Tiny and Efficient Model for the Edge Detection Generalization logo

Tiny and Efficient Model for the Edge Detection Generalization

Operations such as edge detection, image enhancement, and super-resolution, provide the foundations for higher level image analysis.

GitHub Link

The GitHub link is https://github.com/xavysp/teed

Introduce

The TEED (Tiny and Efficient Edge Detector) is a lightweight convolutional neural network designed for edge detection. It has only 58K parameters, significantly fewer than state-of-the-art models, making it highly efficient. Training on the BIPED dataset is quick, with each epoch taking less than 5 minutes, and the model converges rapidly. The resulting edge maps are of high quality. The paper detailing TEED's capabilities has been accepted by ICCV 2023-Workshop RCV. The code and dataset are available on GitHub, and the UDED dataset is also accessible for edge detection. If using TEED or its dataset in academic work, appropriate citation is recommended.

Content

Copy and paste your images into data/ folder, and: Set the following lines in main.py: Check the configurations of the datasets in dataset.py Here the link to access the UDED dataset for edge detection If you like TEED, why not starring the project on GitHub! Please cite our Dataset if you find helpful in your academic/scientific publication...

Alternatives & Similar Tools

LongLLaMA-handle very long text contexts, up to 256,000 tokens logo

LongLLaMA is a large language model designed to handle very long text contexts, up to 256,000 tokens. It's based on OpenLLaMA and uses a technique called Focused Transformer (FoT) for training. The repository provides a smaller 3B version of LongLLaMA for free use. It can also be used as a replacement for LLaMA models with shorter contexts.