Model Visualizer
Project description
NRTK EXPLORER
NRTK Explorer is a web application for exploring image datasets. It provides insights of a image dataset in COCO format and it evaluate image transformation and perturbation resilience of object recognition DL models. It is built using trame by the kitware team.
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.
Installing
Install it from pypi:
pip install nrtk_explorer
Or, download and install it manually with:
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.
Contribute to NRTK_EXPLORER
Run tests with:
pytest
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
nrtk_explorer-0.0.5.tar.gz
(4.8 MB
view hashes)
Built Distribution
Close
Hashes for nrtk_explorer-0.0.5-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 06f7bad6f5682cb4ea8ab0d964059931b01c4eea6d3cd1f00fca433dba25cd47 |
|
MD5 | ae2f229b35a37c6c48bac7a2047757e5 |
|
BLAKE2b-256 | 8f79371153844b68820bf06781db0431ebf4aa563c9039dfc8331cd7d1f94e16 |