openocr-python 0.0.2__py3-none-any.whl

openocr/tools/utils/stats.py

@@ -0,0 +1,58 @@
+import collections
+import numpy as np
+import datetime
+
+__all__ = ["TrainingStats", "Time"]
+
+
+class SmoothedValue(object):
+    """Track a series of values and provide access to smoothed values over a
+    window or the global series average.
+    """
+
+    def __init__(self, window_size):
+        self.deque = collections.deque(maxlen=window_size)
+
+    def add_value(self, value):
+        self.deque.append(value)
+
+    def get_median_value(self):
+        return np.median(self.deque)
+
+
+def Time():
+    return datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S.%f")
+
+
+class TrainingStats(object):
+    def __init__(self, window_size, stats_keys):
+        self.window_size = window_size
+        self.smoothed_losses_and_metrics = {
+            key: SmoothedValue(window_size)
+            for key in stats_keys
+        }
+
+    def update(self, stats):
+        for k, v in stats.items():
+            if k not in self.smoothed_losses_and_metrics:
+                self.smoothed_losses_and_metrics[k] = SmoothedValue(
+                    self.window_size)
+            self.smoothed_losses_and_metrics[k].add_value(v)
+
+    def get(self, extras=None):
+        stats = collections.OrderedDict()
+        if extras:
+            for k, v in extras.items():
+                stats[k] = v
+        for k, v in self.smoothed_losses_and_metrics.items():
+            stats[k] = round(v.get_median_value(), 6)
+
+        return stats
+
+    def log(self, extras=None):
+        d = self.get(extras)
+        strs = []
+        for k, v in d.items():
+            strs.append("{}: {:x<6f}".format(k, v))
+        strs = ", ".join(strs)
+        return strs

