Segment Anything High Quality (SAM HQ) model for use with Autodistill
Project description
Autodistill Segment Anything HQ Module
This repository contains the code supporting the Segment Anything base model for use with Autodistill.
SAM HQ is a zero-shot segmentation model capable of producing detailed masks, developed by ETH VIS. SAM HQ can segment an entire image into masks, or use points to segment specific parts of an object. You can use Segment Anything with Autodistill to segment objects. Segment Anything does not assign classes, so you should use SAM HQ model with a tool like Grounding DINO or GPT-4V.
Read the full Autodistill documentation.
Read the SAM HQ Autodistill documentation.
Installation
To use SAM HQ with autodistill, you need to install the following dependency:
pip3 install autodistill-sam-hq
Quickstart
from autodistill_sam_hq import HQSAM
base_model = HQSAM(None)
masks = base_model.predict("./image.jpeg")
print(masks)
License
This project is licensed under an Apache 2.0 license.
🏆 Contributing
We love your input! Please see the core Autodistill contributing guide to get started. Thank you 🙏 to all our contributors!
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
Built Distribution
File details
Details for the file autodistill-sam-hq-0.1.1.tar.gz
.
File metadata
- Download URL: autodistill-sam-hq-0.1.1.tar.gz
- Upload date:
- Size: 9.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.4
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | afa881dd325e923472f3858c3193217b9c13415a493de7fb76a0d9985a35f83b |
|
MD5 | 45fe7589fbd9ec1c5116018a24161243 |
|
BLAKE2b-256 | 695a42aefd1780f26ae994eca9e3cefff4a7158d977f5de96c1d2db6612f6ba8 |
File details
Details for the file autodistill_sam_hq-0.1.1-py3-none-any.whl
.
File metadata
- Download URL: autodistill_sam_hq-0.1.1-py3-none-any.whl
- Upload date:
- Size: 7.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.4
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 143005c7450087a638ebbcb290815509826e82ec0b498324e5a45b653eec2c5a |
|
MD5 | 638af2b7ac55419cffb68969423f4dbc |
|
BLAKE2b-256 | eeda72c21fb1431467d9326115084ad0ca359540e3925c681f5365b9bc033c2b |