Merge branch 'develop' into develop
This commit is contained in:
shaohua.zhang
GitHub
commit
1a0848a464
|
|
@ -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.
|
||||
- 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 [BeyondYourself](https://github.com/BeyondYourself) for contributing many great suggestions and simplifying part of the code style.
|
||||
|
|
|
|||
|
|
@ -32,7 +32,7 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力
|
|||
上图是超轻量级中文OCR模型效果展示，更多效果图请见[效果展示页面](./doc/doc_ch/visualization.md)。
|
||||
|
||||
- 超轻量级中文OCR在线体验地址：https://www.paddlepaddle.org.cn/hub/scene/ocr
|
||||
- 移动端DEMO体验(基于EasyEdge和Paddle-Lite, 支持iOS和Android系统)：[安装包二维码获取地址](https://ai.baidu.com/easyedge/app/openSource?from=paddlelite)
|
||||
- 移动端DEMO体验(基于EasyEdge和Paddle-Lite, 支持iOS和Android系统)：[安装包二维码获取地址](https://ai.baidu.com/easyedge/app/openSource?from=paddlelite)
|
||||
|
||||
Android手机也可以扫描下面二维码安装体验。
|
||||
|
||||
|
|
@ -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
|
||||
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 [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 [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。
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# 如何快速测试
|
||||
### 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
|
||||
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
|
|||
- glibc 2.23
|
||||
- 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。*
|
||||
|
||||
|
|
|
|||
|
|
@ -21,12 +21,11 @@ ln -sf <path/to/dataset> <path/to/paddle_ocr>/train_data/dataset
|
|||
* 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。
|
||||
|
||||
- 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。
|
||||
|
||||
* 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 "
|
||||
|
|
@ -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
|
||||
# 测试集标签
|
||||
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：
|
||||
|
||||
```
|
||||
|-train_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
|
|||
|
||||
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 |
|
||||
|
|
|
|||
|
|
@ -17,7 +17,7 @@ import cv2
|
|||
import numpy as np
|
||||
import json
|
||||
import sys
|
||||
from ppocr.utils.utility import initial_logger
|
||||
from ppocr.utils.utility import initial_logger, check_and_read_gif
|
||||
logger = initial_logger()
|
||||
|
||||
from .data_augment import AugmentData
|
||||
|
|
@ -100,7 +100,9 @@ class DBProcessTrain(object):
|
|||
|
||||
def __call__(self, label_infor):
|
||||
img_path, gt_label = self.convert_label_infor(label_infor)
|
||||
imgvalue = cv2.imread(img_path)
|
||||
imgvalue, flag = check_and_read_gif(img_path)
|
||||
if not flag:
|
||||
imgvalue = cv2.imread(img_path)
|
||||
if imgvalue is None:
|
||||
logger.info("{} does not exist!".format(img_path))
|
||||
return None
|
||||
|
|
|
|||
|
|
@ -233,7 +233,7 @@ class SimpleReader(object):
|
|||
img_num = len(label_infor_list)
|
||||
img_id_list = list(range(img_num))
|
||||
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."
|
||||
"num_workers will be 1.")
|
||||
self.num_workers = 1
|
||||
|
|
|
|||
|
|
@ -15,6 +15,8 @@
|
|||
import logging
|
||||
import os
|
||||
import imghdr
|
||||
import cv2
|
||||
from paddle import fluid
|
||||
|
||||
|
||||
def initial_logger():
|
||||
|
|
@ -62,7 +64,7 @@ def get_image_file_list(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))
|
||||
|
||||
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:
|
||||
imgs_lists.append(img_file)
|
||||
elif os.path.isdir(img_file):
|
||||
|
|
@ -75,7 +77,18 @@ def get_image_file_list(img_file):
|
|||
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):
|
||||
|
|
|
|||
|
|
@ -20,7 +20,7 @@ sys.path.append(os.path.join(__dir__, '../..'))
|
|||
import tools.infer.utility as utility
|
||||
from ppocr.utils.utility import 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
|
||||
from ppocr.data.det.east_process import EASTProcessTest
|
||||
from ppocr.data.det.db_process import DBProcessTest
|
||||
|
|
@ -139,7 +139,9 @@ if __name__ == "__main__":
|
|||
if not os.path.exists(draw_img_save):
|
||||
os.makedirs(draw_img_save)
|
||||
for image_file in image_file_list:
|
||||
img = cv2.imread(image_file)
|
||||
img, flag = check_and_read_gif(image_file)
|
||||
if not flag:
|
||||
img = cv2.imread(image_file)
|
||||
if img is None:
|
||||
logger.info("error in loading image:{}".format(image_file))
|
||||
continue
|
||||
|
|
|
|||
|
|
@ -20,7 +20,7 @@ sys.path.append(os.path.abspath(os.path.join(__dir__, '../..')))
|
|||
import tools.infer.utility as utility
|
||||
from ppocr.utils.utility import 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 copy
|
||||
import numpy as np
|
||||
|
|
@ -153,7 +153,9 @@ def main(args):
|
|||
valid_image_file_list = []
|
||||
img_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:
|
||||
logger.info("error in loading image:{}".format(image_file))
|
||||
continue
|
||||
|
|
|
|||
|
|
@ -27,7 +27,7 @@ import copy
|
|||
import numpy as np
|
||||
import math
|
||||
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 tools.infer.utility import draw_ocr
|
||||
from tools.infer.utility import draw_ocr_box_txt
|
||||
|
|
@ -49,18 +49,23 @@ class TextSystem(object):
|
|||
points[:, 0] = points[:, 0] - left
|
||||
points[:, 1] = points[:, 1] - top
|
||||
'''
|
||||
img_crop_width = int(max(np.linalg.norm(points[0] - points[1]),
|
||||
np.linalg.norm(points[2] - points[3])))
|
||||
img_crop_height = int(max(np.linalg.norm(points[0] - points[3]),
|
||||
np.linalg.norm(points[1] - points[2])))
|
||||
pts_std = np.float32([[0, 0],
|
||||
[img_crop_width, 0],
|
||||
img_crop_width = int(
|
||||
max(
|
||||
np.linalg.norm(points[0] - points[1]),
|
||||
np.linalg.norm(points[2] - points[3])))
|
||||
img_crop_height = int(
|
||||
max(
|
||||
np.linalg.norm(points[0] - points[3]),
|
||||
np.linalg.norm(points[1] - points[2])))
|
||||
pts_std = np.float32([[0, 0], [img_crop_width, 0],
|
||||
[img_crop_width, img_crop_height],
|
||||
[0, img_crop_height]])
|
||||
M = cv2.getPerspectiveTransform(points, pts_std)
|
||||
dst_img = cv2.warpPerspective(img, M, (img_crop_width, img_crop_height),
|
||||
borderMode=cv2.BORDER_REPLICATE,
|
||||
flags=cv2.INTER_CUBIC)
|
||||
dst_img = cv2.warpPerspective(
|
||||
img,
|
||||
M, (img_crop_width, img_crop_height),
|
||||
borderMode=cv2.BORDER_REPLICATE,
|
||||
flags=cv2.INTER_CUBIC)
|
||||
dst_img_height, dst_img_width = dst_img.shape[0:2]
|
||||
if dst_img_height * 1.0 / dst_img_width >= 1.5:
|
||||
dst_img = np.rot90(dst_img)
|
||||
|
|
@ -119,25 +124,27 @@ def main(args):
|
|||
is_visualize = True
|
||||
tackle_img_num = 0
|
||||
for image_file in image_file_list:
|
||||
img = cv2.imread(image_file)
|
||||
img, flag = check_and_read_gif(image_file)
|
||||
if not flag:
|
||||
img = cv2.imread(image_file)
|
||||
if img is None:
|
||||
logger.info("error in loading image:{}".format(image_file))
|
||||
continue
|
||||
starttime = time.time()
|
||||
tackle_img_num += 1
|
||||
if not args.use_gpu and args.enable_mkldnn and tackle_img_num % 30 == 0:
|
||||
tackle_img_num += 1
|
||||
if not args.use_gpu and args.enable_mkldnn and tackle_img_num % 30 == 0:
|
||||
text_sys = TextSystem(args)
|
||||
dt_boxes, rec_res = text_sys(img)
|
||||
elapse = time.time() - starttime
|
||||
print("Predict time of %s: %.3fs" % (image_file, elapse))
|
||||
|
||||
drop_score = 0.5
|
||||
dt_num = len(dt_boxes)
|
||||
dt_boxes_final = []
|
||||
for dno in range(dt_num):
|
||||
text, score = rec_res[dno]
|
||||
if score >= 0.5:
|
||||
if score >= drop_score:
|
||||
text_str = "%s, %.3f" % (text, score)
|
||||
print(text_str)
|
||||
dt_boxes_final.append(dt_boxes[dno])
|
||||
|
||||
if is_visualize:
|
||||
image = Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
|
||||
|
|
@ -146,7 +153,12 @@ def main(args):
|
|||
scores = [rec_res[i][1] for i in range(len(rec_res))]
|
||||
|
||||
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/"
|
||||
if not os.path.exists(draw_img_save):
|
||||
os.makedirs(draw_img_save)
|
||||
|
|
|
|||
Loading…
Reference in New Issue