> [NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition](https://arxiv.org/abs/1806.00926)
> Fenfen Sheng and Zhineng Chen and Bo Xu
> ICDAR, 2019
Using MJSynth and SynthText two text recognition datasets for training, and evaluating on IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE datasets, the algorithm reproduction effect is as follows:
Please refer to ["Environment Preparation"](../../ppocr/environment.en.md) to configure the PaddleOCR environment, and refer to ["Project Clone"](../../ppocr/blog/clone.en.md)to clone the project code.
## 3. Model Training / Evaluation / Prediction
Please refer to [Text Recognition Tutorial](../../ppocr/model_train/recognition.en.md). PaddleOCR modularizes the code, and training different recognition models only requires **changing the configuration file**.
### Training
Specifically, after the data preparation is completed, the training can be started. The training command is as follows:
```bash linenums="1"
# Single GPU training (long training period, not recommended)
First, the model saved during the NRTR text recognition training process is converted into an inference model. ( [Model download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mtb_nrtr_train.tar)) ), you can use the following command to convert:
- If you are training the model on your own dataset and have modified the dictionary file, please pay attention to modify the `character_dict_path` in the configuration file to the modified dictionary file.
- If you modified the input size during training, please modify the `infer_shape` corresponding to NRTR in the `tools/export_model.py` file.
After the conversion is successful, there are three files in the directory:
```text linenums="1"
/inference/rec_mtb_nrtr/
├── inference.pdiparams
├── inference.pdiparams.info
└── inference.pdmodel
```
For NRTR text recognition model inference, the following commands can be executed:
After executing the command, the prediction result (recognized text and score) of the image above is printed to the screen, an example is as follows:
```bash linenums="1"
Predicts of ./doc/imgs_words_en/word_10.png:('pain', 0.9465042352676392)
```
### 4.2 C++ Inference
Not supported
### 4.3 Serving
Not supported
### 4.4 More
Not supported
## 5. FAQ
1. In the `NRTR` paper, Beam search is used to decode characters, but the speed is slow. Beam search is not used by default here, and greedy search is used to decode characters.
## 6. Release Note
1. The release/2.6 version updates the NRTR code structure. The new version of NRTR can load the model parameters of the old version (release/2.5 and before), and you may use the following code to convert the old version model parameters to the new version model parameters:
<details>
<summary>Click to expand</summary>
```python linenums="1"
params = paddle.load('path/' + '.pdparams') # the old version parameters
state_dict = model.state_dict() # the new version model parameters
new_state_dict = {}
for k1, v1 in state_dict.items():
k = k1
if 'encoder' in k and 'self_attn' in k and 'qkv' in k and 'weight' in k:
