recognition_en.md 18.9 KB
Newer Older
tink2123's avatar
tink2123 committed
1
# TEXT RECOGNITION
Khanh Tran's avatar
Khanh Tran committed
2

WenmuZhou's avatar
WenmuZhou committed
3
4
5
6
7
- [1 DATA PREPARATION](#DATA_PREPARATION)
    - [1.1 Costom Dataset](#Costom_Dataset)
    - [1.2 Dataset Download](#Dataset_download)
    - [1.3 Dictionary](#Dictionary)  
    - [1.4 Add Space Category](#Add_space_category)
WenmuZhou's avatar
WenmuZhou committed
8

WenmuZhou's avatar
WenmuZhou committed
9
10
- [2 TRAINING](#TRAINING)
    - [2.1 Data Augmentation](#Data_Augmentation)
tink2123's avatar
tink2123 committed
11
12
    - [2.2 General Training](#Training)
    - [2.3 Multi-language Training](#Multi_language)
WenmuZhou's avatar
WenmuZhou committed
13

WenmuZhou's avatar
WenmuZhou committed
14
- [3 EVALUATION](#EVALUATION)
WenmuZhou's avatar
WenmuZhou committed
15

WenmuZhou's avatar
WenmuZhou committed
16
17
- [4 PREDICTION](#PREDICTION)
    - [4.1 Training engine prediction](#Training_engine_prediction)
18
- [5 CONVERT TO INFERENCE MODEL](#Inference)
WenmuZhou's avatar
WenmuZhou committed
19
20

<a name="DATA_PREPARATION"></a>
tink2123's avatar
tink2123 committed
21
## 1 DATA PREPARATION
Khanh Tran's avatar
Khanh Tran committed
22
23


WenmuZhou's avatar
WenmuZhou committed
24
PaddleOCR supports two data formats:
tink2123's avatar
tink2123 committed
25
26
- `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):
Khanh Tran's avatar
Khanh Tran committed
27
28
29
30
31
32

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:

```
WenmuZhou's avatar
WenmuZhou committed
33
# linux and mac os
34
ln -sf <path/to/dataset> <path/to/paddle_ocr>/train_data/dataset
WenmuZhou's avatar
WenmuZhou committed
35
36
# windows
mklink /d <path/to/paddle_ocr>/train_data/dataset <path/to/dataset>
Khanh Tran's avatar
Khanh Tran committed
37
38
```

WenmuZhou's avatar
WenmuZhou committed
39
<a name="Costom_Dataset"></a>
tink2123's avatar
tink2123 committed
40
### 1.1 Costom dataset
Khanh Tran's avatar
Khanh Tran committed
41
42
43
44
45

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

- Training set

WenmuZhou's avatar
WenmuZhou committed
46
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:
Khanh Tran's avatar
Khanh Tran committed
47
48
49
50
51
52

* 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 "

WenmuZhou's avatar
WenmuZhou committed
53
54
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
WenmuZhou's avatar
WenmuZhou committed
55
...
Khanh Tran's avatar
Khanh Tran committed
56
57
58
59
60
61
```

The final training set should have the following file structure:

```
|-train_data
WenmuZhou's avatar
WenmuZhou committed
62
  |-rec
WenmuZhou's avatar
WenmuZhou committed
63
64
65
66
67
68
    |- rec_gt_train.txt
    |- train
        |- word_001.png
        |- word_002.jpg
        |- word_003.jpg
        | ...
Khanh Tran's avatar
Khanh Tran committed
69
70
71
72
73
74
75
76
```

- 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
WenmuZhou's avatar
WenmuZhou committed
77
  |-rec
Khanh Tran's avatar
Khanh Tran committed
78
79
80
81
82
83
84
85
    |-ic15_data
        |- rec_gt_test.txt
        |- test
            |- word_001.jpg
            |- word_002.jpg
            |- word_003.jpg
            | ...
```
WenmuZhou's avatar
WenmuZhou committed
86
87

<a name="Dataset_download"></a>
tink2123's avatar
tink2123 committed
88
### 1.2 Dataset download
WenmuZhou's avatar
WenmuZhou committed
89

tink2123's avatar
tink2123 committed
90
- ICDAR2015
WenmuZhou's avatar
WenmuZhou committed
91

tink2123's avatar
tink2123 committed
92
93
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
WenmuZhou's avatar
WenmuZhou committed
94

95
96
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.