openocr/tools/utils/utility.py

@@ -0,0 +1,165 @@
+import logging
+import os
+import cv2
+import numpy as np
+import importlib.util
+import sys
+import subprocess
+
+
+def get_check_global_params(mode):
+    check_params = [
+        "use_gpu",
+        "max_text_length",
+        "image_shape",
+        "image_shape",
+        "character_type",
+        "loss_type",
+    ]
+    if mode == "train_eval":
+        check_params = check_params + [
+            "train_batch_size_per_card",
+            "test_batch_size_per_card",
+        ]
+    elif mode == "test":
+        check_params = check_params + ["test_batch_size_per_card"]
+    return check_params
+
+
+def _check_image_file(path):
+    img_end = {"jpg", "bmp", "png", "jpeg", "rgb", "tif", "tiff", "gif", "pdf"}
+    return any([path.lower().endswith(e) for e in img_end])
+
+
+def get_image_file_list(img_file):
+    imgs_lists = []
+    if img_file is None or not os.path.exists(img_file):
+        raise Exception("not found any img file in {}".format(img_file))
+
+    if os.path.isfile(img_file) and _check_image_file(img_file):
+        imgs_lists.append(img_file)
+    elif os.path.isdir(img_file):
+        for single_file in os.listdir(img_file):
+            file_path = os.path.join(img_file, single_file)
+            if os.path.isfile(file_path) and _check_image_file(file_path):
+                imgs_lists.append(file_path)
+    if len(imgs_lists) == 0:
+        raise Exception("not found any img file in {}".format(img_file))
+    imgs_lists = sorted(imgs_lists)
+    return imgs_lists
+
+
+def binarize_img(img):
+    if len(img.shape) == 3 and img.shape[2] == 3:
+        gray = cv2.cvtColor(img,
+                            cv2.COLOR_BGR2GRAY)  # conversion to grayscale image
+        # use cv2 threshold binarization
+        _, gray = cv2.threshold(gray, 0, 255,
+                                cv2.THRESH_BINARY + cv2.THRESH_OTSU)
+        img = cv2.cvtColor(gray, cv2.COLOR_GRAY2BGR)
+    return img
+
+
+def alpha_to_color(img, alpha_color=(255, 255, 255)):
+    if len(img.shape) == 3 and img.shape[2] == 4:
+        B, G, R, A = cv2.split(img)
+        alpha = A / 255
+
+        R = (alpha_color[0] * (1 - alpha) + R * alpha).astype(np.uint8)
+        G = (alpha_color[1] * (1 - alpha) + G * alpha).astype(np.uint8)
+        B = (alpha_color[2] * (1 - alpha) + B * alpha).astype(np.uint8)
+
+        img = cv2.merge((B, G, R))
+    return img
+
+
+def check_and_read(img_path):
+    if os.path.basename(img_path)[-3:].lower() == "gif":
+        gif = cv2.VideoCapture(img_path)
+        ret, frame = gif.read()
+        if not ret:
+            logger = logging.getLogger("openrec")
+            logger.info("Cannot read {}. This gif image maybe corrupted.")
+            return None, False
+        if len(frame.shape) == 2 or frame.shape[-1] == 1:
+            frame = cv2.cvtColor(frame, cv2.COLOR_GRAY2RGB)
+        imgvalue = frame[:, :, ::-1]
+        return imgvalue, True, False
+    elif os.path.basename(img_path)[-3:].lower() == "pdf":
+        import fitz
+        from PIL import Image
+
+        imgs = []
+        with fitz.open(img_path) as pdf:
+            for pg in range(0, pdf.page_count):
+                page = pdf[pg]
+                mat = fitz.Matrix(2, 2)
+                pm = page.get_pixmap(matrix=mat, alpha=False)
+
+                # if width or height > 2000 pixels, don't enlarge the image
+                if pm.width > 2000 or pm.height > 2000:
+                    pm = page.get_pixmap(matrix=fitz.Matrix(1, 1), alpha=False)
+
+                img = Image.frombytes("RGB", [pm.width, pm.height], pm.samples)
+                img = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)
+                imgs.append(img)
+            return imgs, False, True
+    return None, False, False
+
+
+def load_vqa_bio_label_maps(label_map_path):
+    with open(label_map_path, "r", encoding="utf-8") as fin:
+        lines = fin.readlines()
+    old_lines = [line.strip() for line in lines]
+    lines = ["O"]
+    for line in old_lines:
+        # "O" has already been in lines
+        if line.upper() in ["OTHER", "OTHERS", "IGNORE"]:
+            continue
+        lines.append(line)
+    labels = ["O"]
+    for line in lines[1:]:
+        labels.append("B-" + line)
+        labels.append("I-" + line)
+    label2id_map = {label.upper(): idx for idx, label in enumerate(labels)}
+    id2label_map = {idx: label.upper() for idx, label in enumerate(labels)}
+    return label2id_map, id2label_map
+
+
+def check_install(module_name, install_name):
+    spec = importlib.util.find_spec(module_name)
+    if spec is None:
+        print(f"Warnning! The {module_name} module is NOT installed")
+        print(
+            f"Try install {module_name} module automatically. You can also try to install manually by pip install {install_name}."
+        )
+        python = sys.executable
+        try:
+            subprocess.check_call(
+                [python, "-m", "pip", "install", install_name],
+                stdout=subprocess.DEVNULL, )
+            print(f"The {module_name} module is now installed")
+        except subprocess.CalledProcessError as exc:
+            raise Exception(
+                f"Install {module_name} failed, please install manually")
+    else:
+        print(f"{module_name} has been installed.")
+
+
+class AverageMeter:
+    def __init__(self):
+        self.reset()
+
+    def reset(self):
+        """reset"""
+        self.val = 0
+        self.avg = 0
+        self.sum = 0
+        self.count = 0
+
+    def update(self, val, n=1):
+        """update"""
+        self.val = val
+        self.sum += val * n
+        self.count += n
+        self.avg = self.sum / self.count

