@@ -65,6 +65,7 @@ Supported text recognition algorithms (Click the link to get the tutorial):
-[x] [SAR](./algorithm_rec_sar_en.md)
-[x] [SEED](./algorithm_rec_seed_en.md)
-[x] [SVTR](./algorithm_rec_svtr_en.md)
-[x] [ViTSTR](./algorithm_rec_vitstr_en.md)
Refer to [DTRB](https://arxiv.org/abs/1904.01906), the training and evaluation result of these above text recognition (using MJSynth and SynthText for training, evaluate on IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE) is as follow:
...
...
@@ -83,7 +84,7 @@ Refer to [DTRB](https://arxiv.org/abs/1904.01906), the training and evaluation r
-[3. Model Training / Evaluation / Prediction](#3)
-[3.1 Training](#3-1)
-[3.2 Evaluation](#3-2)
-[3.3 Prediction](#3-3)
-[4. Inference and Deployment](#4)
-[4.1 Python Inference](#4-1)
-[4.2 C++ Inference](#4-2)
-[4.3 Serving](#4-3)
-[4.4 More](#4-4)
-[5. FAQ](#5)
<aname="1"></a>
## 1. Introduction
Paper:
> [Vision Transformer for Fast and Efficient Scene Text Recognition](https://arxiv.org/abs/2105.08582)
> Rowel Atienza
> 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"](./environment_en.md) to configure the PaddleOCR environment, and refer to ["Project Clone"](./clone_en.md) to clone the project code.
<aname="3"></a>
## 3. Model Training / Evaluation / Prediction
Please refer to [Text Recognition Tutorial](./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:
```
#Single GPU training (long training period, not recommended)
First, the model saved during the ViTSTR text recognition training process is converted into an inference model. ( [Model download link](https://paddleocr.bj.bcebos.com/rec_vitstr_none_none_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 ViTSTR in the `tools/export_model.py` file.
After the conversion is successful, there are three files in the directory:
```
/inference/rec_vitstr/
├── inference.pdiparams
├── inference.pdiparams.info
└── inference.pdmodel
```
For ViTSTR 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:
The result is as follows:
```shell
Predicts of ./doc/imgs_words_en/word_10.png:('pain', 0.9265879392623901)
```
<aname="4-2"></a>
### 4.2 C++ Inference
Not supported
<aname="4-3"></a>
### 4.3 Serving
Not supported
<aname="4-4"></a>
### 4.4 More
Not supported
<aname="5"></a>
## 5. FAQ
1. In the `ViTSTR` paper, using pre-trained weights on ImageNet1k for initial training, we did not use pre-trained weights in training, and the final accuracy did not change or even improved.
## Citation
```bibtex
@article{Atienza2021ViTSTR,
title={Vision Transformer for Fast and Efficient Scene Text Recognition},
