未验证 提交 1a0848a4 编写于 作者: S shaohua.zhang 提交者: GitHub

Merge branch 'develop' into develop

...@@ -212,3 +212,4 @@ We welcome all the contributions to PaddleOCR and appreciate for your feedback v ...@@ -212,3 +212,4 @@ We welcome all the contributions to PaddleOCR and appreciate for your feedback v
- Many thanks to [lyl120117](https://github.com/lyl120117) for contributing the code for printing the network structure. - Many thanks to [lyl120117](https://github.com/lyl120117) for contributing the code for printing the network structure.
- Thanks [xiangyubo](https://github.com/xiangyubo) for contributing the handwritten Chinese OCR datasets. - Thanks [xiangyubo](https://github.com/xiangyubo) for contributing the handwritten Chinese OCR datasets.
- Thanks [authorfu](https://github.com/authorfu) for contributing Android demo and [xiadeye](https://github.com/xiadeye) contributing iOS demo, respectively. - Thanks [authorfu](https://github.com/authorfu) for contributing Android demo and [xiadeye](https://github.com/xiadeye) contributing iOS demo, respectively.
- Thanks [BeyondYourself](https://github.com/BeyondYourself) for contributing many great suggestions and simplifying part of the code style.
...@@ -205,8 +205,9 @@ PaddleOCR文本识别算法的训练和使用请参考文档教程中[模型训 ...@@ -205,8 +205,9 @@ PaddleOCR文本识别算法的训练和使用请参考文档教程中[模型训
## 贡献代码 ## 贡献代码
我们非常欢迎你为PaddleOCR贡献代码,也十分感谢你的反馈。 我们非常欢迎你为PaddleOCR贡献代码,也十分感谢你的反馈。
- 非常感谢 [Khanh Tran](https://github.com/xxxpsyduck) 贡献了英文文档 - 非常感谢 [Khanh Tran](https://github.com/xxxpsyduck) 贡献了英文文档
- 非常感谢 [zhangxin](https://github.com/ZhangXinNan)([Blog](https://blog.csdn.net/sdlypyzq)) 贡献新的可视化方式、添加.gitgnore、处理手动设置PYTHONPATH环境变量的问题 - 非常感谢 [zhangxin](https://github.com/ZhangXinNan)([Blog](https://blog.csdn.net/sdlypyzq)) 贡献新的可视化方式、添加.gitgnore、处理手动设置PYTHONPATH环境变量的问题
- 非常感谢 [lyl120117](https://github.com/lyl120117) 贡献打印网络结构的代码 - 非常感谢 [lyl120117](https://github.com/lyl120117) 贡献打印网络结构的代码
- 非常感谢 [xiangyubo](https://github.com/xiangyubo) 贡献手写中文OCR数据集 - 非常感谢 [xiangyubo](https://github.com/xiangyubo) 贡献手写中文OCR数据集
- 非常感谢 [authorfu](https://github.com/authorfu) 贡献Android和[xiadeye](https://github.com/xiadeye) 贡献IOS的demo代码 - 非常感谢 [authorfu](https://github.com/authorfu) 贡献Android和[xiadeye](https://github.com/xiadeye) 贡献IOS的demo代码
- 非常感谢 [BeyondYourself](https://github.com/BeyondYourself) 给PaddleOCR提了很多非常棒的建议,并简化了PaddleOCR的部分代码风格。
# 如何快速测试 # 如何快速测试
### 1. 安装最新版本的Android Studio ### 1. 安装最新版本的Android Studio
可以从https://developer.android.com/studio下载。本Demo使用是4.0版本Android Studio编写。 可以从https://developer.android.com/studio 下载。本Demo使用是4.0版本Android Studio编写。
### 2. 按照NDK 20 以上版本 ### 2. 按照NDK 20 以上版本
Demo测试的时候使用的是NDK 20b版本,20版本以上均可以支持编译成功。 Demo测试的时候使用的是NDK 20b版本,20版本以上均可以支持编译成功。
......
...@@ -7,7 +7,7 @@ PaddleOCR 工作环境 ...@@ -7,7 +7,7 @@ PaddleOCR 工作环境
- glibc 2.23 - glibc 2.23
- cuDNN 7.6+ (GPU) - cuDNN 7.6+ (GPU)
建议使用我们提供的docker运行PaddleOCR,有关docker使用请参考[链接](https://docs.docker.com/get-started/) 建议使用我们提供的docker运行PaddleOCR,有关docker、nvidia-docker使用请参考[链接](https://docs.docker.com/get-started/)
*如您希望使用 mac 或 windows直接运行预测代码,可以从第2步开始执行。* *如您希望使用 mac 或 windows直接运行预测代码,可以从第2步开始执行。*
......
