| library_name: pytorch | |
| pipeline_tag: image-classification | |
| datasets: | |
| - food101 | |
| tags: | |
| - food101 | |
| - image-classification | |
| - vision-transformer | |
| - mobilevit | |
| license: mit | |
| # MobileViT-XXS on Food-101 | |
| Raw training checkpoint exported from this repository: | |
| https://github.com/mnjm/vit | |
| ## Files | |
| - `MobileViT-XXS-food101.pt`: raw checkpoint from this training run | |
| - `config/`: Hydra config snapshot saved with the run | |
| ## Checkpoint | |
| - Path: `MobileViT-XXS-food101.pt` | |
| - Dataset: `food101` | |
| - Model: `MobileViT-XXS` | |
| ## Metrics | |
| | Split | Loss | Acc@1 | Acc@5 | | |
| | --- | ---: | ---: | ---: | | |
| | Train | `1.2891` | `65.42%` | `87.77%` | | |
| | Val | `1.4212` | `62.42%` | `86.32%` | | |
| ## Usage | |
| This is a raw checkpoint dump. To use it check [here](https://github.com/mnjm/vit/compute_acc.py) | |