EdgeFace for 🤗 Transformers EdgeFace (Idiap Research Institute) packaged as a transformers custom model. All four published variants live in this single repository as subfolders and are accessible through the standard AutoModel / AutoImageProcessor API with built in MediaPipe face alignment. EdgeFace replaces the classifier of an edgenext (timm) backbone with a 512 d embedding head trained for face recognition. Two variants additionally apply a static low rank factorization to their linear layers — EdgeFace's "gamma" trick, baked into the pretrained weights and unrelated to PEFT adapters. Model variants Subfolder Backbone Low rank ratio Params edgeface base edgenext base — ~18 M default edgeface s gamma 05 edgenext small 0.5 ~5 M edgeface xs gamma 06 edgenext x small 0.6 ~3 M edgeface xxs edgenext xx small — ~1 M Installation Quick start Pipeline (default — edgeface xxs) AutoModel (any variant) Face alignment The image processor detects and aligns the face by default, warping it onto the ArcFace 112×112 template using 5 MediaPipe landmarks — the same alignment the weights were trained with. If detection fails the processor falls back to a plain resize so batches never crash. Media…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy