/utils/dict/korean_dict.txt` is a Korean dictionary with 3636 characters
W
WenmuZhou 已提交
154

T
tink2123 已提交
155 156
`ppocr/utils/dict/german_dict.txt` is a German dictionary with 131 characters

T
tink2123 已提交
157
`ppocr/utils/en_dict.txt` is a English dictionary with 96 characters
W
WenmuZhou 已提交
158

X
xiaoting 已提交
159

W
WenmuZhou 已提交
160
The current multi-language model is still in the demo stage and will continue to optimize the model and add languages. **You are very welcome to provide us with dictionaries and fonts in other languages**,
littletomatodonkey's avatar
fix doc  
littletomatodonkey 已提交
161
If you like, you can submit the dictionary file to [dict](../../ppocr/utils/dict) and we will thank you in the Repo.
K
Khanh Tran 已提交
162 163 164 165


To customize the dict file, please modify the `character_dict_path` field in `configs/rec/rec_icdar15_train.yml` and set `character_type` to `ch`.

T
tink2123 已提交
166 167 168 169
- Custom dictionary

If you need to customize dic file, please add character_dict_path field in configs/rec/rec_icdar15_train.yml to point to your dictionary path. And set character_type to ch.

W
WenmuZhou 已提交
170
<a name="Add_space_category"></a>
171
### 1.4 Add Space Category
T
tink2123 已提交
172

173
If you want to support the recognition of the `space` category, please set the `use_space_char` field in the yml file to `True`.
T
tink2123 已提交
174 175 176

**Note: use_space_char only takes effect when character_type=ch**

W
WenmuZhou 已提交
177
<a name="TRAINING"></a>
178
## 2.Training
K
Khanh Tran 已提交
179

T
tink2123 已提交
180
<a name="Data_Augmentation"></a>
T
tink2123 已提交
181
### 2.1 Data Augmentation
T
tink2123 已提交
182 183 184 185 186 187 188 189

PaddleOCR provides a variety of data augmentation methods. All the augmentation methods are enabled by default.

The default perturbation methods are: cvtColor, blur, jitter, Gasuss noise, random crop, perspective, color reverse, TIA augmentation.

Each disturbance method is selected with a 40% probability during the training process. For specific code implementation, please refer to: [rec_img_aug.py](../../ppocr/data/imaug/rec_img_aug.py)

<a name="Training"></a>
T
tink2123 已提交
190
### 2.2 General Training
T
tink2123 已提交
191

K
Khanh Tran 已提交
192 193 194 195 196 197 198
PaddleOCR provides training scripts, evaluation scripts, and prediction scripts. In this section, the CRNN recognition model will be used as an example:

First download the pretrain model, you can download the trained model to finetune on the icdar2015 data:

```
cd PaddleOCR/
# Download the pre-trained model of MobileNetV3
T
tink2123 已提交
199
wget -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_none_bilstm_ctc_v2.0_train.tar
K
Khanh Tran 已提交
200 201
# Decompress model parameters
cd pretrain_models
T
tink2123 已提交
202
tar -xf rec_mv3_none_bilstm_ctc_v2.0_train.tar && rm -rf rec_mv3_none_bilstm_ctc_v2.0_train.tar
K
Khanh Tran 已提交
203 204 205 206 207
```

Start training:

```
T
tink2123 已提交
208
# GPU training Support single card and multi-card training
T
tink2123 已提交
209
# Training icdar15 English data and The training log will be automatically saved as train.log under "{save_model_dir}"
T
tink2123 已提交
210 211 212 213

#specify the single card training(Long training time, not recommended)
python3 tools/train.py -c configs/rec/rec_icdar15_train.yml
#specify the card number through --gpus
214
python3 -m paddle.distributed.launch --gpus '0,1,2,3'  tools/train.py -c configs/rec/rec_icdar15_train.yml
K
Khanh Tran 已提交
215
```
T
tink2123 已提交
216 217


K
Khanh Tran 已提交
218 219 220 221 222 223 224 225 226
PaddleOCR supports alternating training and evaluation. You can modify `eval_batch_step` in `configs/rec/rec_icdar15_train.yml` to set the evaluation frequency. By default, it is evaluated every 500 iter and the best acc model is saved under `output/rec_CRNN/best_accuracy` during the evaluation process.

