Create image embeddings easily.
Project description
image-vectors
image-vectors makes extracting embedding vectors from images as simple as possible.
Get Started
Install image-vectors from PyPI:
pip install image-vectors
and start extracting embedding vectors:
from PIL import Image
from image_vectors import ImageEmbedder
embedder = ImageEmbedder(model="vit_base_patch32_clip_224.openai")
image = Image.open(<path_to_image>)
embedding = embedder.embed(image)
Available Embedding Models
CLIP Models
Model | Embedding Dimensions |
---|---|
vit_base_patch32_clip_224.openai |
768 |
vit_base_patch16_clip_224.openai |
768 |
DINO Models
Model | Embedding Dimensions |
---|---|
vit_small_patch14_dinov2.lvd142m |
384 |
SAM Models
Model | Embedding Dimensions |
---|---|
samvit_base_patch16.sa1b |
256 |
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
image_vectors-0.1.1.tar.gz
(127.9 kB
view hashes)
Built Distribution
Close
Hashes for image_vectors-0.1.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 88baf2bd469a41c2c97482cbb46427527ba41d50ea0c7fa467e47bffd05fc2e2 |
|
MD5 | e0afb3b15800ac8937d462d852de90d5 |
|
BLAKE2b-256 | 6c16c20afaf7ac9e6c8af36509648cea94837e960391e767420488c7d72d9011 |