diff options
Diffstat (limited to 'text_recognizer/data')
-rw-r--r-- | text_recognizer/data/emnist.py | 2 | ||||
-rw-r--r-- | text_recognizer/data/emnist_lines.py | 2 | ||||
-rw-r--r-- | text_recognizer/data/iam.py | 8 | ||||
-rw-r--r-- | text_recognizer/data/iam_extended_paragraphs.py | 4 | ||||
-rw-r--r-- | text_recognizer/data/iam_lines.py | 2 | ||||
-rw-r--r-- | text_recognizer/data/iam_paragraphs.py | 4 | ||||
-rw-r--r-- | text_recognizer/data/iam_synthetic_paragraphs.py | 14 | ||||
-rw-r--r-- | text_recognizer/data/transforms/image.py | 4 | ||||
-rw-r--r-- | text_recognizer/data/transforms/line.py | 2 | ||||
-rw-r--r-- | text_recognizer/data/transforms/paragraph.py | 1 | ||||
-rw-r--r-- | text_recognizer/data/utils/sentence_generator.py | 2 |
11 files changed, 22 insertions, 23 deletions
diff --git a/text_recognizer/data/emnist.py b/text_recognizer/data/emnist.py index b5db075..4a14521 100644 --- a/text_recognizer/data/emnist.py +++ b/text_recognizer/data/emnist.py @@ -11,10 +11,10 @@ import numpy as np import toml from loguru import logger as log +import text_recognizer.metadata.emnist as metadata from text_recognizer.data.base_data_module import BaseDataModule, load_and_print_info from text_recognizer.data.base_dataset import BaseDataset, split_dataset from text_recognizer.data.utils.download_utils import download_dataset -import text_recognizer.metadata.emnist as metadata class EMNIST(BaseDataModule): diff --git a/text_recognizer/data/emnist_lines.py b/text_recognizer/data/emnist_lines.py index 4ae4787..aaec93f 100644 --- a/text_recognizer/data/emnist_lines.py +++ b/text_recognizer/data/emnist_lines.py @@ -9,13 +9,13 @@ import torch from loguru import logger as log from torch import Tensor +import text_recognizer.metadata.emnist_lines as metadata from text_recognizer.data.base_data_module import BaseDataModule, load_and_print_info from text_recognizer.data.base_dataset import BaseDataset, convert_strings_to_labels from text_recognizer.data.emnist import EMNIST from text_recognizer.data.tokenizer import Tokenizer from text_recognizer.data.transforms.line import LineStem from text_recognizer.data.utils.sentence_generator import SentenceGenerator -import text_recognizer.metadata.emnist_lines as metadata class EMNISTLines(BaseDataModule): diff --git a/text_recognizer/data/iam.py b/text_recognizer/data/iam.py index 8a31205..e1f6c21 100644 --- a/text_recognizer/data/iam.py +++ b/text_recognizer/data/iam.py @@ -4,18 +4,18 @@ Which encompasses both paragraphs and lines, with associated utilities. """ import os -from pathlib import Path -from typing import Any, Dict, List import xml.etree.ElementTree as ElementTree import zipfile +from pathlib import Path +from typing import Any, Dict, List +import toml from boltons.cacheutils import cachedproperty from loguru import logger as log -import toml +import text_recognizer.metadata.iam as metadata from text_recognizer.data.base_data_module import BaseDataModule, load_and_print_info from text_recognizer.data.utils.download_utils import download_dataset -import text_recognizer.metadata.iam as metadata class IAM(BaseDataModule): diff --git a/text_recognizer/data/iam_extended_paragraphs.py b/text_recognizer/data/iam_extended_paragraphs.py index 3f3500f..3f730ab 100644 --- a/text_recognizer/data/iam_extended_paragraphs.py +++ b/text_recognizer/data/iam_extended_paragraphs.py @@ -3,13 +3,13 @@ from typing import Callable, Optional from torch.utils.data import ConcatDataset +import text_recognizer.metadata.iam_paragraphs as metadata from text_recognizer.data.base_data_module import BaseDataModule, load_and_print_info from text_recognizer.data.iam_paragraphs import IAMParagraphs from text_recognizer.data.iam_synthetic_paragraphs import IAMSyntheticParagraphs -from text_recognizer.data.transforms.pad import Pad from text_recognizer.data.tokenizer import Tokenizer +from text_recognizer.data.transforms.pad import Pad from text_recognizer.data.transforms.paragraph import ParagraphStem -import text_recognizer.metadata.iam_paragraphs as metadata class IAMExtendedParagraphs(BaseDataModule): diff --git a/text_recognizer/data/iam_lines.py b/text_recognizer/data/iam_lines.py index 800e0d7..443386c 100644 --- a/text_recognizer/data/iam_lines.py +++ b/text_recognizer/data/iam_lines.py @@ -12,6 +12,7 @@ from loguru import logger as log from PIL import Image, ImageFile, ImageOps from torch import Tensor +import text_recognizer.metadata.iam_lines as metadata from text_recognizer.data.base_data_module import BaseDataModule, load_and_print_info from