Common functionality for object detection
Project description
detection-utils provides utilities that are common across many object detection projects. This includes things like:
- Box overlap computation (IoU)
- Precision and recall calculations
- Computing targets for training a detector given a set of ground-truth objects and anchor boxes
- Non-maximum suppression
- Coordinate transformation utilities
- Focal loss
All the functions here are well-tested to ensure proper functionality and are used in real projects, so are intended to be enterprise-grade. This repository is meant to ensure that modifications and improvements that are implemented in one object detection project migrate to other projects as appropriate, to reduce code duplication, and to enable a quicker start to working on object detection.
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
detection-utils-1.0.0.tar.gz
(24.2 kB
view details)
File details
Details for the file detection-utils-1.0.0.tar.gz
.
File metadata
- Download URL: detection-utils-1.0.0.tar.gz
- Upload date:
- Size: 24.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/1.13.0 pkginfo/1.5.0.1 requests/2.21.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.7.3
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | bb63290ec1f84aa0b0e0db51c5d8493e48aa04a6c3664627b840f383d76b3807 |
|
MD5 | 96db03b0fec97fa372a15cf7256a853f |
|
BLAKE2b-256 | d4c20c2de88e547dedd4cf39bf6c6f8d108953dfa8df54620b78ff7f30dc677d |