Skip to main content

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


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 details)

Uploaded Source

Built Distribution

image_vectors-0.1.1-py3-none-any.whl (2.1 kB view details)

Uploaded Python 3

File details

Details for the file image_vectors-0.1.1.tar.gz.

File metadata

  • Download URL: image_vectors-0.1.1.tar.gz
  • Upload date:
  • Size: 127.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: pdm/2.12.3 CPython/3.12.2

File hashes

Hashes for image_vectors-0.1.1.tar.gz
Algorithm Hash digest
SHA256 9f69c0085844748d21c48e22c097af712a9cf385da92441d2a2c2b9e19d1b444
MD5 03a8a1887b073ad49d3563d3693a7220
BLAKE2b-256 195b0758d756bc1df506c8593c8beecc5da5dffc740df358f13c3fd497702b56

See more details on using hashes here.

File details

Details for the file image_vectors-0.1.1-py3-none-any.whl.

File metadata

File hashes

Hashes for image_vectors-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 88baf2bd469a41c2c97482cbb46427527ba41d50ea0c7fa467e47bffd05fc2e2
MD5 e0afb3b15800ac8937d462d852de90d5
BLAKE2b-256 6c16c20afaf7ac9e6c8af36509648cea94837e960391e767420488c7d72d9011

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page