...@@ -21,12 +21,11 @@ ln -sf <path/to/dataset> <path/to/paddle_ocr>/train_data/dataset ...@@ -21,12 +21,11 @@ ln -sf <path/to/dataset> <path/to/paddle_ocr>/train_data/dataset
* 使用自己数据集: * 使用自己数据集:
若您希望使用自己的数据进行训练,请参考下文组织您的数据。 若您希望使用自己的数据进行训练,请参考下文组织您的数据。
- 训练集 - 训练集
首先请将训练图片放入同一个文件夹(train_images),并用一个txt文件(rec_gt_train.txt)记录图片路径和标签。 首先请将训练图片放入同一个文件夹(train_images),并用一个txt文件(rec_gt_train.txt)记录图片路径和标签。
* 注意: 默认请将图片路径和图片标签用 \t 分割,如用其他方式分割将造成训练报错 **注意:** 默认请将图片路径和图片标签用 \t 分割,如用其他方式分割将造成训练报错
``` ```
" 图像文件名 图像标注信息 " " 图像文件名 图像标注信息 "
...@@ -41,12 +40,9 @@ PaddleOCR 提供了一份用于训练 icdar2015 数据集的标签文件,通 ...@@ -41,12 +40,9 @@ PaddleOCR 提供了一份用于训练 icdar2015 数据集的标签文件,通
wget -P ./train_data/ic15_data https://paddleocr.bj.bcebos.com/dataset/rec_gt_train.txt wget -P ./train_data/ic15_data https://paddleocr.bj.bcebos.com/dataset/rec_gt_train.txt
# 测试集标签 # 测试集标签
wget -P ./train_data/ic15_data https://paddleocr.bj.bcebos.com/dataset/rec_gt_test.txt wget -P ./train_data/ic15_data https://paddleocr.bj.bcebos.com/dataset/rec_gt_test.txt
``` ```
最终训练集应有如下文件结构: 最终训练集应有如下文件结构:
``` ```
|-train_data |-train_data
|-ic15_data |-ic15_data
...@@ -150,7 +146,7 @@ PaddleOCR支持训练和评估交替进行, 可以在 `configs/rec/rec_icdar15_t ...@@ -150,7 +146,7 @@ PaddleOCR支持训练和评估交替进行, 可以在 `configs/rec/rec_icdar15_t
如果验证集很大,测试将会比较耗时,建议减少评估次数,或训练完再进行评估。 如果验证集很大,测试将会比较耗时,建议减少评估次数,或训练完再进行评估。
* 提示: 可通过 -c 参数选择 `configs/rec/` 路径下的多种模型配置进行训练,PaddleOCR支持的识别算法有: **提示:** 可通过 -c 参数选择 `configs/rec/` 路径下的多种模型配置进行训练,PaddleOCR支持的识别算法有:
| 配置文件 | 算法名称 | backbone | trans | seq | pred | | 配置文件 | 算法名称 | backbone | trans | seq | pred |
......
...@@ -17,7 +17,7 @@ import cv2 ...@@ -17,7 +17,7 @@ import cv2
import numpy as np import numpy as np
import json import json
import sys import sys
from ppocr.utils.utility import initial_logger from ppocr.utils.utility import initial_logger, check_and_read_gif
logger = initial_logger() logger = initial_logger()
from .data_augment import AugmentData from .data_augment import AugmentData
...@@ -100,6 +100,8 @@ class DBProcessTrain(object): ...@@ -100,6 +100,8 @@ class DBProcessTrain(object):
def __call__(self, label_infor): def __call__(self, label_infor):
img_path, gt_label = self.convert_label_infor(label_infor) img_path, gt_label = self.convert_label_infor(label_infor)
imgvalue, flag = check_and_read_gif(img_path)
if not flag:
imgvalue = cv2.imread(img_path) imgvalue = cv2.imread(img_path)
if imgvalue is None: if imgvalue is None:
logger.info("{} does not exist!".format(img_path)) logger.info("{} does not exist!".format(img_path))
......
...@@ -233,7 +233,7 @@ class SimpleReader(object): ...@@ -233,7 +233,7 @@ class SimpleReader(object):
img_num = len(label_infor_list) img_num = len(label_infor_list)
img_id_list = list(range(img_num)) img_id_list = list(range(img_num))
random.shuffle(img_id_list) random.shuffle(img_id_list)
if sys.platform == "win32": if sys.platform == "win32" and self.num_workers != 1:
print("multiprocess is not fully compatible with Windows." print("multiprocess is not fully compatible with Windows."
