Awesome ritm_annotation created by lucasew
Project description
ritm_annotation
Tool to do dataset annotation for semantic segmentation datasets.
Based on SamsungLabs/ritm_interactive_segmentation
Work in progress
Installation
- Pip
pip install ritm_annotation
- Nix flakes
Running it using Nix flakes
nix run github:lucasew/ritm_annotation -- --help
- Docker
docker run -ti ghcr.io/lucasew/ritm_annotation:latest bash
Usage
$ python -m ritm_annotation --help
# or
$ ritm_annotation --help
Pretrained model weights
Here you can download pretrained weights
In my tests I used coco_lvis_h18_itermask.pth (SHA256 5f69cfce354d1507e3850bfc39ee7057c8dd27b6a4910d1d2dc724916b9ee32b)
Development
Read the CONTRIBUTING.md file.
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
ritm_annotation-0.5.1.tar.gz
(93.6 kB
view details)
Built Distribution
File details
Details for the file ritm_annotation-0.5.1.tar.gz.
File metadata
- Download URL: ritm_annotation-0.5.1.tar.gz
- Upload date:
- Size: 93.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.0.0 CPython/3.12.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | f018f01c3d25fad70ddc88a77f91355663b7ed9a371eeeb5fe5577bc9c69906d |
|
| MD5 | 3665f7f3db20f980977826e1ffe245f5 |
|
| BLAKE2b-256 | 17766044f628f2afd1c199040579ce702f2551bec0d985d3a83dad61bfd0dcc2 |
Provenance
File details
Details for the file ritm_annotation-0.5.1-py3-none-any.whl.
File metadata
- Download URL: ritm_annotation-0.5.1-py3-none-any.whl
- Upload date:
- Size: 156.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.0.0 CPython/3.12.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 732474db1667bd6085a336f8383cc8130e9148bcbdf3a9a0f7c429402b181676 |
|
| MD5 | 2c13ca025f0d240a7f0ed7a09d85d554 |
|
| BLAKE2b-256 | e23875cd3091975f66a2368d0ec0bcc2ec77d4a6ef37a60820adc5952ed0385f |