If the evaluation set is large, the test will be time-consuming. It is recommended to reduce the number of evaluations, or evaluate after training.

* Tip: You can use the `-c` parameter to select multiple model configurations under the `configs/rec/` path for training. The recognition algorithms supported by PaddleOCR are:


| Configuration file |  Algorithm |   backbone |   trans   |   seq      |     pred     |
| :--------: |  :-------:   | :-------:  |   :-------:   |   :-----:   |  :-----:   |
227 228
| [rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml) |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  |
| [rec_chinese_common_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml) |  CRNN | ResNet34_vd |  None   |  BiLSTM |  ctc  |
K
Khanh Tran 已提交
229
| rec_chinese_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  |
W
WenmuZhou 已提交
230
| rec_chinese_common_train.yml |  CRNN |   ResNet34_vd |  None   |  BiLSTM |  ctc  |
K
Khanh Tran 已提交
231 232 233 234 235
| rec_icdar15_train.yml |  CRNN |   Mobilenet_v3 large 0.5 |  None   |  BiLSTM |  ctc  |
| rec_mv3_none_bilstm_ctc.yml |  CRNN |   Mobilenet_v3 large 0.5 |  None   |  BiLSTM |  ctc  |
| rec_mv3_none_none_ctc.yml |  Rosetta |   Mobilenet_v3 large 0.5 |  None   |  None |  ctc  |
| rec_r34_vd_none_bilstm_ctc.yml |  CRNN |   Resnet34_vd |  None   |  BiLSTM |  ctc  |
| rec_r34_vd_none_none_ctc.yml |  Rosetta |   Resnet34_vd |  None   |  None |  ctc  |
L
LDOUBLEV 已提交
236 237
| rec_mv3_tps_bilstm_att.yml |  CRNN |   Mobilenet_v3 |  TPS   |  BiLSTM |  att  |
| rec_r34_vd_tps_bilstm_att.yml |  CRNN |   Resnet34_vd |  TPS   |  BiLSTM |  att  |
T
tink2123 已提交
238
| rec_r50fpn_vd_none_srn.yml    | SRN | Resnet50_fpn_vd    | None    | rnn | srn |
T
Topdu 已提交
239
| rec_mtb_nrtr.yml    | NRTR | nrtr_mtb    | None    | transformer encoder | transformer decoder |
A
andyjpaddle 已提交
240
| rec_r31_sar.yml               | SAR | ResNet31 | None | LSTM encoder | LSTM decoder |
K
Khanh Tran 已提交
241 242


