opencv/edge_detection_dexined
By opencv · ↓ 0 · ♥ 2 · Updated 2025-06-20
What's in this repo
This page lists the files in opencv/edge_detection_dexined, including edge_detection_dexined_2024sep.onnx.
- 1 ONNX models (.onnx files)
- 11 files, including 2 .py, 2 .jpg, 1 .txt, 1 .md, 1 .cpp, 1 .onnx
- Last updated 2025-06-20
ONNX files
| File | Size | Download |
|---|---|---|
| edge_detection_dexined_2024sep.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
DexiNed
DexiNed is a Convolutional Neural Network (CNN) architecture for edge detection.
Notes:
- Model source: ONNX.
- Model source: .pth.
- This ONNX model has fixed input shape, but OpenCV DNN infers on the exact shape of input image. See https://github.com/opencv/opencv_zoo/issues/44 for more information.
Requirements
Install latest OpenCV >=5.0.0 and CMake >= 3.22.2 to get started with.
Demo
Python
Run the following command to try the demo:
# detect on camera input
python demo.py
# detect on an image
python demo.py --input /path/to/image
# get help regarding various parameters
python demo.py --help
C++
# A typical and default installation path of OpenCV is /usr/local
cmake -B build -D OPENCV_INSTALLATION_PATH=/path/to/opencv/installation .
cmake --build build
# detect on camera input
./build/demo
# detect on an image
./build/demo --input=/path/to/image
# get help messages
./build/demo -h
Example outputs
License
All files in this directory are licensed under MIT License.
Reference
- https://github.com/xavysp/DexiNed
Files (11)
Related models
More from opencv
More models
No task type declared.