最近发现了一个挺厉害的人工智能学习网站,内容通俗易懂,风趣幽默,感兴趣的可以点击此链接进行查看:床长人工智能教程
废话不多说,请看正文!
一、下载CHINESE-OCR
该项目github地址:GitHub - xiaofengShi/CHINESE-OCR: [python3.6] 运用tf实现自然场景文字检测,keras/pytorch实现ctpn+crnn+ctc实现不定长场景文字OCR识别
或者gitee地址:
CHINESE-OCR: [python3.6] 运用tf实现自然场景文字检测,keras/pytorch实现ctpn+crnn+ctc实现不定长场景文字OCR识别
二、配置环境
1、需要安装几个库
sudo apt install graphviz
pip3 install graphviz
pip3 install pydot
pip3 install torchvision
pip3 install torch torchvision
pip3 install torch utils
2、运行sh脚本.
./CHINESE-OCR/setup.sh
./CHINESE-OCR/ctpn/lib/utils/make.sh
在终端进入文件夹分别执行:
sh setup.sh
sh make.sh
3、下载checkpoints
下载文件.checkpoints 的存放地址需要与 CHINESE-OCR-maser\ctpn\ctpn\model.py
中的地址对应.
4、下载modelAngle.h5( modelAngle.h5_免费高速下载|百度网盘-分享无限制 )
modelAngle.h5的存放地址需要与CHINESE-OCR-master\angle\predict.py中的地址对应。
5、更改信息
- 需要将CHINESE-OCR-master\angle\predict.py文件中/Users/xiaofeng/Code/Github/dataset/CHINESE_OCR/angle/modelAngle.h5改成你存放modelAngle.h5的绝对路径
- 需要将CHINESE-OCR-master\ctpn\ctpn\model.py文件中/Users/xiaofeng/Code/Github/dataset/CHINESE_OCR/ctpn/ctpn_checkpoints/ 改成你存放checkpoints的绝对路径.
- 其他文件中还有类似的路径错误都需要更改.
6、下载ocr0.2.h5
( https://github.com/jiangxiluning/chinese-ocr/blob/master/ocr/ocr0.2.h5 ),放到./CHINESE-OCR/ocr/路径下
7、安装tensorflow
因为我前面安装了cuda9.0 ,torch, nvidia-384,安装tensorflow-gpu-1.12.3后,程序运行不成功.各种包之间的配置不相符.所以我就卸载了cuda9.0,重新安装.
根据网址 https://www.tensorflow.org/install/gpu#install_cuda_with_apt
终端输入以下十条命令重新安装cuda9.0和相关配置:
sudo apt-key adv --fetch-keys http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64/7fa2af80.pub
wget http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64/cuda-repo-ubuntu1604_9.1.85-1_amd64.deb
sudo apt install ./cuda-repo-ubuntu1604_9.1.85-1_amd64.deb
wget http://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1604/x86_64/nvidia-machine-learning-repo-ubuntu1604_1.0.0-1_amd64.deb
sudo apt install ./nvidia-machine-learning-repo-ubuntu1604_1.0.0-1_amd64.deb
sudo apt update
sudo apt install cuda9.0 cuda-cublas-9-0 cuda-cufft-9-0 cuda-curand-9-0 \
cuda-cusolver-9-0 cuda-cusparse-9-0 libcudnn7=7.2.1.38-1+cuda9.0 \
libnccl2=2.2.13-1+cuda9.0 cuda-command-line-tools-9-0
sudo apt update
sudo apt install libnvinfer4=4.1.2-1+cuda9.0
pip3 install tensorflow-gpu==1.12.3
8、 运行时:
提示错误:No module named cv2
pip3 install opencv-python
提示错误:No module named lmdb
pip3 install lmdb
提示错误:No module named mahotas
pip3 install mahotas
三、运行结果展示
原图为
运行后的输出:
自定义的图片:
运行结果: