zhubenfu / License-Plate-Detect-Recognition-via-Deep-Neural-Networks-accuracy-up-to-99.9

works in real-time with detection and recognition accuracy up to 99.8% for Chinese license plates: 100 ms/plate
1.38k stars 326 forks source link

请问源代码的入口在哪个文件,我想改成linux版本 #11

Open beizhengren opened 6 years ago

beizhengren commented 6 years ago

作者您好,请问源代码的入口在哪个文件,我想改成linux版本,感觉文件有点多,cmake也不是很熟悉,所以直接问您了,请求帮助,谢谢!

zhubenfu commented 6 years ago

License-Plate-Detect-Recognition-via-Deep-Neural-Networks-accuracy-up-to-99.9/src/ocr_test/ocr_test.cpp

zhubenfu commented 6 years ago

int main(int argc, char *argv) {
const char
keys = { "{help h usage | | show help message}" "{recogmodel rm | lstm_ctc | harr_cnn or lstm_ctc}" };

CommandLineParser parser(argc, argv, keys);
string recogmodel = parser.get<string>("recogmodel"); 
return recogmodel == "lstm_ctc" ? main_mtcnn_lstm_ctc(argc, argv) : main_mtcnn_haar(argc, argv);

}

root1369 commented 6 years ago

Hi, thanks for sharing your project with us. I beleive lot of people is being beneifited from this repository. Now, I've been trying to run on a Linux Distribution. My environment and dependencies details is as follows: OS: Ubuntu 16.04 LTS CUDA: 9.2 CuDNN: 7.3.0 Caffe: 1.0.0 OpenCV: 3.4.0 Boost: 1.58 protobuf: 3.0.0 While running ./ocr_test, I'm receiving this error:

"terminate called after throwing an instance of 'boost::filesystem::filesystem_error' what(): boost::filesystem::directory_iterator::construct: No such file or directory Aborted (core dumped)"

I'm stuck here, got no idea where to dig in and solve this error. Appreciate your help. screenshot from 2018-10-17 15-27-34

Jimjipeng commented 5 years ago

-lboost_system -lboost_filesystem

moni123456 commented 5 years ago

@magiccreator69 能否给份你在Linux编译的代码

root1369 commented 5 years ago

@moni123456 Didn't work in this project for a while. The owner of this repo has made some changes to the project. Now, I'll give it a try and see if it's working here on my environment then will share as much as I can.

root1369 commented 5 years ago

@Jimjipeng I'm not sure yet what to do with libboost_system and libboost_filesystem. Any suggestions?

beizhengren commented 5 years ago

int main(int argc, char *argv) { const char keys = { "{help h usage | | show help message}" "{recogmodel rm | lstm_ctc | harr_cnn or lstm_ctc}" };

CommandLineParser parser(argc, argv, keys);
string recogmodel = parser.get<string>("recogmodel"); 
return recogmodel == "lstm_ctc" ? main_mtcnn_lstm_ctc(argc, argv) : main_mtcnn_haar(argc, argv);

}

谢谢作者。我建议您可以写一个关于如何用该项目检测和训练的比较详细的流程。感觉您的readme看起来比较吃力。再次感谢!

dreambander commented 5 years ago

@moni123456 Didn't work in this project for a while. The owner of this repo has made some changes to the project. Now, I'll give it a try and see if it's working here on my environment then will share as much as I can.

@magiccreator69 麻烦请教下linux编译问题 ,希望得到答复 qq 1171462284 谢谢