(*) Since the official homepage is unavailable now, we provide an alternative for quick reference. However, we do not guarantee the correctness of the dataset.
## Preparation Steps
### ICDAR 2013
- Step1: Download `Challenge2_Test_Task3_Images.zip` and `Challenge2_Training_Task3_Images_GT.zip` from [homepage](https://rrc.cvc.uab.es/?ch=2&com=downloads)
- Step2: Download [test_label_1015.txt](https://download.openmmlab.com/mmocr/data/mixture/icdar_2013/test_label_1015.txt) and [train_label.txt](https://download.openmmlab.com/mmocr/data/mixture/icdar_2013/train_label.txt)
- Step1: Download `mjsynth.tar.gz` from [homepage](https://www.robots.ox.ac.uk/~vgg/data/text/)
- Step2: Download [label.txt](https://download.openmmlab.com/mmocr/data/mixture/Syn90k/label.txt) (8,919,273 annotations) and [shuffle_labels.txt](https://download.openmmlab.com/mmocr/data/mixture/Syn90k/shuffle_labels.txt) (2,400,000 randomly sampled annotations). **Please make sure you're using the right annotation to train the model by checking its dataset specs in Model Zoo.**
- Step3:
```bash
mkdir Syn90k && cd Syn90k
mv /path/to/mjsynth.tar.gz .
tar -xzf mjsynth.tar.gz
mv /path/to/shuffle_labels.txt .
mv /path/to/label.txt .
# create soft link
cd /path/to/mmocr/data/mixture
ln -s /path/to/Syn90k Syn90k
```
### SynthText (Synth800k)
- Step1: Download `SynthText.zip` from [homepage](https://www.robots.ox.ac.uk/~vgg/data/scenetext/)
- Step2: Download [label.txt](https://download.openmmlab.com/mmocr/data/mixture/SynthText/label.txt) (7,266,686 annotations) and [shuffle_labels.txt](https://download.openmmlab.com/mmocr/data/mixture/SynthText/shuffle_labels.txt) (2,400,000 randomly sampled annotations). **Please make sure you're using the right annotation to train the model by checking its dataset specs in Model Zoo.**
- Step1: Download [train_val_images.zip](https://dl.fbaipublicfiles.com/textvqa/images/train_val_images.zip), [TextOCR_0.1_train.json](https://dl.fbaipublicfiles.com/textvqa/data/textocr/TextOCR_0.1_train.json) and [TextOCR_0.1_val.json](https://dl.fbaipublicfiles.com/textvqa/data/textocr/TextOCR_0.1_val.json) to `textocr/`.
- Step1: Download `totaltext.zip` from [github dataset](https://github.com/cs-chan/Total-Text-Dataset/tree/master/Dataset) and `groundtruth_text.zip` from [github Groundtruth](https://github.com/cs-chan/Total-Text-Dataset/tree/master/Groundtruth/Text) (Our totaltext_converter.py supports groundtruth with both .mat and .txt format).
```bash
mkdir totaltext && cd totaltext
mkdir imgs && mkdir annotations
# For images
# in ./totaltext
unzip totaltext.zip
mv Images/Train imgs/training
mv Images/Test imgs/test
# For annotations
unzip groundtruth_text.zip
cd Groundtruth
mv Polygon/Train ../annotations/training
mv Polygon/Test ../annotations/test
```
- Step2: Generate cropped images, `train_label.txt` and `test_label.txt` with the following command (the cropped images will be saved to `data/totaltext/dst_imgs/`):
```bash
python tools/data/textrecog/totaltext_converter.py /path/to/totaltext -o /path/to/totaltext --split-list training test
