metadata
license: apache-2.0
tags:
- clip
- multimodal
- computer-vision
- nlp
- faiss
- face-recognition
multimodal-face-clip
Multimodal CLIP model fine-tuned for face recognition and retrieval.
Usage
from transformers import CLIPModel, CLIPProcessor
from huggingface_hub import hf_hub_download
import faiss
import json
# Load model
model = CLIPModel.from_pretrained("multimodal-face-clip", subfolder=".")
processor = CLIPProcessor.from_pretrained("multimodal-face-clip", subfolder=".")
# Load embeddings (optional)
text_index_path = hf_hub_download(repo_id="multimodal-face-clip", filename="embeddings/text_index.faiss")
image_index_path = hf_hub_download(repo_id="multimodal-face-clip", filename="embeddings/image_index.faiss")