Face Parsing Semantic segmentation model fine tuned from nvidia/mit b5 with CelebAMask HQ for face parsing. For additional options, see the Transformers Segformer docs. ONNX model for web inference contributed by Xenova. Usage in Python Exhaustive list of labels can be extracted from config.json. id label note : : : : 0 background 1 skin 2 nose 3 eye g eyeglasses 4 l eye left eye 5 r eye right eye 6 l brow left eyebrow 7 r brow right eyebrow 8 l ear left ear 9 r ear right ear 10 mouth area between lips 11 u lip upper lip 12 l lip lower lip 13 hair 14 hat 15 ear r earring 16 neck l necklace 17 neck 18 cloth clothing Usage in the browser (Transformers.js) p5.js Since p5.js uses an animation loop abstraction, we need to take care loading the model and making predictions. full p5.js example Model Description Developed by: Jonathan Dinu Model type: Transformer based semantic segmentation image model License: non commercial research and educational purposes Resources for more information: Transformers docs on Segformer and/or the original research paper. Limitations and Bias Bias While the capabilities of computer vision models are impressive, they can also reinforce or exacerbate social…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy