NRTK EXPLORER
=============
NRTK Explorer is a web application for exploring image datasets. It provides
insights of a image dataset in [COCO][3] format and it evaluate image
transformation and perturbation resilience of object recognition DL models. It
is built using [trame][1] by the [kitware][2] team.
![nrtk explorer](https://raw.githubusercontent.com/Kitware/nrtk-explorer/main/screenshot.png)
Features
--------
- Explore image datasets in COCO format.
- Apply parametrized image degradation (such as blur) to the images.
- Benchmark dataset resilience with a differential PCA|UMAP analysis of the
embeddings of the images and its transformation.
- Evaluate object detection DL models in both the source images and its
transformations.
- When possible it will attempt to utilize the user GPU as much as possible to
speedup its computations.
Usage
----------
Usage example with virtual-env creation
```bash
# Setup python environment
python3 -m venv .venv
source .venv/bin/activate
pip install -U pip
# install application
pip install nrtk-explorer
# get some sample data
git clone https://github.com/vicentebolea/nrtk_explorer_datasets.git
# Run the application on given dataset (908 images)
nrtk-explorer --dataset ./nrtk_explorer_datasets/OIRDS_v1_0/oirds.json
```
![nrtk explorer usage](https://raw.githubusercontent.com/Kitware/nrtk-explorer/main/usage.png)
Installing
----------
Install it from pypi:
```bash
pip install nrtk-explorer
```
Or, download and install it manually with:
```bash
curl -OL https://github.com/Kitware/nrtk-explorer/archive/refs/heads/main.zip
```
Inside the application source code top directory, install it with:
```
pip install -e .
```
Run the application:
```
nrtk-explorer
```
CLI flags and options
---------------------
- `-h|--help` show the help for the command line options, it inherit trame
command line options and flags.
- `--dataset` specify the directory containing a json file describing a COCO
image dataset. You can specify multiple directory using a comma `,` as a
separator. Example usage: `nrtk_explorer --dataset <dataset dir>`. More
images datasets available at:
https://github.com/vicentebolea/nrtk_explorer_datasets/
Contribute to NRTK_EXPLORER
---------------------------
Run tests with:
```bash
pytest
```
[1]: https://trame.readthedocs.io/en/latest/
[2]: https://www.kitware.com/
[3]: https://cocodataset.org/
Raw data
{
"_id": null,
"home_page": null,
"name": "nrtk-explorer",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": "Application, Framework, Interactive, Python, Web",
"author": null,
"author_email": "Alessandro Genova <alessandro.genova@kitware.com>, Vicente Adolfo Bolea Sanchez <vicente.bolea@kitware.com>",
"download_url": "https://files.pythonhosted.org/packages/fa/d3/92ce1a0ed5a713477c0113c6bf61b1917ad0d1b109e873a19fb35cd2c9aa/nrtk_explorer-0.1.2.tar.gz",
"platform": null,
"description": "NRTK EXPLORER\n=============\n\nNRTK Explorer is a web application for exploring image datasets. It provides\ninsights of a image dataset in [COCO][3] format and it evaluate image\ntransformation and perturbation resilience of object recognition DL models. It\nis built using [trame][1] by the [kitware][2] team.\n\n![nrtk explorer](https://raw.githubusercontent.com/Kitware/nrtk-explorer/main/screenshot.png)\n\nFeatures\n--------\n\n- Explore image datasets in COCO format.\n- Apply parametrized image degradation (such as blur) to the images.\n- Benchmark dataset resilience with a differential PCA|UMAP analysis of the\n embeddings of the images and its transformation.\n- Evaluate object detection DL models in both the source images and its\n transformations.\n- When possible it will attempt to utilize the user GPU as much as possible to\n speedup its computations.\n\nUsage\n----------\n\nUsage example with virtual-env creation\n\n```bash\n# Setup python environment\npython3 -m venv .venv\nsource .venv/bin/activate\npip install -U pip\n\n# install application\npip install nrtk-explorer\n\n# get some sample data\ngit clone https://github.com/vicentebolea/nrtk_explorer_datasets.git\n\n# Run the application on given dataset (908 images)\nnrtk-explorer --dataset ./nrtk_explorer_datasets/OIRDS_v1_0/oirds.json\n```\n\n![nrtk explorer usage](https://raw.githubusercontent.com/Kitware/nrtk-explorer/main/usage.png)\n\nInstalling\n----------\n\nInstall it from pypi:\n\n```bash\npip install nrtk-explorer\n```\n\nOr, download and install it manually with:\n\n```bash\ncurl -OL https://github.com/Kitware/nrtk-explorer/archive/refs/heads/main.zip\n```\n\nInside the application source code top directory, install it with:\n\n```\npip install -e .\n```\n\nRun the application:\n\n```\nnrtk-explorer\n```\n\nCLI flags and options\n---------------------\n\n- `-h|--help` show the help for the command line options, it inherit trame\n command line options and flags.\n- `--dataset` specify the directory containing a json file describing a COCO\n image dataset. You can specify multiple directory using a comma `,` as a\n separator. Example usage: `nrtk_explorer --dataset <dataset dir>`. More\n images datasets available at:\n https://github.com/vicentebolea/nrtk_explorer_datasets/\n\nContribute to NRTK_EXPLORER\n---------------------------\n\nRun tests with:\n\n```bash\npytest\n```\n\n[1]: https://trame.readthedocs.io/en/latest/\n[2]: https://www.kitware.com/\n[3]: https://cocodataset.org/\n",
"bugtrack_url": null,
"license": null,
"summary": "Model Visualizer",
"version": "0.1.2",
"project_urls": null,
"split_keywords": [
"application",
" framework",
" interactive",
" python",
" web"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "d55b8f2d0f9e2f4c4e50108e7a29edceb0d75cbe6078ac7c101584dbf3705630",
"md5": "c2248c3442f828a3de746d2ce2447c30",
"sha256": "b3c8db99e5fe2745fa25e26a6939d3c370558ace94b7171749d465b9a521a29a"
},
"downloads": -1,
"filename": "nrtk_explorer-0.1.2-py2.py3-none-any.whl",
"has_sig": false,
"md5_digest": "c2248c3442f828a3de746d2ce2447c30",
"packagetype": "bdist_wheel",
"python_version": "py2.py3",
"requires_python": null,
"size": 3008059,
"upload_time": "2024-04-19T23:44:54",
"upload_time_iso_8601": "2024-04-19T23:44:54.750775Z",
"url": "https://files.pythonhosted.org/packages/d5/5b/8f2d0f9e2f4c4e50108e7a29edceb0d75cbe6078ac7c101584dbf3705630/nrtk_explorer-0.1.2-py2.py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "fad392ce1a0ed5a713477c0113c6bf61b1917ad0d1b109e873a19fb35cd2c9aa",
"md5": "4db4aa70701e31b09cdacb141d4fe399",
"sha256": "05a0c81476df66979b4a6fc23814a6b4e8589573115b910aabf667b8fac092ac"
},
"downloads": -1,
"filename": "nrtk_explorer-0.1.2.tar.gz",
"has_sig": false,
"md5_digest": "4db4aa70701e31b09cdacb141d4fe399",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 8094972,
"upload_time": "2024-04-19T23:44:57",
"upload_time_iso_8601": "2024-04-19T23:44:57.040583Z",
"url": "https://files.pythonhosted.org/packages/fa/d3/92ce1a0ed5a713477c0113c6bf61b1917ad0d1b109e873a19fb35cd2c9aa/nrtk_explorer-0.1.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-04-19 23:44:57",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "nrtk-explorer"
}