"num_workers will be 1.") "num_workers will be 1.")
self.num_workers = 1 self.num_workers = 1
......
...@@ -15,6 +15,8 @@ ...@@ -15,6 +15,8 @@
import logging import logging
import os import os
import imghdr import imghdr
import cv2
from paddle import fluid
def initial_logger(): def initial_logger():
...@@ -62,7 +64,7 @@ def get_image_file_list(img_file): ...@@ -62,7 +64,7 @@ def get_image_file_list(img_file):
if img_file is None or not os.path.exists(img_file): if img_file is None or not os.path.exists(img_file):
raise Exception("not found any img file in {}".format(img_file)) raise Exception("not found any img file in {}".format(img_file))
img_end = {'jpg', 'bmp', 'png', 'jpeg', 'rgb', 'tif', 'tiff'} img_end = {'jpg', 'bmp', 'png', 'jpeg', 'rgb', 'tif', 'tiff', 'gif', 'GIF'}
if os.path.isfile(img_file) and imghdr.what(img_file) in img_end: if os.path.isfile(img_file) and imghdr.what(img_file) in img_end:
imgs_lists.append(img_file) imgs_lists.append(img_file)
elif os.path.isdir(img_file): elif os.path.isdir(img_file):
...@@ -75,7 +77,18 @@ def get_image_file_list(img_file): ...@@ -75,7 +77,18 @@ def get_image_file_list(img_file):
return imgs_lists return imgs_lists
from paddle import fluid def check_and_read_gif(img_path):
if os.path.basename(img_path)[-3:] in ['gif', 'GIF']:
gif = cv2.VideoCapture(img_path)
ret, frame = gif.read()
if not ret:
logging.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
return None, False
def create_multi_devices_program(program, loss_var_name): def create_multi_devices_program(program, loss_var_name):
......
...@@ -20,7 +20,7 @@ sys.path.append(os.path.join(__dir__, '../..')) ...@@ -20,7 +20,7 @@ sys.path.append(os.path.join(__dir__, '../..'))
import tools.infer.utility as utility import tools.infer.utility as utility
from ppocr.utils.utility import initial_logger from ppocr.utils.utility import initial_logger
logger = initial_logger() logger = initial_logger()
from ppocr.utils.utility import get_image_file_list from ppocr.utils.utility import get_image_file_list, check_and_read_gif
import cv2 import cv2
from ppocr.data.det.east_process import EASTProcessTest from ppocr.data.det.east_process import EASTProcessTest
from ppocr.data.det.db_process import DBProcessTest from ppocr.data.det.db_process import DBProcessTest
...@@ -139,6 +139,8 @@ if __name__ == "__main__": ...@@ -139,6 +139,8 @@ if __name__ == "__main__":
if not os.path.exists(draw_img_save): if not os.path.exists(draw_img_save):
os.makedirs(draw_img_save) os.makedirs(draw_img_save)
for image_file in image_file_list: for image_file in image_file_list:
img, flag = check_and_read_gif(image_file)
if not flag:
img = cv2.imread(image_file) img = cv2.imread(image_file)
if img is None: if img is None:
logger.info("error in loading image:{}".format(image_file)) logger.info("error in loading image:{}".format(image_file))
......
...@@ -20,7 +20,7 @@ sys.path.append(os.path.abspath(os.path.join(__dir__, '../..'))) ...@@ -20,7 +20,7 @@ sys.path.append(os.path.abspath(os.path.join(__dir__, '../..')))
import tools.infer.utility as utility import tools.infer.utility as utility
from ppocr.utils.utility import initial_logger from ppocr.utils.utility import initial_logger
logger = initial_logger() logger = initial_logger()
from ppocr.utils.utility import get_image_file_list from ppocr.utils.utility import get_image_file_list, check_and_read_gif
import cv2 import cv2
import copy import copy
import numpy as np import numpy as np
...@@ -153,7 +153,9 @@ def main(args): ...@@ -153,7 +153,9 @@ def main(args):
valid_image_file_list = [] valid_image_file_list = []
img_list = [] img_list = []
for image_file in image_file_list: for image_file in image_file_list:
img = cv2.imread(image_file, cv2.IMREAD_COLOR) img, flag = check_and_read_gif(image_file)
if not flag:
img = cv2.imread(image_file)
if img is None: if img is None:
logger.info("error in loading image:{}".format(image_file)) logger.info("error in loading image:{}".format(image_file))
continue continue
......
