8b5a8bedaeb5e8bc35878d7ae39430a5c285c9ec,calamari_ocr/ocr/datasets/abbyy_dataset/dataset.py,AbbyyDataSet,_load_sample,#AbbyyDataSet#Any#Any#,68

Before Change

            ly, lx = img.shape

            // Cut the Image
            img = img[line.rect.top: -ly + line.rect.bottom, line.rect.left: -lx + line.rect.right]

            // add padding as required from normal files
            img = np.pad(img, ((3, 3), (0, 0)), mode="constant", constant_values=img.max())

            Binarize Image
            if self.binary:
                img = img > 0.9

        return img, text

    def store_text(self, sentence, sample, output_dir, extension):

After Change

            if self.binary:
                img = img > 0.9
        else:
            img = None

        for p, page in enumerate(book.pages):
            for l, line in enumerate(page.getLines()):
                for f, fo in enumerate(line.formats):
                    text = None
                    cut_img = None
                    if self.mode == DataSetMode.EVAL or self.mode == DataSetMode.TRAIN:
                        text = fo.text

                    if text_only:
                        yield cut_img, text

                    else:
                        if self.mode == DataSetMode.TRAIN or self.mode == DataSetMode.PREDICT:
                            ly, lx = img.shape

Instances