Tomk187

/

MIR-L

like 0

This PR enhances the model card by adding crucial metadata to improve its discoverability and utility on the Hugging Face Hub:

• pipeline_tag: image-to-image: The model performs various image restoration tasks (deraining, dehazing, denoising), which fall under the image-to-image pipeline category. This will ensure the model appears in relevant task filters.
• library_name: pytorch: The GitHub repository explicitly states it's a "PyTorch implementation" and provides PyTorch-based training and testing scripts. Adding this tag enables an automated PyTorch usage snippet on the Hub, making it easier for users to get started.
• tags: Specific tags such as image-restoration, deraining, dehazing, and denoising have been added. These reflect the core functionalities of the MIR-L model as described in the paper abstract, further improving searchability for specific image degradation tasks.

The existing arXiv paper link has been retained as per instructions, and no sample usage code has been added since it wasn't present in the original GitHub README.