README.md

BlendMask instance detection

coco/
  thing_train2017/
    # thing class label maps for auxiliary semantic loss
lvis/
  thing_train/
    # semantic labels for LVIS

Run python prepare_thing_sem_from_instance.py, to extract semantic labels from instance annotations.

Run python prepare_thing_sem_from_lvis.py, to extract semantic labels from LVIS annotations.

Text Spotting

English pretrained data:

• Totaltext [paper] [source].

  • Download (0.4G) (Origin, Google, BaiduNetDisk password: kgy7)

• CTW1500 [paper] [source].

  • Download (0.8G) (Origin, Google, BaiduNetDisk password: 7kvx)

• MLT [paper].

  • Download (6.8G) (Origin, Google, BaiduNetDisk password: zqrm)

• CurvedSynText150k [paper]:

  • Part1 (94,723) Download (15.8G) (Origin, Google, BaiduNetDisk password: 4k3x)
  • Part2 (54,327) Download (9.7G) (Origin, Google, BaiduNetDisk password: a5f5)

Chinese pretrained data:

• ReCTs [Source]
  • Download (1.7G) (Google, BaiduNetDisk password: wo3o)
• ReCTs test set [Source]
  • Download (0.5G) (Google, BaiduNetDisk password: l1zy)
• LSVT [Source]
  • Download (8.2G) (Google, BaiduNetDisk password: qv7k)
• ArT [Source]
  • Download (1.5G) (Google, BaiduNetDisk password: ozht)
• SynChinese130k [Source]
  • Download (25G) (Google, BaiduNetDisk password: zc3q)

text/
  totaltext/
    annotations/
    train_images/
    test_images/
  mlt2017/
    annotations/train.json
    images/
    ...
  syntext1/
  syntext2/
  ...
  evaluation/
    gt_ctw1500.zip
    gt_totaltext.zip

To evaluate on Total Text and CTW1500, first download the zipped annotations with

mkdir evaluation
cd evaluation
wget -O gt_ctw1500.zip https://cloudstor.aarnet.edu.au/plus/s/xU3yeM3GnidiSTr/download
wget -O gt_totaltext.zip https://cloudstor.aarnet.edu.au/plus/s/SFHvin8BLUM4cNd/download

Person In Context instance detection

pic/
  thing_train/
    # thing class label maps for auxiliary semantic loss
  annotations/
    train_person.json
    val_person.json
  image/
    train/
    ...
  

First link the PIC_2.0 dataset to this folder with ln -s \path\to\PIC_2.0 pic. Then use the python gen_coco_person.py to generate train and validation annotation jsons.

Run python prepare_thing_sem_from_instance.py --dataset-name pic, to extract semantic labels from instance annotations.