clip-ods

Pre-release

This release is a pre-release and may not be stable for production use.

[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.

INSTALLING

pip install clip_ods

Minimal Examples

ClipDetectionV0:
ClipDetectionV1 (with simple segmentation):

V0:

Authors:

Supported by:

OCRV
RZD

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 Apr 16, 2021 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

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

Uploaded Apr 16, 2021 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: Apr 16, 2021
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: Apr 16, 2021
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`