Skip to main content

This lib is about a simple add-on over CLIP by OpenAI for Unsupervised Object Detection (Zeroshot). You can search bounding boxes of objects using NATURAL LANGUAGE UNDERSTANDING - no classes, only text.

Project description

[CLIP ODS] CLIP Object Detection & Segmentation

This repo is about a simple add-on over CLIP by OpenAI for Unsupervised Object Detection (Zeroshot). You can search bounding boxes and some regions of objects using NATURAL LANGUAGE UNDERSTANDING - no classes, only text.

Open In Colab

INSTALLING

pip install clip_ods

Minimal Examples

  • ClipDetectionV0: Open In Colab
  • ClipDetectionV1 (with simple segmentation): Open In Colab

V0:

Authors:

Supported by:

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

clip_ods-0.0.1rc2.tar.gz (1.4 MB view details)

Uploaded Source

Built Distribution

clip_ods-0.0.1rc2-py3-none-any.whl (1.5 MB view details)

Uploaded Python 3

File details

Details for the file clip_ods-0.0.1rc2.tar.gz.

File metadata

  • Download URL: clip_ods-0.0.1rc2.tar.gz
  • Upload date:
  • Size: 1.4 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.1 importlib_metadata/3.10.0 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.60.0 CPython/3.8.5

File hashes

Hashes for clip_ods-0.0.1rc2.tar.gz
Algorithm Hash digest
SHA256 2782275c87700f4901c37e6c0c83f719835624b920543637091306bd4f03d995
MD5 d4589cb3cf9ff6aedc1a97c706362f25
BLAKE2b-256 1dae066e9833f60c76c8ed6ba4ace37c8309d6608364ddba69251937ebee5540

See more details on using hashes here.

File details

Details for the file clip_ods-0.0.1rc2-py3-none-any.whl.

File metadata

  • Download URL: clip_ods-0.0.1rc2-py3-none-any.whl
  • Upload date:
  • Size: 1.5 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.1 importlib_metadata/3.10.0 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.60.0 CPython/3.8.5

File hashes

Hashes for clip_ods-0.0.1rc2-py3-none-any.whl
Algorithm Hash digest
SHA256 bd69b9106b340839d4cf4c9e5c4e3ec7aada266e00d46b060241ce5bc07fd335
MD5 7c0b89c7313bc949f8f3a6e67a1bcad5
BLAKE2b-256 3189076b5dcffcee07dfc8161562251544f48ce06a1f86593e277cbfb30011a4

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