Downloads · 30 days
29.2K
6% of all-time downloads
clip-ViT-B-32-vision
Qdrant/clip-ViT-B-32-vision
clip-ViT-B-32-vision is a image classification model from Qdrant. Use it when you need a label for an image. It is set up for transformers. The card lists the license as mit.
ONNX port of sentence-transformers/clip-ViT-B-32.
All-time downloads
498K
Public
Repo size
352 MB
Likes
16
Public
Repo makeup
Click a slice to open those files.
.onnx352 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- mit
- Model type
- clip_vision_model
- Access
- Public
- Created
- Apr 30, 2024
- Updated
- Oct 16, 2024
- SHA
- e0c24ed0
Model card
From the Hugging Face model README
ONNX port of sentence-transformers/clip-ViT-B-32.
This model is intended to be used for image classification and similarity searches.
Usage
Here's an example of performing inference using the model with FastEmbed.
from fastembed import ImageEmbedding
images = [
"./path/to/image1.jpg",
"./path/to/image2.jpg",
]
model = ImageEmbedding(model_name="Qdrant/clip-ViT-B-32-vision")
embeddings = list(model.embed(images))
# [
# array([-0.1115, 0.0097, 0.0052, 0.0195, ...], dtype=float32),
# array([-0.1019, 0.0635, -0.0332, 0.0522, ...], dtype=float32)
# ]
- Task
- Image Classification
- Library
- transformers
- Type
- clip_vision_model
- License
- mit
- Created
- Apr 30, 2024
- Updated
- Oct 16, 2024