W
WenmuZhou 已提交
243
For training Chinese data, it is recommended to use
244
[rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml). If you want to try the result of other algorithms on the Chinese data set, please refer to the following instructions to modify the configuration file:
K
Khanh Tran 已提交
245
co
246
Take `rec_chinese_lite_train_v2.0.yml` as an example:
K
Khanh Tran 已提交
247 248 249
```
Global:
  ...
250 251
  # Add a custom dictionary, such as modify the dictionary, please point the path to the new dictionary
  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
K
Khanh Tran 已提交
252 253 254
  # Modify character type
  character_type: ch
  ...
255
  # Whether to recognize spaces
256
  use_space_char: True
K
Khanh Tran 已提交
257

258 259 260 261

Optimizer:
  ...
  # Add learning rate decay strategy
262 263 264 265 266 267 268 269 270
  lr:
    name: Cosine
    learning_rate: 0.001
  ...

...

Train:
  dataset:
M
MissPenguin 已提交
271
    # Type of dataset,we support LMDBDataSet and SimpleDataSet
272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290
    name: SimpleDataSet
    # Path of dataset
    data_dir: ./train_data/
    # Path of train list
    label_file_list: ["./train_data/train_list.txt"]
    transforms:
      ...
      - RecResizeImg:
          # Modify image_shape to fit long text
          image_shape: [3, 32, 320]
      ...
  loader:
    ...
    # Train batch_size for Single card
    batch_size_per_card: 256
    ...

Eval:
  dataset:
M
MissPenguin 已提交
291
    # Type of dataset,we support LMDBDataSet and SimpleDataSet
292 293 294 295 296 297 298 299 300 301 302 303 304 305 306
    name: SimpleDataSet
    # Path of dataset
    data_dir: ./train_data
    # Path of eval list
    label_file_list: ["./train_data/val_list.txt"]
    transforms:
      ...
      - RecResizeImg:
          # Modify image_shape to fit long text
          image_shape: [3, 32, 320]
      ...
  loader:
    # Eval batch_size for Single card
    batch_size_per_card: 256
    ...
K
Khanh Tran 已提交
307 308 309
```
**Note that the configuration file for prediction/evaluation must be consistent with the training.**

W
WenmuZhou 已提交
310
<a name="Multi_language"></a>
T
tink2123 已提交
311
### 2.3 Multi-language Training
T
tink2123 已提交
312 313 314

Currently, the multi-language algorithms supported by PaddleOCR are:

T
tink2123 已提交
315
| Configuration file |  Algorithm name |   backbone |   trans   |   seq      |     pred     |  language | character_type |
T
tink2123 已提交
316 317
| :--------: |  :-------:   | :-------:  |   :-------:   |   :-----:   |  :-----:   | :-----:  | :-----:  |
| rec_chinese_cht_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | chinese traditional  | chinese_cht|
T
tink2123 已提交
318
| rec_en_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | English(Case sensitive)   | EN |
T
tink2123 已提交
319 320 321 322
| rec_french_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | French |  french |
| rec_ger_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | German   | german |
| rec_japan_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | Japanese | japan |
| rec_korean_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | Korean  | korean |
T
tink2123 已提交
323 324 325 326
| rec_latin_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | Latin  | latin |
| rec_arabic_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | arabic |  ar |
| rec_cyrillic_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | cyrillic   | cyrillic |
| rec_devanagari_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | devanagari  | devanagari |
T
tink2123 已提交
327

T
tink2123 已提交
328
For more supported languages, please refer to : [Multi-language model](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_en/multi_languages_en.md#4-support-languages-and-abbreviations)
W
WenmuZhou 已提交
329 330 331 332 333 334 335 336 337


If you want to finetune on the basis of the existing model effect, please refer to the following instructions to modify the configuration file:

Take `rec_french_lite_train` as an example:

```
Global:
  ...
338
  # Add a custom dictionary, such as modify the dictionary, please point the path to the new dictionary
W
WenmuZhou 已提交
339 340
  character_dict_path: ./ppocr/utils/dict/french_dict.txt
  ...
341
  # Whether to recognize spaces
342
  use_space_char: True
343

W
WenmuZhou 已提交
344
...
345 346 347

Train:
  dataset:
M
MissPenguin 已提交
348
    # Type of dataset,we support LMDBDataSet and SimpleDataSet
349 350 351 352 353 354 355 356 357
    name: SimpleDataSet
    # Path of dataset
    data_dir: ./train_data/
    # Path of train list
    label_file_list: ["./train_data/french_train.txt"]
    ...

Eval:
  dataset:
M
MissPenguin 已提交
358
    # Type of dataset,we support LMDBDataSet and SimpleDataSet
359 360 361 362 363 364
    name: SimpleDataSet
    # Path of dataset
    data_dir: ./train_data
    # Path of eval list
    label_file_list: ["./train_data/french_val.txt"]
    ...
W
WenmuZhou 已提交
365
```
K
Khanh Tran 已提交
366

