def _predict(
self,
pcgts_files: List[PcGts],
callback: Optional[PredictionCallback] = None
) -> Generator[SingleLinePredictionResult, None, None]:
dataset = SymbolDetectionDataset(pcgts_files, self.dataset_params)
for p in self.predictor.predict(
dataset.to_page_segmentation_dataset()):
m: RegionLineMaskData = p.data.user_data
symbols = SingleLinePredictionResult(
self.exract_symbols(p.probabilities, p.labels, m, dataset),
p.data.user_data)
if False:
from shared.pcgtscanvas import PcGtsCanvas
canvas = PcGtsCanvas(m.operation.page,
PageScaleReference.NORMALIZED_X2)
for s in symbols.symbols:
s.coord = m.operation.music_line.staff_lines.compute_coord_by_position_in_staff(
s.coord.x, s.position_in_staff)
canvas.draw(symbols.symbols, invert=True)
canvas.show()
if False:
import matplotlib.pyplot as plt
f, ax = plt.subplots(5, 1, sharey='all', sharex='all')
ax[0].imshow(p.probabilities[:, :, 0], vmin=0.0, vmax=1.0)
ax[1].imshow(p.data.image, vmin=0.0, vmax=255)
ax[2].imshow(render_prediction_labels(p.labels, p.data.image))
ax[3].imshow(
(p.probabilities[:, :, 0] <= 0.8) *
(1 + np.argmax(p.probabilities[:, :, 1:], axis=-1)))
ax[4].imshow(
render_prediction_labels(p.data.mask, p.data.image))
plt.show()
yield symbols
def predict(self, pages: List[DatabasePage], callback: Optional[PredictionCallback] = None) -> AlgorithmPredictionResultGenerator:
pcgts_files = [p.pcgts() for p in pages]
page_results = [PredictionResult(pcgts, pcgts.page.location, [], []) for pcgts in pcgts_files]
for line_results in self._predict(pcgts_files, callback):
if isinstance(line_results, SingleLinePredictionResult):
page_result = [p for p in page_results if p.pcgts == line_results.line.operation.pcgts][0]
page_result.music_lines.append(line_results)
else:
if len(line_results) == 2:
line_results_symbols = line_results[0]
page_result = [p for p in page_results if p.pcgts == line_results_symbols.line.operation.pcgts][0]
page_result.music_lines.append(line_results_symbols)
line_results_symbols = line_results[1]
page_result = [p for p in page_results if p.pcgts == line_results_symbols.line.operation.pcgts][0]
page_result.debug_music_lines.append(line_results_symbols)
for page_result in page_results:
if False:
from .evaluator import SymbolDetectionEvaluator, Codec
evaluator = SymbolDetectionEvaluator()
canvas = PcGtsCanvas(page_result.music_lines[0].line.operation.page, PageScaleReference.NORMALIZED_X2)
for i, ml in enumerate(page_result.music_lines):
canvas.draw(ml.line.operation.music_line.staff_lines)
for s in ml.symbols:
canvas.draw_music_symbol_position_in_line(ml.line.operation.music_line.staff_lines, s, color=(255, 255, 0), thickness=2)
for s in ml.line.operation.music_line.symbols:
canvas.draw_music_symbol_position_in_line(ml.line.operation.music_line.staff_lines, s, color=(0,0, 255))
c = Codec()
gt = c.symbols_to_label_sequence(ml.line.operation.music_line.symbols, False)
pred = c.symbols_to_label_sequence(ml.symbols, False)
r = c.compute_sequence_diffs(gt, pred)
print(i + 1, r)
print(i + 1, evaluator.evaluate([ml.line.operation.music_line.symbols], [ml.symbols])[-3])
canvas.show()
yield page_result
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)
canvas.show()