| --- |
| library_name: pytorch |
| pipeline_tag: image-classification |
| datasets: |
| - food101 |
| tags: |
| - food101 |
| - image-classification |
| - vision-transformer |
| - vit |
| license: mit |
| --- |
| |
| # ViT-B-16 on Food-101 |
|
|
| Raw training checkpoint exported from this repository: |
| https://github.com/mnjm/vit |
|
|
| ## Files |
|
|
| - `ViT-B-16-food101.pt`: raw checkpoint from this training run |
| - `config/`: Hydra config snapshot saved with the run |
|
|
| ## Checkpoint |
|
|
| - Path: `ViT-B-16-food101.pt` |
| - Dataset: `food101` |
| - Model: `ViT-B/16` |
|
|
| ## Metrics |
|
|
| | Split | Loss | Acc@1 | Acc@5 | |
| | --- | ---: | ---: | ---: | |
| | Train | `0.0227` | `99.41%` | `99.87%` | |
| | Val | `2.5183` | `58.57%` | `81.41%` | |
|
|
| ## Usage |
|
|
| This is a raw checkpoint dump. To use it check [here](https://github.com/mnjm/vit/blob/main/compute_acc.py) |
|
|
