Scripts for training Layout Detection Models using Detectron2

Usage

Directory Structure

• In tools/, we provide a series of handy scripts for converting data formats and training the models.
• In scripts/, it lists specific command for running the code for processing the given dataset.
• The configs/ contains the configuration for different deep learning models, and is organized by datasets.

How to train the models?

• Get the dataset and annotations -- if you are not sure, feel free to check this tutorial.
• Duplicate and modify the config files and training scripts
  • For example, you might want to copy configs/prima/fast_rcnn_R_50_FPN_3x to configs/your-dataset-name/fast_rcnn_R_50_FPN_3x, and you can create your own scripts/train_<your-dataset-name>.sh based on scripts/train_prima.sh.
  • You'll modify the --dataset_name, --json_annotation_train, --image_path_train, --json_annotation_val, --image_path_val, and --config-file args appropriately.
• If you have a dataset with segmentation masks, you can try to train with the mask_rcnn model; otherwise you might want to start with the fast_rcnn model
  • If you see error AttributeError: Cannot find field 'gt_masks' in the given Instances! during training, this means you should not use

Supported Datasets

• Prima Layout Analysis Dataset scripts/train_prima.sh
  • You will need to download the dataset from the official website and put it in the data/prima folder.
  • As the original dataset is stored in the PAGE format, the script will use tools/convert_prima_to_coco.py to convert it to COCO format.
  • The final dataset folder structure should look like:

    data/
    └── prima/
        ├── Images/
        ├── XML/
        ├── License.txt
        └── annotations*.json