Skip to main content

Standalone cython_bbox

Project description

cython_bbox

cython_bbox is widely used in object detection tasks. To my best knowledge, it was first implemented in Faster-RCNN. Since then, almost all object detection projects use the source code directly.

In order to use it in standalone code snippets or small projects, I make it a pypi module. The cython_bbox.pyx is totally borrowed from Faster-RCNN. Thanks RBG!

install

pip install cython_bbox

usage

from cython_bbox import bbox_overlaps
import numpy as np

gt = np.random.random((5, 4))
dt = np.random.random((10, 4))

overlaps = bbox_overlaps(
        np.ascontiguousarray(dt, dtype=np.float),
        np.ascontiguousarray(gt, dtype=np.float)
    )

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cython_bbox-0.1.5.tar.gz (4.4 kB view details)

Uploaded Source

File details

Details for the file cython_bbox-0.1.5.tar.gz.

File metadata

  • Download URL: cython_bbox-0.1.5.tar.gz
  • Upload date:
  • Size: 4.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.8.10

File hashes

Hashes for cython_bbox-0.1.5.tar.gz
Algorithm Hash digest
SHA256 c73a513e4f668db483e703701707c6d289de61322f8083635111cf8ee3e969a2
MD5 9c7e0f96cafdee79297743c80049045b
BLAKE2b-256 218ffcf24b032c7d501a995e9c8420ac5e601d8fd883dd045522b63b7869cabd

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page