Loading
¿Tienes un flujo de trabajo de ComfyUI? Obtén un Workflow Doc legible en tu navegador.Haz legible un flujo de trabajo.Pruébalo ahora ↗
Foundation model for biology organismal images. It is trained on TreeOfLife-200M on the basis of a CLIP model (ViT-14/L) pre-trained on LAION-2B. BioCLIP 2 yields state-of-the-art performance in recognizing various...
Fuente del modelo
Descripción de la fuente
Foundation model for biology organismal images. It is trained on TreeOfLife-200M on the basis of a CLIP model (ViT-14/L) pre-trained on LAION-2B. BioCLIP 2 yields state-of-the-art performance in recognizing various species. More importantly, it demonstrates emergent properties beyond species classification after extensive hierarchical contrastive training.
Fuentes
1 fuenteVerificado 17 sept
Artefactos del modelo
1 artefactoopen_clip_model.safetensors
safetensors · 1,59 GB · SHA-256 b7b2bf6fbc95…dfef · Hugging Face
DescargarExtractos de fuentes
2 extractosFoundation model for biology organismal images. It is trained on TreeOfLife-200M on the basis of a CLIP model (ViT-14/L) pre-trained on LAION-2B. BioCLIP 2 yields state-of-the-art performance in recognizing various species. More importantly, it demonstrates emergent properties beyond species classification after extensive hierarchical contrastive training.
Source context: 99952 downloads · 39 likes · Pipeline zero-shot-image-classification · Library open_clip · Repo imageomics/bioclip-2