...@@ -27,7 +27,7 @@ import copy ...@@ -27,7 +27,7 @@ import copy
import numpy as np import numpy as np
import math import math
import time import time
from ppocr.utils.utility import get_image_file_list from ppocr.utils.utility import get_image_file_list, check_and_read_gif
from PIL import Image from PIL import Image
from tools.infer.utility import draw_ocr from tools.infer.utility import draw_ocr
from tools.infer.utility import draw_ocr_box_txt from tools.infer.utility import draw_ocr_box_txt
...@@ -49,16 +49,21 @@ class TextSystem(object): ...@@ -49,16 +49,21 @@ class TextSystem(object):
points[:, 0] = points[:, 0] - left points[:, 0] = points[:, 0] - left
points[:, 1] = points[:, 1] - top points[:, 1] = points[:, 1] - top
''' '''
img_crop_width = int(max(np.linalg.norm(points[0] - points[1]), img_crop_width = int(
max(
np.linalg.norm(points[0] - points[1]),
np.linalg.norm(points[2] - points[3]))) np.linalg.norm(points[2] - points[3])))
img_crop_height = int(max(np.linalg.norm(points[0] - points[3]), img_crop_height = int(
max(
np.linalg.norm(points[0] - points[3]),
np.linalg.norm(points[1] - points[2]))) np.linalg.norm(points[1] - points[2])))
pts_std = np.float32([[0, 0], pts_std = np.float32([[0, 0], [img_crop_width, 0],
[img_crop_width, 0],
[img_crop_width, img_crop_height], [img_crop_width, img_crop_height],
[0, img_crop_height]]) [0, img_crop_height]])
M = cv2.getPerspectiveTransform(points, pts_std) M = cv2.getPerspectiveTransform(points, pts_std)
dst_img = cv2.warpPerspective(img, M, (img_crop_width, img_crop_height), dst_img = cv2.warpPerspective(
img,
M, (img_crop_width, img_crop_height),
borderMode=cv2.BORDER_REPLICATE, borderMode=cv2.BORDER_REPLICATE,
flags=cv2.INTER_CUBIC) flags=cv2.INTER_CUBIC)
dst_img_height, dst_img_width = dst_img.shape[0:2] dst_img_height, dst_img_width = dst_img.shape[0:2]
...@@ -119,6 +124,8 @@ def main(args): ...@@ -119,6 +124,8 @@ def main(args):
is_visualize = True is_visualize = True
tackle_img_num = 0 tackle_img_num = 0
for image_file in image_file_list: for image_file in image_file_list:
img, flag = check_and_read_gif(image_file)
if not flag:
img = cv2.imread(image_file) img = cv2.imread(image_file)
if img is None: if img is None:
logger.info("error in loading image:{}".format(image_file)) logger.info("error in loading image:{}".format(image_file))
...@@ -130,14 +137,14 @@ def main(args): ...@@ -130,14 +137,14 @@ def main(args):
dt_boxes, rec_res = text_sys(img) dt_boxes, rec_res = text_sys(img)
elapse = time.time() - starttime elapse = time.time() - starttime
print("Predict time of %s: %.3fs" % (image_file, elapse)) print("Predict time of %s: %.3fs" % (image_file, elapse))
drop_score = 0.5
dt_num = len(dt_boxes) dt_num = len(dt_boxes)
dt_boxes_final = []
for dno in range(dt_num): for dno in range(dt_num):
text, score = rec_res[dno] text, score = rec_res[dno]
if score >= 0.5: if score >= drop_score:
text_str = "%s, %.3f" % (text, score) text_str = "%s, %.3f" % (text, score)
print(text_str) print(text_str)
dt_boxes_final.append(dt_boxes[dno])
if is_visualize: if is_visualize:
image = Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB)) image = Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
...@@ -146,7 +153,12 @@ def main(args): ...@@ -146,7 +153,12 @@ def main(args):
scores = [rec_res[i][1] for i in range(len(rec_res))] scores = [rec_res[i][1] for i in range(len(rec_res))]
draw_img = draw_ocr( draw_img = draw_ocr(
image, boxes, txts, scores, draw_txt=True, drop_score=0.5) image,
boxes,
txts,
scores,
draw_txt=True,
drop_score=drop_score)
draw_img_save = "./inference_results/" draw_img_save = "./inference_results/"
if not os.path.exists(draw_img_save): if not os.path.exists(draw_img_save):
os.makedirs(draw_img_save) os.makedirs(draw_img_save)
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册