WenmuZhou's avatar
WenmuZhou committed
97
98
99
100
101
102
103
104
105
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
```

tink2123's avatar
tink2123 committed
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
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)


WenmuZhou's avatar
WenmuZhou committed
126
<a name="Dictionary"></a>
tink2123's avatar
tink2123 committed
127
### 1.3 Dictionary
Khanh Tran's avatar
Khanh Tran committed
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143

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]

WenmuZhou's avatar
WenmuZhou committed
144
145
PaddleOCR has built-in dictionaries, which can be used on demand.

Khanh Tran's avatar
Khanh Tran committed
146
147
`ppocr/utils/ppocr_keys_v1.txt` is a Chinese dictionary with 6623 characters.

WenmuZhou's avatar
WenmuZhou committed
148
149
150
151
`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

152
`ppocr/utils/dict/japan_dict.txt` is a Japanese dictionary with 4399 characters
WenmuZhou's avatar
WenmuZhou committed
153

tink2123's avatar
tink2123 committed
154
`ppocr/utils/dict/korean_dict.txt` is a Korean dictionary with 3636 characters
WenmuZhou's avatar
WenmuZhou committed
155

tink2123's avatar
tink2123 committed
156
157
`ppocr/utils/dict/german_dict.txt` is a German dictionary with 131 characters

tink2123's avatar
tink2123 committed
158
`ppocr/utils/en_dict.txt` is a English dictionary with 96 characters
WenmuZhou's avatar
WenmuZhou committed
159

160

WenmuZhou's avatar
WenmuZhou committed
161
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 committed
162
If you like, you can submit the dictionary file to [dict](../../ppocr/utils/dict) and we will thank you in the Repo.
Khanh Tran's avatar
Khanh Tran committed
163
164
165
166


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`.

tink2123's avatar
tink2123 committed
167
168
169
170
- 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.

WenmuZhou's avatar
WenmuZhou committed
171
<a name="Add_space_category"></a>
tink2123's avatar
tink2123 committed
172
### 1.4 Add space category
tink2123's avatar
tink2123 committed
173

xmy0916's avatar
xmy0916 committed
174
If you want to support the recognition of the `space` category, please set the `use_space_char` field in the yml file to `True`.
tink2123's avatar
tink2123 committed
175
176
177

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

WenmuZhou's avatar
WenmuZhou committed
178
<a name="TRAINING"></a>
tink2123's avatar
tink2123 committed
179
## 2 TRAINING
Khanh Tran's avatar
Khanh Tran committed
180

tink2123's avatar
tink2123 committed
181
<a name="Data_Augmentation"></a>
tink2123's avatar
tink2123 committed
182
### 2.1 Data Augmentation
tink2123's avatar
tink2123 committed
183
184
185
186
187
188
189
190

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>
tink2123's avatar
tink2123 committed
191
### 2.2 General Training
tink2123's avatar
tink2123 committed
192

Khanh Tran's avatar
Khanh Tran committed
193
194
195
196
197
198
199
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
tink2123's avatar
tink2123 committed
200
wget -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_none_bilstm_ctc_v2.0_train.tar
Khanh Tran's avatar
Khanh Tran committed
201
202
# Decompress model parameters
cd pretrain_models
tink2123's avatar
tink2123 committed
203
tar -xf rec_mv3_none_bilstm_ctc_v2.0_train.tar && rm -rf rec_mv3_none_bilstm_ctc_v2.0_train.tar
Khanh Tran's avatar
Khanh Tran committed
204
205
206
207
208
```

Start training:

```
tink2123's avatar
tink2123 committed
209
# GPU training Support single card and multi-card training
tink2123's avatar
tink2123 committed
210
# Training icdar15 English data and The training log will be automatically saved as train.log under "{save_model_dir}"
tink2123's avatar
tink2123 committed
211
212
213
214

#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
xmy0916's avatar
xmy0916 committed
215
python3 -m paddle.distributed.launch --gpus '0,1,2,3'  tools/train.py -c configs/rec/rec_icdar15_train.yml
Khanh Tran's avatar
Khanh Tran committed
216
```
tink2123's avatar
tink2123 committed
217
218