W
WenmuZhou 已提交
367
<a name="EVALUATION"></a>
368

369
## 3. Evalution
K
Khanh Tran 已提交
370

W
WenmuZhou 已提交
371
The evaluation dataset can be set by modifying the `Eval.dataset.label_file_list` field in the `configs/rec/rec_icdar15_train.yml` file.
K
Khanh Tran 已提交
372 373 374

```
# GPU evaluation, Global.checkpoints is the weight to be tested
W
WenmuZhou 已提交
375
python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_icdar15_train.yml -o Global.checkpoints={path/to/weights}/best_accuracy
K
Khanh Tran 已提交
376 377
```

W
WenmuZhou 已提交
378
<a name="PREDICTION"></a>
379
## 4. Prediction
K
Khanh Tran 已提交
380 381 382 383


Using the model trained by paddleocr, you can quickly get prediction through the following script.

T
tink2123 已提交
384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404
The default prediction picture is stored in `infer_img`, and the trained weight is specified via `-o Global.checkpoints`:


According to the `save_model_dir` and `save_epoch_step` fields set in the configuration file, the following parameters will be saved:

```
output/rec/
├── best_accuracy.pdopt  
├── best_accuracy.pdparams  
├── best_accuracy.states  
├── config.yml  
├── iter_epoch_3.pdopt  
├── iter_epoch_3.pdparams  
├── iter_epoch_3.states  
├── latest.pdopt  
├── latest.pdparams  
├── latest.states  
└── train.log
```

Among them, best_accuracy.* is the best model on the evaluation set; iter_epoch_x.* is the model saved at intervals of `save_epoch_step`; latest.* is the model of the last epoch.
K
Khanh Tran 已提交
405 406 407

```
# Predict English results
W
WenmuZhou 已提交
408
python3 tools/infer_rec.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.load_static_weights=false Global.infer_img=doc/imgs_words/en/word_1.jpg
K
Khanh Tran 已提交
409 410
```

T
tink2123 已提交
411

K
Khanh Tran 已提交
412 413
Input image:

414
![](../imgs_words/en/word_1.png)
K
Khanh Tran 已提交
415 416 417 418 419

Get the prediction result of the input image:

```
infer_img: doc/imgs_words/en/word_1.png
T
tink2123 已提交
420
        result: ('joint', 0.9998967)
K
Khanh Tran 已提交
421 422
```

423
The configuration file used for prediction must be consistent with the training. For example, you completed the training of the Chinese model with `python3 tools/train.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml`, you can use the following command to predict the Chinese model:
K
Khanh Tran 已提交
424 425 426

```
# Predict Chinese results
W
WenmuZhou 已提交
427
python3 tools/infer_rec.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.load_static_weights=false Global.infer_img=doc/imgs_words/ch/word_1.jpg
K
Khanh Tran 已提交
428 429 430 431
```

Input image:

432
![](../imgs_words/ch/word_1.jpg)
K
Khanh Tran 已提交
433 434 435 436 437

Get the prediction result of the input image:

```
infer_img: doc/imgs_words/ch/word_1.jpg
T
tink2123 已提交
438
        result: ('韩国小馆', 0.997218)
K
Khanh Tran 已提交
439
```
440 441 442

<a name="Inference"></a>

443
## 5. Convert to Inference Model
444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476

The recognition model is converted to the inference model in the same way as the detection, as follows:

```
# -c Set the training algorithm yml configuration file
# -o Set optional parameters
# Global.pretrained_model parameter Set the training model address to be converted without adding the file suffix .pdmodel, .pdopt or .pdparams.
# Global.save_inference_dir Set the address where the converted model will be saved.

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/
```

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.

After the conversion is successful, there are three files in the model save directory:

```
inference/det_db/
    ├── 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
```

- Text recognition model Inference using custom characters dictionary

  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`

  ```
  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_type="ch" --rec_char_dict_path="your text dict path"
  ```