def test_model_zoo(self):
version = '1.0'
url = f"https://github.com/Calamari-OCR/calamari_models/archive/{version}.tar.gz"
with tempfile.TemporaryDirectory() as d:
d = 'model_archive_permanent' # for debugging
os.makedirs(d, exist_ok=True)
os.chdir(d)
if not os.path.exists('calamari_models'):
check_call([
'sh', '-c', ' '.join([
'wget', '-q', '-O', '-', url, '|', 'tar', 'xz', '&&',
'mv', f'calamari_models-{version}', 'calamari_models'
])
])
trainer_params = uw3_trainer_params(with_validation=True)
args = PredictAndEvalArgs(
checkpoint=glob(
os.path.join('calamari_models', 'antiqua_modern',
'*.ckpt.json')),
predictor=PredictorParams(pipeline=DataPipelineParams(
batch_size=5)),
data=trainer_params.gen.val_gen(),
)
full_evaluation = predict_and_eval_main(args)
self.assertLess(
full_evaluation['voted']['eval']['avg_ler'], 0.001,
"The accuracy on the test data must be below 0.1%")
def test_predict_and_eval_uw3_with_voting(self):
from calamari_ocr.test.test_train_file import uw3_trainer_params
checkpoint = os.path.join(this_dir, "models", "best.ckpt")
trainer_params = uw3_trainer_params(with_validation=True)
args = PredictAndEvalArgs(
checkpoint=[checkpoint, checkpoint, checkpoint],
predictor=PredictorParams(pipeline=DataPipelineParams(
batch_size=5)),
data=trainer_params.gen.val_gen(),
)
main(args)
def test_predict_and_eval_hdf5(self):
from calamari_ocr.test.test_train_hdf5 import default_trainer_params
checkpoint = os.path.join(this_dir, "models", "best.ckpt")
trainer_params = default_trainer_params(with_validation=True)
args = PredictAndEvalArgs(
checkpoint=[checkpoint],
predictor=PredictorParams(pipeline=DataPipelineParams(
num_processes=1)),
data=trainer_params.gen.val_gen(),
)
main(args)
def test_model_zoo(self):
version = "1.0"
url = f"https://github.com/Calamari-OCR/calamari_models/archive/{version}.tar.gz"
with tempfile.TemporaryDirectory() as d:
d = "model_archive_permanent" # for debugging
os.makedirs(d, exist_ok=True)
os.chdir(d)
if not os.path.exists("calamari_models"):
check_call(
[
"sh",
"-c",
" ".join(
[
"wget",
"-q",
"-O",
"-",
url,
"|",
"tar",
"xz",
"&&",
"mv",
f"calamari_models-{version}",
"calamari_models",
]
),
]
)
trainer_params = uw3_trainer_params(with_validation=True)
args = PredictAndEvalArgs(
checkpoint=glob(os.path.join("calamari_models", "antiqua_modern", "*.ckpt.json")),
predictor=PredictorParams(pipeline=DataPipelineParams(batch_size=5)),
data=trainer_params.gen.val_gen(),
)
full_evaluation = predict_and_eval_main(args)
self.assertLess(
full_evaluation["voted"]["eval"]["avg_ler"],
0.001,
"The accuracy on the test data must be below 0.1%",
)