Khanh Tran's avatar
Khanh Tran committed
219
220
221
222
223
224
225
226
227
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     |
| :--------: |  :-------:   | :-------:  |   :-------:   |   :-----:   |  :-----:   |
xmy0916's avatar
xmy0916 committed
228
229
| [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  |
Khanh Tran's avatar
Khanh Tran committed
230
| rec_chinese_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  |
WenmuZhou's avatar
WenmuZhou committed
231
| rec_chinese_common_train.yml |  CRNN |   ResNet34_vd |  None   |  BiLSTM |  ctc  |
Khanh Tran's avatar
Khanh Tran committed
232
233
234
235
236
| 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  |
LDOUBLEV's avatar
LDOUBLEV committed
237
238
| 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  |
tink2123's avatar
tink2123 committed
239
| rec_r50fpn_vd_none_srn.yml    | SRN | Resnet50_fpn_vd    | None    | rnn | srn |
Topdu's avatar
Topdu committed
240
| rec_mtb_nrtr.yml    | NRTR | nrtr_mtb    | None    | transformer encoder | transformer decoder |
andyjpaddle's avatar
andyjpaddle committed
241
| rec_r31_sar.yml               | SAR | ResNet31 | None | LSTM encoder | LSTM decoder |
Khanh Tran's avatar
Khanh Tran committed
242
243


WenmuZhou's avatar
WenmuZhou committed
244
For training Chinese data, it is recommended to use
xmy0916's avatar
xmy0916 committed
245
[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:
Khanh Tran's avatar
Khanh Tran committed
246
co
xmy0916's avatar
xmy0916 committed
247
Take `rec_chinese_lite_train_v2.0.yml` as an example:
Khanh Tran's avatar
Khanh Tran committed
248
249
250
```
Global:
  ...
xmy0916's avatar
xmy0916 committed
251
252
  # 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
Khanh Tran's avatar
Khanh Tran committed
253
254
255
  # Modify character type
  character_type: ch
  ...
256
  # Whether to recognize spaces
xmy0916's avatar
xmy0916 committed
257
  use_space_char: True
Khanh Tran's avatar
Khanh Tran committed
258

259
260
261
262

Optimizer:
  ...
  # Add learning rate decay strategy
xmy0916's avatar
xmy0916 committed
263
264
265
266
267
268
269
270
271
  lr:
    name: Cosine
    learning_rate: 0.001
  ...

...

Train:
  dataset:
MissPenguin's avatar
MissPenguin committed
272
    # Type of dataset,we support LMDBDataSet and SimpleDataSet
xmy0916's avatar
xmy0916 committed
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
    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:
MissPenguin's avatar
MissPenguin committed
292
    # Type of dataset,we support LMDBDataSet and SimpleDataSet
xmy0916's avatar
xmy0916 committed
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
    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
    ...
Khanh Tran's avatar
Khanh Tran committed
308
309
310
```
**Note that the configuration file for prediction/evaluation must be consistent with the training.**

WenmuZhou's avatar
WenmuZhou committed
311
<a name="Multi_language"></a>
tink2123's avatar
tink2123 committed
312
### 2.3 Multi-language Training
tink2123's avatar
tink2123 committed
313
314
315

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

tink2123's avatar
tink2123 committed
316
| Configuration file |  Algorithm name |   backbone |   trans   |   seq      |     pred     |  language | character_type |
tink2123's avatar
tink2123 committed
317
318
| :--------: |  :-------:   | :-------:  |   :-------:   |   :-----:   |  :-----:   | :-----:  | :-----:  |
| rec_chinese_cht_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | chinese traditional  | chinese_cht|
tink2123's avatar
tink2123 committed
319
| rec_en_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | English(Case sensitive)   | EN |
tink2123's avatar
tink2123 committed
320
321
322
323
| 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 |
tink2123's avatar
tink2123 committed
324
325
326
327
| 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 |
tink2123's avatar
tink2123 committed
328

tink2123's avatar
tink2123 committed
329
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)
WenmuZhou's avatar
WenmuZhou committed
330
331
332
333
334
335
336
337
338


