Zum Inhalt springen
ModelAufgelistetExtern
Herunterladen

Swin T Food101

Raw training checkpoint exported from this repository:

ArtOtherVersionVersion 1CBewertung

Modellquelle

Art
Other
Dateigröße
317 MB
Version
vVersion 1
Aktualisiert
22. Okt. 2026
Quelle
Hugging Face

Quellenbeschreibung

Swin-T on Food-101

Raw training checkpoint exported from this repository: https://github.com/mnjm/vit

Files

  • Swin-T-food101.pt: raw checkpoint from this training run
  • config/: Hydra config snapshot saved with the run

Checkpoint

  • Path: Swin-T-food101.pt
  • Dataset: food101
  • Model: Swin-T

Metrics

SplitLossAcc@1Acc@5
Train0.013999.63%99.97%
Val1.699669.97%88.88%

Usage

This is a raw checkpoint dump. To use it check here

Quellen

1 Quelle
Hugging FacePrimärVersion 6878b3a76ce62b3089152f92ceb3de0be6b98dc2
huggingface.co/mnjm/swin-t-food101/tree/6878b3a76ce62b3089152f92ceb3de0be6b98dc2

Verifiziert 22. Okt.

Modellartefakte

1 Artefakt

Swin-T-food101.pt

pt · 317 MB · SHA-256 a37052c697b0…05d3 · Hugging Face

Herunterladen

Quellenauszüge

2 Auszüge

--- library_name: pytorch pipeline_tag: image-classification datasets: - food101 tags: - food101 - image-classification - vision-transformer - swin-transformer license: mit --- # Swin-T on Food-101 Raw training checkpoint exported from this repository: https://github.com/mnjm/vit ## Files - `Swin-T-food101.pt`: raw checkpoint from this training run - `config/`: Hydra config snapshot saved with the run ## Checkpoint - Path: `Swin-T-food101.pt` - Dataset: `food101` - Model: `Swin-T` ## Metrics | Split | Loss | Acc@1 | Acc@5 | | --- | ---: | ---: | ---: | | Train | `0.0139` | `99.63%` | `99.97%` | | Val | `1.6996` | `69.97%` | `88.88%` | ## Usage This is a raw checkpoint dump. To use it check [here](https://github.com/mnjm/vit/compute_acc.py)

Source context: 0 downloads · 0 likes · Pipeline image-classification · Library pytorch · Repo mnjm/swin-t-food101