walleclipse / chineseaddress_ocr Goto Github PK
View Code? Open in Web Editor NEWPhotographing Chinese-Address OCR implemented using CTPN+CTC+Address Correction. 拍照文档中文地址文字识别。
Photographing Chinese-Address OCR implemented using CTPN+CTC+Address Correction. 拍照文档中文地址文字识别。
打扰下,没有太搞懂给的cpu链接示例;跟着如下描述修改:
To use cpu only, I follow the author's instruction and make the following modifications:
(1) Set "USE_GPU_NMS " in the file ./ctpn/text.yml as "False"
(2) Set the "__C.USE_GPU_NMS" in the file ./lib/fast_rcnn/config.py as "False";
(3) Comment out the line "from lib.utils.gpu_nms import gpu_nms" in the file ./lib/fast_rcnn/nms_wrapper.py;
(4) To rebuild the setup.py:
最后的setup.py步骤应该与本项目应该无关;
在修改上面三个参数后运行 demo_final.py,在读取Vggnet_fast_rcnn_iter_86000;显示未找到/data/share/chinese_ocr/ctpn/checkpoints。
老师可能借用这个为baseline启动一个项目,目前因为设备问题,只有虚拟机没法用显卡。而对方近期需要演示一下demo。
你好 请教几个问题
1.请问检测那块的数据集是重新用具体所需图像标注训练还是直接用ctpn作者提供的数据voc啊
2.看项目介绍像是商户的证件,请问检测之前是对原图做个区域选择 还是直接全部检测啊,因为看到你最终只是检测公司地址这一块或者说预测前是否做了一些预处理呢 。
3.densenet识别那块 也是直接用原作者给出的数据进行训练的吗? 我看你给出了一个全是公司地址的一个测试集
the train data of Grocery don't need convert to wordvec? grocery.train(add_list) the format of add_list is ("adderss","广州...")
可以针对任何地址获悉吗?
你是怎么做到的?
例如,从其他国家学习并推断地址。
很抱歉,如果联系地点错误。
我这边虚拟机上没有GPU,仅能使用CPU进行计算,这个工程只能在GPU的环境下运行吗?如果可以在仅CPU的环境下运行,我需要改哪些文件呢?
博主您好,我是在校一名学生,之前也看了YCG的这个ctpn+densenet+ctc的ocr项目,也自己训练了模型,现在想学习您一样在微信小程序上这样部署,感觉比较炫酷,恕小弟唐突了,不知能否方便加下您的qq或者微信,小弟想跟您学习一下,我的qq是1164757353,微信是wjc953368
VGGnet_fast_rcnn_iter_86000.ckpt 在哪儿可以下载呀?可否提供?
十分感谢!
when i run demo_final,it comes as follows:
This is the metric converter
What would you like to convert ?
You can either convert a measurement, weight or volume
Can you share how to generate the following file? Looking forward to your reply. Thanks very much.
full_address1.csv
so_stupid_smart_adrs_lib_fuck.me.txt
strokes.txt
您好,小程序提示上传失败,请检查网络连接,请问如何解决?谢谢。
大佬你好,我用的照片是ChineseAddress_OCR_Report.pdf里面的截图。我让demo_final.py下面的代码输出结果;
result, image_framed = ocr_whole.model(image)
output_file = os.path.join(result_dir, image_file.split('/')[-1])
Image.fromarray(image_framed).save(output_file)
ret_total = ''
for key in result:
string1 = result[key][1]
# print("predict line text :",string1)
string2 = re.sub("[\s+.!/_,$%^(+"']+|[+——!,。?、~@#¥%……&{}[]+", "", string1)
print('key是什么?',key)
print('内容是什么?')
print(string2)
结果输出的是中文的乱码
key是什么? 1
内容是什么?
蓝供犁蓝脑栗蓝脑具蓝蓝蓝镂具蓝蓝蓝蓝供仗蓝仗仗仗蓝
请问怎么回事?我应该怎么办?
window下可以运行吗?会报bbox导入错误的问题
你好,打扰一下,在ctpn模型中,在conv5进行3x3,步长为1的滑窗
。为什么得到的3x3xC的向量?卷积得到不是11C的向量吗?
执行这一步的时候报错:
tensorflow.python.framework.errors_impl.AbortedError: Operation received an exception:Status: 3, message: could not create a reorder primitive descriptor, in file tensorflow/core/kernels/mkl_concat_op.cc:813
[[Node: concatenate_49/concat = _MklConcatV2[N=2, T=DT_FLOAT, Tidx=DT_INT32, _kernel="MklOp", _device="/job:localhost/replica:0/task:0/device:CPU:0"](conv2d_55/convolution, conv2d_56/BiasAdd, concatenate_49/concat/axis, conv2d_55/convolution:2, conv2d_56/BiasAdd:2, DMT/_10)]]
basemodel.load_weights(modelPath) 这一步没问题,在预测的时候报错了,请问这个是什么原因啊
谢谢
/ctpn/lib/utils/init.py里的
from . import bbox
from . import cython_nms
总是报错,搜索不到bbox和cython_nms。。。网上搜了好多都没能解决
运行demo_final.py需要编译什么c文件吗
python所需要的依赖包能发一下吗
请问是python3版本的吗?我运行的时候出现下面问题。
File "demo_final.py", line 10, in
from tgrocery import Grocery
File "/root/anaconda3/lib/python3.6/site-packages/tgrocery/init.py", line 1, in
from converter import *
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.