openocr/tools/utils/visual.py

@@ -0,0 +1,117 @@
+import cv2
+import random
+import math
+import numpy as np
+from PIL import Image, ImageDraw, ImageFont
+
+__all__ = ["draw_system", "draw_det"]
+
+
+def draw_det(dt_boxes, img):
+    for box in dt_boxes:
+        box = np.array(box).astype(np.int32).reshape(-1, 2)
+        cv2.polylines(img, [box], True, color=(255, 255, 0), thickness=2)
+    return img
+
+
+def draw_system(
+        image,
+        boxes,
+        txts=None,
+        scores=None,
+        drop_score=0.5,
+        font_path="./doc/fonts/simfang.ttf", ):
+    h, w = image.height, image.width
+    img_left = image.copy()
+    img_right = np.ones((h, w, 3), dtype=np.uint8) * 255
+    random.seed(0)
+
+    draw_left = ImageDraw.Draw(img_left)
+    if txts is None or len(txts) != len(boxes):
+        txts = [None] * len(boxes)
+    for idx, (box, txt) in enumerate(zip(boxes, txts)):
+        if scores is not None and scores[idx] < drop_score:
+            continue
+        color = (random.randint(0, 255), random.randint(0, 255),
+                 random.randint(0, 255))
+        draw_left.polygon(box, fill=color)
+        img_right_text = draw_box_txt_fine((w, h), box, txt, font_path)
+        pts = np.array(box, np.int32).reshape((-1, 1, 2))
+        cv2.polylines(img_right_text, [pts], True, color, 1)
+        img_right = cv2.bitwise_and(img_right, img_right_text)
+    img_left = Image.blend(image, img_left, 0.5)
+    img_show = Image.new("RGB", (w * 2, h), (255, 255, 255))
+    img_show.paste(img_left, (0, 0, w, h))
+    img_show.paste(Image.fromarray(img_right), (w, 0, w * 2, h))
+    return np.array(img_show)
+
+
+def draw_box_txt_fine(img_size, box, txt, font_path="./doc/fonts/simfang.ttf"):
+    box_height = int(
+        math.sqrt((box[0][0] - box[3][0])**2 + (box[0][1] - box[3][1])**2))
+    box_width = int(
+        math.sqrt((box[0][0] - box[1][0])**2 + (box[0][1] - box[1][1])**2))
+
+    if box_height > 2 * box_width and box_height > 30:
+        img_text = Image.new("RGB", (box_height, box_width), (255, 255, 255))
+        draw_text = ImageDraw.Draw(img_text)
+        if txt:
+            font = create_font(txt, (box_height, box_width), font_path)
+            draw_text.text([0, 0], txt, fill=(0, 0, 0), font=font)
+        img_text = img_text.transpose(Image.ROTATE_270)
+    else:
+        img_text = Image.new("RGB", (box_width, box_height), (255, 255, 255))
+        draw_text = ImageDraw.Draw(img_text)
+        if txt:
+            font = create_font(txt, (box_width, box_height), font_path)
+            draw_text.text([0, 0], txt, fill=(0, 0, 0), font=font)
+
+    pts1 = np.float32(
+        [[0, 0], [box_width, 0], [box_width, box_height], [0, box_height]])
+    pts2 = np.array(box, dtype=np.float32)
+    M = cv2.getPerspectiveTransform(pts1, pts2)
+
+    img_text = np.array(img_text, dtype=np.uint8)
+    img_right_text = cv2.warpPerspective(
+        img_text,
+        M,
+        img_size,
+        flags=cv2.INTER_NEAREST,
+        borderMode=cv2.BORDER_CONSTANT,
+        borderValue=(255, 255, 255), )
+    return img_right_text
+
+
+def create_font(txt, sz, font_path="./doc/fonts/simfang.ttf"):
+    font_size = int(sz[1] * 0.99)
+    font = ImageFont.truetype(font_path, font_size, encoding="utf-8")
+    length = font.getlength(txt)
+    if length > sz[0]:
+        font_size = int(font_size * sz[0] / length)
+        font = ImageFont.truetype(font_path, font_size, encoding="utf-8")
+    return font
+
+
+def str_count(s):
+    """
+    Count the number of Chinese characters,
+    a single English character and a single number
+    equal to half the length of Chinese characters.
+    args:
+        s(string): the input of string
+    return(int):
+        the number of Chinese characters
+    """
+    import string
+
+    count_zh = count_pu = 0
+    s_len = len(s)
+    en_dg_count = 0
+    for c in s:
+        if c in string.ascii_letters or c.isdigit() or c.isspace():
+            en_dg_count += 1
+        elif c.isalpha():
+            count_zh += 1
+        else:
+            count_pu += 1
+    return s_len - math.ceil(en_dg_count / 2)

openocr_python-0.0.2.dist-info/LICENCE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   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.

