imagenette160

# Imagenette 160 (LibreYOLO) A LibreYOLO-hosted copy of **Imagenette** — 10 easily-classified ImageNet classes at 160 px — for classification training, validation, and benchmarking. ## Provenance Rebuilt from the canonical upstream, **not** from any third-party repackaging: - Source: `https://s3.amazonaws.com/fast-ai-imageclas/imagenette2-160.tgz` (fast.ai, **Apache-2.0**) - Source `sha256`: `64d0c4859f35a461889e0147755a999a48b49bf38a7e0f9bd27003f10db02fe5` - Transform: extracted and repackaged `.tgz` -> `.zip`, preserving the original `train/val/<wordnet_id>` ImageFolder layout. No relabeling, no third-party assets. ## Contents `imagenette160.zip` — ImageFolder layout: - `train/<wnid>/*.JPEG` — 9,469 images - `val/<wnid>/*.JPEG` — 3,925 images 10 classes (folders are WordNet IDs): - `n01440764` — tench - `n02102040` — English springer - `n02979186` — cassette player - `n03000684` — chain saw - `n03028079` — church - `n03394916` — French horn - `n03417042` — garbage truck - `n03425413` — gas pump - `n03445777` — golf ball - `n03888257` — parachute ## Use with LibreYOLO ```python from libreyolo import LibreYOLO model = LibreYOLO("LibreMobileNetV4s-cls.pt") model.val(data="imagenette160") # auto-downloads this dataset ``` ## License Apache-2.0, inherited from upstream Imagenette (fast.ai).