The kwcoco_dataloader module
Project description
A windowed torch dataloader for kwcoco files with support for image sequences, heterogeneous image sensors, arbitrary bands, efficient subimage loading via COGs, pixelwise weighting, balanced sampling, and more.
An independent component ported from the geowatch project.
As of version 0.1.0 it is a port of all features from geowatch needed to make all doctest tests pass without issue. This means that the dependency footprint is slightly larger than it should be, and it will likely shrink over time or have parts (particularly for GIS components) become options.
See Slides 77-86 in the GeoWATCH slide deck.
The geowatch tutorials also make heavy use of this dataloader and is a good referene while this repo is constructed.
Read the Docs |
|
Gitlab (main) |
https://gitlab.kitware.com/computer-vision/kwcoco_dataloader |
Github (mirror) |
|
Pypi |
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
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file kwcoco_dataloader-0.1.2.tar.gz.
File metadata
- Download URL: kwcoco_dataloader-0.1.2.tar.gz
- Upload date:
- Size: 272.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c679c703b08fcc7e673fdff48c3dad9128d8d64efd59cf649a7d2b705f09b582
|
|
| MD5 |
c2dbd92b53d0394c2192c7a6b74aa6be
|
|
| BLAKE2b-256 |
209e90aa76d889798c757aa62b2e38c8c7e0896368579fa7e1852b14bc6d4c82
|
File details
Details for the file kwcoco_dataloader-0.1.2-py3-none-any.whl.
File metadata
- Download URL: kwcoco_dataloader-0.1.2-py3-none-any.whl
- Upload date:
- Size: 275.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
6cf7e2d92d1e37c4cabc2375470c605aadd5fda939964ca8903ee42ccd1bf9d9
|
|
| MD5 |
c8616ee1e538418b85944fe68e6451df
|
|
| BLAKE2b-256 |
68d0e4f12247805c7578c6fa762b6ea23e1344678d9cd7404a3f5d5edae4affd
|