text_recognizer.data.base_dataset import ( BaseDataset, @@ -22,7 +23,6 @@ from text_recognizer.data.iam import IAM from text_recognizer.data.tokenizer import Tokenizer from text_recognizer.data.transforms.line import IamLinesStem from text_recognizer.data.utils import image_utils -import text_recognizer.metadata.iam_lines as metadata ImageFile.LOAD_TRUNCATED_IMAGES = True diff --git a/text_recognizer/data/iam_paragraphs.py b/text_recognizer/data/iam_paragraphs.py index 0d53d6b..247b54d 100644 --- a/text_recognizer/data/iam_paragraphs.py +++ b/text_recognizer/data/iam_paragraphs.py @@ -9,6 +9,7 @@ from loguru import logger as log from PIL import Image, ImageOps from tqdm import tqdm +import text_recognizer.metadata.iam_paragraphs as metadata from text_recognizer.data.base_data_module import BaseDataModule, load_and_print_info from text_recognizer.data.base_dataset import ( BaseDataset, @@ -16,10 +17,9 @@ from text_recognizer.data.base_dataset import ( split_dataset, ) from text_recognizer.data.iam import IAM -from text_recognizer.data.transforms.pad import Pad from text_recognizer.data.tokenizer import Tokenizer +from text_recognizer.data.transforms.pad import Pad from text_recognizer.data.transforms.paragraph import ParagraphStem -import text_recognizer.metadata.iam_paragraphs as metadata class IAMParagraphs(BaseDataModule): diff --git a/text_recognizer/data/iam_synthetic_paragraphs.py b/text_recognizer/data/iam_synthetic_paragraphs.py index 5743bcc..45d7904 100644 --- a/text_recognizer/data/iam_synthetic_paragraphs.py +++ b/text_recognizer/data/iam_synthetic_paragraphs.py @@ -6,23 +6,23 @@ import numpy as np from loguru import logger as log from PIL import Image +import text_recognizer.metadata.iam_synthetic_paragraphs as metadata from text_recognizer.data.base_data_module import load_and_print_info from text_recognizer.data.base_dataset import BaseDataset, convert_strings_to_labels from text_recognizer.data.iam import IAM -from text_recognizer.data.iam_paragraphs import ( - IAMParagraphs, - get_dataset_properties, - resize_image, -) from text_recognizer.data.iam_lines import ( line_crops_and_labels, load_line_crops_and_labels, save_images_and_labels, ) +from text_recognizer.data.iam_paragraphs import ( + IAMParagraphs, + get_dataset_properties, + resize_image, +) from text_recognizer.data.tokenizer import Tokenizer -from text_recognizer.data.transforms.paragraph import ParagraphStem from text_recognizer.data.transforms.pad import Pad -import text_recognizer.metadata.iam_synthetic_paragraphs as metadata +from text_recognizer.data.transforms.paragraph import ParagraphStem class IAMSyntheticParagraphs(IAMParagraphs): diff --git a/text_recognizer/data/transforms/image.py b/text_recognizer/data/transforms/image.py index f04b3a0..05c9d94 100644 --- a/text_recognizer/data/transforms/image.py +++ b/text_recognizer/data/transforms/image.py @@ -1,7 +1,7 @@ -from PIL import Image import torch -from torch import Tensor import torchvision.transforms as T +from PIL import Image +from torch import Tensor class ImageStem: diff --git a/text_recognizer/data/transforms/line.py b/text_recognizer/data/transforms/line.py index 6c38213..e4473eb 100644 --- a/text_recognizer/data/transforms/line.py +++ b/text_recognizer/data/transforms/line.py @@ -1,8 +1,8 @@ import random from typing import Any, Dict -from PIL import Image import torchvision.transforms as T +from PIL import Image import text_recognizer.metadata.iam_lines as metadata from text_recognizer.data.transforms.image import ImageStem diff --git a/text_recognizer/data/transforms/paragraph.py b/text_recognizer/data/transforms/paragraph.py index b364f91..639bb59 100644 --- a/text_recognizer/data/transforms/paragraph.py +++ b/text_recognizer/data/transforms/paragraph.py @@ -4,7 +4,6 @@ import torchvision.transforms as T import text_recognizer.metadata.iam_paragraphs as metadata from text_recognizer.data.transforms.image import ImageStem - IMAGE_HEIGHT, IMAGE_WIDTH = metadata.IMAGE_HEIGHT, metadata.IMAGE_WIDTH IMAGE_SHAPE = metadata.IMAGE_SHAPE diff --git a/text_recognizer/data/utils/sentence_generator.py b/text_recognizer/data/utils/sentence_generator.py index c40373d..8ea345a 100644 --- a/text_recognizer/data/utils/sentence_generator.py +++ b/text_recognizer/data/utils/sentence_generator.py @@ -5,8 +5,8 @@ import string from typing import Optional import nltk -from nltk.corpus.reader.util import ConcatenatedCorpusView import numpy as np +from nltk.corpus.reader.util import ConcatenatedCorpusView import text_recognizer.metadata.shared as metadata |