- Set up the pipenv environment via the following command
$ pipenv install --skip-lock --dev
└── iam_online
├── ascii
├── gen_iam_256 ( <- we'll generate this later)
├── lineImages
├── lineStrokes
├── org_unp ( <- we'll generate this later)
└── original
-
- First, convert the structured xml file into a more readable unp file
$ pipenv run iam_cvt_xml2unp
-
- Next, for the PoC of the TraTra model,
extracting the single stroke data and generating images.
$ pipenv run iam_gen_single_stroke
-
- Resampling is used because the method of taking points does not seem always suitable for deep learning.
$ pipenv run iam_resampling
$ pipenv run iam_train --gpu_id 0
- Download pre-trained PoC TraTra model from
gdrive link
and save it wherever you want.
- Change
load_model config from null to your path in config/exp001.yaml.
- Run script (change
test_data_path config from null to directory path that contains test images in config/exp001.yaml)
$ pipenv run iam_test --gpu_id 0
