EasyCV/easycv/models/ocr/postprocess/rec_postprocess.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.
# Modified from https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.6/ppocr/postprocess/rec_postprocess.py
import os.path as osp
import re
import string

import numpy as np
import requests
import torch


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

    def __init__(self, character_dict_path=None, use_space_char=False):
        self.beg_str = 'sos'
        self.end_str = 'eos'

        self.character_str = []
        if character_dict_path is None:
            self.character_str = '0123456789abcdefghijklmnopqrstuvwxyz'
            dict_character = list(self.character_str)
        else:
            if character_dict_path.startswith('http'):
                r = requests.get(character_dict_path)
                tpath = character_dict_path.split('/')[-1]
                while not osp.exists(tpath):
                    try:
                        with open(tpath, 'wb') as code:
                            code.write(r.content)
                    except:
                        pass
                character_dict_path = tpath
            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.append(line)
            if use_space_char:
                self.character_str.append(' ')
            dict_character = list(self.character_str)

        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 decode(self, text_index, text_prob=None, is_remove_duplicate=False):
        """ convert text-index into text-label. """
        result_list = []
        ignored_tokens = self.get_ignored_tokens()
        batch_size = len(text_index)
        for batch_idx in range(batch_size):
            selection = np.ones(len(text_index[batch_idx]), dtype=bool)
            if is_remove_duplicate:
                selection[1:] = text_index[batch_idx][1:] != text_index[
                    batch_idx][:-1]
            for ignored_token in ignored_tokens:
                selection &= text_index[batch_idx] != ignored_token
            char_list = [
                self.character[text_id]
                for text_id in text_index[batch_idx][selection]
            ]
            if text_prob is not None:
                conf_list = text_prob[batch_idx][selection]
            else:
                conf_list = [1] * len(selection)
            if len(conf_list) == 0:
                conf_list = [0]

            text = ''.join(char_list)
            result_list.append((text, np.mean(conf_list).tolist()))
        return result_list

    def get_ignored_tokens(self):
        return [0]  # for ctc blank


class CTCLabelDecode(BaseRecLabelDecode):
    """ Convert between text-label and text-index """

    def __init__(self,
                 character_dict_path=None,
                 use_space_char=False,
                 **kwargs):
        super(CTCLabelDecode, self).__init__(character_dict_path,
                                             use_space_char)

    def __call__(self, preds, label=None, *args, **kwargs):
        if isinstance(preds, tuple) or isinstance(preds, list):
            preds = preds[-1]
        if isinstance(preds, torch.Tensor):
            preds = preds.numpy()
        preds_idx = preds.argmax(axis=2)
        preds_prob = preds.max(axis=2)
        text = self.decode(preds_idx, preds_prob, is_remove_duplicate=True)
        if label is None:
            return text
        label = self.decode(label)
        return text, label

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


class SARLabelDecode(BaseRecLabelDecode):
    """ Convert between text-label and text-index """

    def __init__(self,
                 character_dict_path=None,
                 use_space_char=False,
                 **kwargs):
        super(SARLabelDecode, self).__init__(character_dict_path,
                                             use_space_char)

        self.rm_symbol = kwargs.get('rm_symbol', False)

    def add_special_char(self, dict_character):
        beg_end_str = '<BOS/EOS>'
        unknown_str = '<UKN>'
        padding_str = '<PAD>'
        dict_character = dict_character + [unknown_str]
        self.unknown_idx = len(dict_character) - 1
        dict_character = dict_character + [beg_end_str]
        self.start_idx = len(dict_character) - 1
        self.end_idx = len(dict_character) - 1
        dict_character = dict_character + [padding_str]
        self.padding_idx = len(dict_character) - 1
        return dict_character

    def decode(self, text_index, text_prob=None, is_remove_duplicate=False):
        """ convert text-index into text-label. """
        result_list = []
        ignored_tokens = self.get_ignored_tokens()

        batch_size = len(text_index)
        for batch_idx in range(batch_size):
            char_list = []
            conf_list = []
            for idx in range(len(text_index[batch_idx])):
                if text_index[batch_idx][idx] in ignored_tokens:
                    continue
                if int(text_index[batch_idx][idx]) == int(self.end_idx):
                    if text_prob is None and idx == 0:
                        continue
                    else:
                        break
                if is_remove_duplicate:
                    # only for predict
                    if idx > 0 and text_index[batch_idx][
                            idx - 1] == text_index[batch_idx][idx]:
                        continue
                char_list.append(self.character[int(
                    text_index[batch_idx][idx])])
                if text_prob is not None:
                    conf_list.append(text_prob[batch_idx][idx])
                else:
                    conf_list.append(1)
            text = ''.join(char_list)
            if self.rm_symbol:
                comp = re.compile('[^A-Z^a-z^0-9^\u4e00-\u9fa5]')
                text = text.lower()
                text = comp.sub('', text)
            result_list.append((text, np.mean(conf_list).tolist()))
        return result_list

    def __call__(self, preds, label=None, *args, **kwargs):
        if isinstance(preds, torch.Tensor):
            preds = preds.cpu().numpy()
        preds_idx = preds.argmax(axis=2)
        preds_prob = preds.max(axis=2)

        text = self.decode(preds_idx, preds_prob, is_remove_duplicate=False)

        if label is None:
            return text
        label = self.decode(label, is_remove_duplicate=False)
        return text, label

    def get_ignored_tokens(self):
        return [self.padding_idx]