汀丶人工智能 6fa0bf2433 | 11 months ago | |
---|---|---|
test | 11 months ago | |
train | 11 months ago | |
README.md | 11 months ago | |
demo.py | 11 months ago | |
keras_demo.py | 11 months ago | |
keras_model.py | 11 months ago | |
model.py | 11 months ago | |
pytorch_demo.py | 11 months ago | |
pytorch_model.py | 11 months ago | |
setup-python2-cpu.sh | 11 months ago | |
setup-python3-cpu.sh | 11 months ago | |
setup-python3-gpu.sh | 11 months ago |
Bash
##GPU环境
sh setup-python3-gpu.sh
##CPU python3环境
sh setup-python3-cpu.sh
##额外依赖的安装包
apt install graphviz
pip3 install graphviz
pip3 install pydot
pip3 install torch torchvision
基于图像分类,在VGG16模型的基础上,训练0、90、180、270度检测的分类模型.
详细代码参考angle/predict.py文件,训练图片8000张,准确率88.23%
模型地址[BaiduCloud](链接:https://pan.baidu.com/s/1Sqbnoeh1lCMmtp64XBaK9w 提取码:n2v4)
支持CPU、GPU环境,一键部署,
文本检测训练参考
提供keras 与pytorch版本的训练代码,在理解keras的基础上,可以切换到pytorch版本,此版本更稳定
运行demo.py或者pytorch_demo.py(建议) 写入测试图片的路径即可,如果想要显示ctpn的结果,修改文件./ctpn/ctpn/other.py 的draw_boxes函数的最后部分,cv2.inwrite('dest_path',img),如此,可以得到ctpn检测的文字区域框以及图像的ocr识别结果
parser.add_argument(
'--crnn',
help="path to crnn (to continue training)",
default=预训练权重的路径,看你下载的预训练权重在哪啦)
parser.add_argument(
'--experiment',
help='Where to store samples and models',
default=模型训练的权重保存位置,这个自己指定)
[pytorch预训练权重](链接:https://pan.baidu.com/s/1kAXKudJLqJbEKfGcJUMVtw 提取码:9six)
===========================================================
===========================================================
主要是因为训练的时候,只包含中文和英文字母,因此很多公式结构是识别不出来的
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》