label_ops.py

# copyright (c) 2020 PaddlePaddle Authors. All Rights Reserve.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literals

import numpy as np


class ClsLabelEncode(object):
    def __init__(self, label_list, **kwargs):
        self.label_list = label_list

    def __call__(self, data):
        label = data['label']
        if label not in self.label_list:
            return None
        label = self.label_list.index(label)
        data['label'] = label
        return data


class DetLabelEncode(object):
    def __init__(self, **kwargs):
        pass

    def __call__(self, data):
        import json
        label = data['label']
        label = json.loads(label)
        nBox = len(label)
        boxes, txts, txt_tags = [], [], []
        for bno in range(0, nBox):
            box = label[bno]['points']
            txt = label[bno]['transcription']
            boxes.append(box)
            txts.append(txt)
            if txt in ['*', '###']:
                txt_tags.append(True)
            else:
                txt_tags.append(False)
        boxes = self.expand_points_num(boxes)
        boxes = np.array(boxes, dtype=np.float32)
        txt_tags = np.array(txt_tags, dtype=np.bool)

        data['polys'] = boxes
        data['texts'] = txts
        data['ignore_tags'] = txt_tags
        return data

    def order_points_clockwise(self, pts):
        rect = np.zeros((4, 2), dtype="float32")
        s = pts.sum(axis=1)
        rect[0] = pts[np.argmin(s)]
        rect[2] = pts[np.argmax(s)]
        diff = np.diff(pts, axis=1)
        rect[1] = pts[np.argmin(diff)]
        rect[3] = pts[np.argmax(diff)]
        return rect

    def expand_points_num(self, boxes):
        max_points_num = 0
        for box in boxes:
            if len(box) > max_points_num:
                max_points_num = len(box)
        ex_boxes = []
        for box in boxes:
            ex_box = box + [box[-1]] * (max_points_num - len(box))
            ex_boxes.append(ex_box)
        return ex_boxes


class BaseRecLabelEncode(object):
    """ Convert between text-label and text-index """

    def __init__(self,
                 max_text_length,
                 character_dict_path=None,
                 character_type='ch',
                 use_space_char=False):
        support_character_type = [
            'ch', 'en', 'en_sensitive', 'french', 'german', 'japan', 'korean'
        ]
        assert character_type in support_character_type, "Only {} are supported now but get {}".format(
            support_character_type, character_type)

        self.max_text_len = max_text_length
        if character_type == "en":
            self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"
            dict_character = list(self.character_str)
        elif character_type in ["ch", "french", "german", "japan", "korean"]:
            self.character_str = ""
            assert character_dict_path is not None, "character_dict_path should not be None when character_type is ch"
            with open(character_dict_path, "rb") as fin:
                lines = fin.readlines()
                for line in lines:
                    line = line.decode('utf-8').strip("\n").strip("\r\n")
                    self.character_str += line
            if use_space_char:
                self.character_str += " "
            dict_character = list(self.character_str)
        elif character_type == "en_sensitive":
            # same with ASTER setting (use 94 char).
            import string
            self.character_str = string.printable[:-6]
            dict_character = list(self.character_str)
        self.character_type = character_type
        dict_character = self.add_special_char(dict_character)
        self.dict = {}
        for i, char in enumerate(dict_character):
            self.dict[char] = i
        self.character = dict_character

    def add_special_char(self, dict_character):
        return dict_character

    def encode(self, text):
        """convert text-label into text-index.
        input:
            text: text labels of each image. [batch_size]

        output:
            text: concatenated text index for CTCLoss.
                    [sum(text_lengths)] = [text_index_0 + text_index_1 + ... + text_index_(n - 1)]
            length: length of each text. [batch_size]
        """
        if len(text) == 0 or len(text) > self.max_text_len:
            return None
        if self.character_type == "en":
            text = text.lower()
        text_list = []
        for char in text:
            if char not in self.dict:
                # logger = get_logger()
                # logger.warning('{} is not in dict'.format(char))
                continue
            text_list.append(self.dict[char])
        if len(text_list) == 0:
            return None
        return text_list


class CTCLabelEncode(BaseRecLabelEncode):
    """ Convert between text-label and text-index """

    def __init__(self,
                 max_text_length,
                 character_dict_path=None,
                 character_type='ch',
                 use_space_char=False,
                 **kwargs):
        super(CTCLabelEncode,
              self).__init__(max_text_length, character_dict_path,
                             character_type, use_space_char)

    def __call__(self, data):
        text = data['label']
        text = self.encode(text)
        if text is None:
            return None
        data['length'] = np.array(len(text))
        text = text + [0] * (self.max_text_len - len(text))
        data['label'] = np.array(text)
        return data

    def add_special_char(self, dict_character):
        dict_character = ['blank'] + dict_character
        return dict_character


class AttnLabelEncode(BaseRecLabelEncode):
    """ Convert between text-label and text-index """

    def __init__(self,
                 max_text_length,
                 character_dict_path=None,
                 character_type='ch',
                 use_space_char=False,
                 **kwargs):
        super(AttnLabelEncode,
              self).__init__(max_text_length, character_dict_path,
                             character_type, use_space_char)
        self.beg_str = "sos"
        self.end_str = "eos"

    def add_special_char(self, dict_character):
        dict_character = [self.beg_str, self.end_str] + dict_character
        return dict_character

    def __call__(self, text):
        text = self.encode(text)
        return text

    def get_beg_end_flag_idx(self, beg_or_end):
        if beg_or_end == "beg":
            idx = np.array(self.dict[self.beg_str])
        elif beg_or_end == "end":
            idx = np.array(self.dict[self.end_str])
        else:
            assert False, "Unsupport type %s in get_beg_end_flag_idx" \
                          % beg_or_end
        return idx