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:
  ...
xmy0916's avatar
xmy0916 committed
339
  # Add a custom dictionary, such as modify the dictionary, please point the path to the new dictionary
WenmuZhou's avatar
WenmuZhou committed
340
341
  character_dict_path: ./ppocr/utils/dict/french_dict.txt
  ...
xmy0916's avatar
xmy0916 committed
342
  # Whether to recognize spaces
xmy0916's avatar
xmy0916 committed
343
  use_space_char: True
xmy0916's avatar
xmy0916 committed
344

WenmuZhou's avatar
WenmuZhou committed
345
...
xmy0916's avatar
xmy0916 committed
346
347
348

Train:
  dataset:
MissPenguin's avatar
MissPenguin committed
349
    # Type of dataset,we support LMDBDataSet and SimpleDataSet
xmy0916's avatar
xmy0916 committed
350
351
352
353
354
355
356
357
358
    name: SimpleDataSet
    # Path of dataset
    data_dir: ./train_data/
    # Path of train list
    label_file_list: ["./train_data/french_train.txt"]
    ...

Eval:
  dataset:
MissPenguin's avatar
MissPenguin committed
359
    # Type of dataset,we support LMDBDataSet and SimpleDataSet
xmy0916's avatar
xmy0916 committed
360
361
362
363
364
365
    name: SimpleDataSet
    # Path of dataset
    data_dir: ./train_data
    # Path of eval list
    label_file_list: ["./train_data/french_val.txt"]
    ...
WenmuZhou's avatar
WenmuZhou committed
366
```
Khanh Tran's avatar
Khanh Tran committed
367

WenmuZhou's avatar
WenmuZhou committed
368
<a name="EVALUATION"></a>
369

tink2123's avatar
tink2123 committed
370
## 3 EVALUATION
Khanh Tran's avatar
Khanh Tran committed
371

WenmuZhou's avatar
WenmuZhou committed
372
The evaluation dataset can be set by modifying the `Eval.dataset.label_file_list` field in the `configs/rec/rec_icdar15_train.yml` file.
Khanh Tran's avatar
Khanh Tran committed
373
374
375

```
# GPU evaluation, Global.checkpoints is the weight to be tested
WenmuZhou's avatar
WenmuZhou committed
376
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
Khanh Tran's avatar
Khanh Tran committed
377
378
```

WenmuZhou's avatar
WenmuZhou committed
379
<a name="PREDICTION"></a>
tink2123's avatar
tink2123 committed
380
## 4 PREDICTION
Khanh Tran's avatar
Khanh Tran committed
381
382
383
384


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

tink2123's avatar
tink2123 committed
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
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.
Khanh Tran's avatar
Khanh Tran committed
406
407
408

```
# Predict English results
WenmuZhou's avatar
WenmuZhou committed
409
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
Khanh Tran's avatar
Khanh Tran committed
410
411
```

tink2123's avatar
tink2123 committed
412

Khanh Tran's avatar
Khanh Tran committed
413
414
Input image:

415
![](../imgs_words/en/word_1.png)
Khanh Tran's avatar
Khanh Tran committed
416
417
418
419
420

Get the prediction result of the input image:

```
infer_img: doc/imgs_words/en/word_1.png
tink2123's avatar
tink2123 committed
421
        result: ('joint', 0.9998967)
Khanh Tran's avatar
Khanh Tran committed
422
423
```

xmy0916's avatar
xmy0916 committed
424
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:
Khanh Tran's avatar
Khanh Tran committed
425
426
427

```
# Predict Chinese results
WenmuZhou's avatar
WenmuZhou committed
428
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
Khanh Tran's avatar
Khanh Tran committed
429
430
431
432
```

Input image:

433
![](../imgs_words/ch/word_1.jpg)
Khanh Tran's avatar
Khanh Tran committed
434
435
436
437
438

Get the prediction result of the input image:

```
infer_img: doc/imgs_words/ch/word_1.jpg
tink2123's avatar
tink2123 committed
439
        result: ('韩国小馆', 0.997218)
Khanh Tran's avatar
Khanh Tran committed
440
```
441
442
443
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
477

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

## 5 CONVERT TO INFERENCE MODEL

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"
  ```