openocr_python-0.0.2.dist-info/METADATA

@@ -0,0 +1,98 @@
+Metadata-Version: 2.1
+Name: openocr-python
+Version: 0.0.2
+Summary: a python package for openocr, which is used to help developers quickly deploy OCR algorithms implemented in the openocr framework.
+Home-page: https://github.com/Topdu/OpenOCR
+Author: OpenOCR
+Author-email: 784990967@qq.com
+Project-URL: Source Code, https://github.com/Topdu/OpenOCR
+Keywords: python,OCR,STR,OpenOCR,openocr
+Classifier: Development Status :: 1 - Planning
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: Unix
+Classifier: Operating System :: Microsoft :: Windows
+Description-Content-Type: text/markdown
+License-File: LICENCE
+Requires-Dist: opencv-python<=4.6.0.66
+Requires-Dist: tqdm
+Requires-Dist: rapidfuzz
+Requires-Dist: lmdb
+Requires-Dist: imgaug
+Requires-Dist: pyyaml
+Requires-Dist: pyclipper
+
+# OpenOCR: a general OCR system with accuracy and efficiency
+
+## Quick Start
+
+### Dependencies:
+
+- [PyTorch](http://pytorch.org/) version >= 1.13.0
+- Python version >= 3.7
+
+```shell
+conda create -n openocr python==3.8
+conda activate openocr
+conda install pytorch==2.2.0 torchvision==0.17.0 torchaudio==2.2.0 pytorch-cuda=11.8 -c pytorch -c nvidia
+```
+
+After installing dependencies, the following two installation methods are available. Either one can be chosen.
+
+### 1. Python Modules
+
+```shell
+pip install openocr-python
+```
+
+**Usage**:
+
+```python
+from openocr import OpenOCR
+
+engine = OpenOCR()
+
+img_path = '/path/img_path or /path/img_file'
+result, elapse = engine(img_path)
+
+# Server mode
+# engine = OpenOCR(mode='server')
+```
+
+### 2. Clone this repository:
+
+```shell
+git clone https://github.com/Topdu/OpenOCR.git
+cd OpenOCR
+pip install -r requirements.txt
+wget https://github.com/Topdu/OpenOCR/releases/download/develop0.0.1/openocr_det_repvit_ch.pth
+wget https://github.com/Topdu/OpenOCR/releases/download/develop0.0.1/openocr_repsvtr_ch.pth
+# Rec Server model
+# wget https://github.com/Topdu/OpenOCR/releases/download/develop0.0.1/openocr_svtrv2_ch.pth
+```
+
+**Usage**:
+
+```shell
+# OpenOCR system: Det + Rec model
+python tools/infer_e2e.py --img_path=/path/img_fold or /path/img_file
+
+# Det model
+python tools/infer_det.py --c ./configs/det/dbnet/repvit_db.yml --o Global.infer_img=/path/img_fold or /path/img_file
+
+# Rec model
+python tools/infer_rec.py --c ./configs/rec/svtrv2/repsvtr_ch.yml --o Global.infer_img=/path/img_fold or /path/img_file
+```
+
+#### Demo
+
+```shell
+pip install gradio==4.20.0
+wget https://github.com/Topdu/OpenOCR/releases/download/develop0.0.1/OCR_e2e_img.tar
+tar xf OCR_e2e_img.tar
+# start demo
+python demo_gradio.py
+```
+
+
+## More detail in [OpenOCR Documentation](https://github.com/Topdu/OpenOCR)