> [Reciprocal Feature Learning via Explicit and Implicit Tasks in Scene Text Recognition](https://arxiv.org/abs/2105.06229.pdf)
> Hui Jiang, Yunlu Xu, Zhanzhan Cheng, Shiliang Pu, Yi Niu, Wenqi Ren, Fei Wu, and Wenming Tan
> ICDAR, 2021
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
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"
#step1:train the CNT branch
# Single GPU training (long training period, not recommended)
First, the model saved during the RFL text recognition training process is converted into an inference model. ( [Model download link](https://paddleocr.bj.bcebos.com/contribution/rec_resnet_rfl.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_resnet_rfl_att/
├── inference.pdiparams
├── inference.pdiparams.info
└── inference.pdmodel
```
For RFL text recognition model inference, the following commands can be executed:
