61 lines
2.4 KiB
Python
61 lines
2.4 KiB
Python
from typing import Iterable
|
|
|
|
from funcy import juxt
|
|
|
|
from image_prediction.classifier.classifier import Classifier
|
|
from image_prediction.classifier.image_classifier import ImageClassifier
|
|
from image_prediction.compositor.compositor import TransformerCompositor
|
|
from image_prediction.encoder.encoders.hash_encoder import HashEncoder
|
|
from image_prediction.estimator.adapter.adapter import EstimatorAdapter
|
|
from image_prediction.formatter.formatter import format_image_plus
|
|
from image_prediction.formatter.formatters.camel_case import Snake2CamelCaseKeyFormatter
|
|
from image_prediction.formatter.formatters.enum import EnumFormatter
|
|
from image_prediction.image_extractor.extractors.parsable import ParsablePDFImageExtractor
|
|
from image_prediction.label_mapper.mappers.probability import ProbabilityMapper
|
|
from image_prediction.model_loader.loader import ModelLoader
|
|
from image_prediction.model_loader.loaders.mlflow import MlflowConnector
|
|
from image_prediction.redai_adapter.mlflow import MlflowModelReader
|
|
from image_prediction.transformer.transformers.coordinate.pdfnet import PDFNetCoordinateTransformer
|
|
from image_prediction.transformer.transformers.response import ResponseTransformer
|
|
from pdf2img.extraction import extract_images_via_metadata
|
|
|
|
|
|
def get_mlflow_model_loader(mlruns_dir):
|
|
model_loader = ModelLoader(MlflowConnector(MlflowModelReader(mlruns_dir)))
|
|
return model_loader
|
|
|
|
|
|
def get_image_classifier(model_loader, model_identifier):
|
|
model, classes = juxt(model_loader.load_model, model_loader.load_classes)(model_identifier)
|
|
return ImageClassifier(Classifier(EstimatorAdapter(model), ProbabilityMapper(classes)))
|
|
|
|
|
|
# def get_extractor(**kwargs):
|
|
# image_extractor = ParsablePDFImageExtractor(**kwargs)
|
|
#
|
|
# return image_extractor
|
|
|
|
|
|
def get_dispatched_extract(**kwargs):
|
|
image_extractor = ParsablePDFImageExtractor(**kwargs)
|
|
|
|
def extract(pdf: bytes, page_range: range = None, metadata_per_image: Iterable[dict] = None):
|
|
if metadata_per_image:
|
|
image_pluses = extract_images_via_metadata(pdf, metadata_per_image)
|
|
yield from map(format_image_plus, image_pluses)
|
|
else:
|
|
yield from image_extractor.extract(pdf, page_range)
|
|
|
|
return extract
|
|
|
|
|
|
def get_formatter():
|
|
formatter = TransformerCompositor(
|
|
PDFNetCoordinateTransformer(), EnumFormatter(), ResponseTransformer(), Snake2CamelCaseKeyFormatter()
|
|
)
|
|
return formatter
|
|
|
|
|
|
def get_encoder():
|
|
return HashEncoder()
|