def run(self,
n_train: int,
val_amount: float,
cross_folds: int,
single_folds: List[int],
train_books: List[str],
test_books: List[str],
train_books_extend: List[str]
):
from omr.steps.step import Step
global_args = self.global_args
logger.info("Finding PcGts files with valid ground truth")
train_args = generate_dataset(
lock_states=[LockState(Locks.STAFF_LINES, True), LockState(Locks.LAYOUT, True)],
n_train=n_train,
val_amount=val_amount,
cross_folds=cross_folds,
single_folds=single_folds,
train_books=train_books,
test_books=test_books,
train_books_extend=train_books_extend,
)
train_args = [SingleDataArgs(gd.fold,
os.path.join(global_args.model_dir, '{}_{}'.format(global_args.algorithm_type.value, gd.fold)),
gd.train_pcgts_files, gd.validation_pcgts_files,
gd.test_pcgts_files,
global_args) for gd in train_args]
experimenter_class = Step.meta(self.global_args.algorithm_type).experimenter()
results = [experimenter_class(args, logger).run_single() for args in train_args]
experimenter_class.print_results(self.global_args, results, logger)
def put(self, request, group, style):
meta = ModelMeta.from_json(request.body)
default_type = AlgorithmGroups(group).types()[0]
model = Model.from_id_str(meta.id)
target_meta = MetaId(
DatabaseAvailableModels.local_default_models(style, default_type),
Step.meta(default_type).model_dir())
target_model = Model(target_meta)
model.copy_to(target_model, override=True)
return Response()
def __init__(self, settings: AlgorithmPredictorSettings):
super().__init__(settings)
meta = Step.meta(AlgorithmTypes.OCR_CALAMARI)
from ommr4all.settings import BASE_DIR
model = Model(
MetaId.from_custom_path(
BASE_DIR +
'/internal_storage/default_models/fraktur/text_calamari/',
meta.type()))
settings = AlgorithmPredictorSettings(model=model, )
settings.params.ctcDecoder.params.type = CTCDecoderParams.CTC_DEFAULT
self.ocr_predictor = meta.create_predictor(settings)
def __init__(self, settings: AlgorithmPredictorSettings):
super().__init__(settings)
self.document_id = settings.params.documentId
self.document_text = settings.params.documentText
self.document_similar_tester = SimilarDocumentChecker()
self.text_normalizer = LyricsNormalizationProcessor(
LyricsNormalizationParams(LyricsNormalization.WORDS))
meta = Step.meta(AlgorithmTypes.OCR_CALAMARI)
from ommr4all.settings import BASE_DIR
model = Model(
MetaId.from_custom_path(
BASE_DIR +
'/internal_storage/default_models/fraktur/text_calamari/',
meta.type()))
settings = AlgorithmPredictorSettings(model=model, )
settings.params.ctcDecoder.params.type = CTCDecoderParams.CTC_DEFAULT
self.ocr_predictor = meta.create_predictor(settings)
from omr.dataset.datafiles import dataset_by_locked_pages, LockState
random.seed(1)
np.random.seed(1)
if False:
train_pcgts, val_pcgts = dataset_by_locked_pages(
0.8,
[LockState(Locks.SYMBOLS, True),
LockState(Locks.LAYOUT, True)],
True,
[
# DatabaseBook('Graduel_Part_1'),
# DatabaseBook('Graduel_Part_2'),
# DatabaseBook('Graduel_Part_3'),
])
book = DatabaseBook('Gothic_Test')
meta = Step.meta(AlgorithmTypes.OCR_CALAMARI)
# model = meta.newest_model_for_book(book)
model = Model(
MetaId.from_custom_path(
BASE_DIR +
'/internal_storage/pretrained_models/text_calamari/fraktur_historical',
meta.type()))
settings = AlgorithmPredictorSettings(model=model, )
pred = meta.create_predictor(settings)
ps: List[PredictionResult] = list(pred.predict(book.pages()[0:1]))
for i, p in enumerate(ps):
canvas = PcGtsCanvas(p.pcgts.page,
p.text_lines[0].line.operation.scale_reference)
for j, s in enumerate(p.text_lines):
canvas.draw(s)
from shared.pcgtscanvas import PcGtsCanvas
from omr.dataset.datafiles import dataset_by_locked_pages, LockState
random.seed(1)
np.random.seed(1)
if False:
train_pcgts, val_pcgts = dataset_by_locked_pages(
0.8,
[LockState(Locks.SYMBOLS, True),
LockState(Locks.LAYOUT, True)],
True,
[
# DatabaseBook('Graduel_Part_1'),
# DatabaseBook('Graduel_Part_2'),
# DatabaseBook('Graduel_Part_3'),
])
book = DatabaseBook('Paper_New_York')
meta = Step.meta(AlgorithmTypes.SYLLABLES_FROM_TEXT)
model = meta.best_model_for_book(book)
settings = AlgorithmPredictorSettings(model=model, )
pred = meta.create_predictor(settings)
ps: List[PredictionResult] = list(pred.predict(book.pages()[:1]))
for i, p in enumerate(ps):
pmr = p.page_match_result
canvas = PcGtsCanvas(pmr.pcgts.page, PageScaleReference.NORMALIZED_X2)
canvas.draw(pmr.text_prediction_result.text_lines[4],
color=(25, 150, 25),
background=True)
# canvas.draw(pmr.match_results)
# canvas.draw(p.annotations)
canvas.show()
os.environ['DJANGO_SETTINGS_MODULE'] = 'ommr4all.settings'
django.setup()
from ommr4all.settings import BASE_DIR
import random
import matplotlib.pyplot as plt
from shared.pcgtscanvas import PcGtsCanvas
from omr.dataset.datafiles import dataset_by_locked_pages, LockState
from database.file_formats.pcgts import PageScaleReference
random.seed(1)
np.random.seed(1)
if False:
train_pcgts, val_pcgts = dataset_by_locked_pages(0.8, [LockState(Locks.SYMBOLS, True), LockState(Locks.LAYOUT, True)], True, [
# DatabaseBook('Graduel_Part_1'),
# DatabaseBook('Graduel_Part_2'),
# DatabaseBook('Graduel_Part_3'),
])
book = DatabaseBook('Paper_New_York')
meta = Step.meta(AlgorithmTypes.SYLLABLES_IN_ORDER)
model = meta.best_model_for_book(book)
settings = AlgorithmPredictorSettings(
model=model,
)
pred = meta.create_predictor(settings)
ps: List[PredictionResult] = list(pred.predict(book.pages()[:1]))
for i, p in enumerate(ps):
pmr = p.page_match_result
canvas = PcGtsCanvas(pmr.pcgts.page, PageScaleReference.NORMALIZED_X2)
canvas.draw(pmr.match_results)
canvas.draw(p.annotations)
canvas.show()
def get(self, request, group, style):
default_type = AlgorithmGroups(group).types()[0]
return Response(
Step.meta(default_type).list_available_models_for_style(
style).to_dict())