| title: Which Image Models Are Best | |
| emoji: 💻 | |
| colorFrom: gray | |
| colorTo: red | |
| sdk: gradio | |
| sdk_version: 5.29.1 | |
| app_file: app.py | |
| pinned: false | |
| license: apache-2.0 | |
| short_description: Alternative to the timm leaderboard | |
| # Image Model Performance Analysis | |
| This interactive tool analyzes and visualizes performance metrics of different image models based on benchmark data from the pytorch-image-models repository. | |
| ## Features | |
| - Select from various benchmark files | |
| - Choose different metrics for X and Y axes | |
| - Filter by model families | |
| - Toggle log scales | |
| - Interactive Plotly visualizations | |
| ## Data Source | |
| The benchmark data comes from the [pytorch-image-models](https://github.com/huggingface/pytorch-image-models) repository by Ross Wightman. | |
| Based on the original notebook by Jeremy Howard. | |
| ## About | |
| Read more about the project on my blog [dronelab.dev](https://dronelab.dev). | |