Skip to main content

A video decoding and model inference package using YOLO, OpenCV, and PyTorch

Project description

crazy-vision

A video decoding and model inference package that utilizes YOLO, OpenCV, and PyTorch. The package provides classes for GPU/CPU video decoding, frame processing (including resizing and letterboxing), and model inference using YOLO with convenient API wrappers.

Features

  • Video Decoding: Supports GPU decoding (NVDEC/CUVID) with a CPU fallback.
  • Frame Processing: Resize and pad frames while preserving aspect ratio.
  • Model Inference: Object tracking with YOLO, including batch processing.
  • Easy Integration: Designed to be modular and extendable.

Installation

pip install crazy-vision

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

crazy_vision-0.1.0.tar.gz (5.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

crazy_vision-0.1.0-py3-none-any.whl (6.1 kB view details)

Uploaded Python 3

File details

Details for the file crazy_vision-0.1.0.tar.gz.

File metadata

  • Download URL: crazy_vision-0.1.0.tar.gz
  • Upload date:
  • Size: 5.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.6

File hashes

Hashes for crazy_vision-0.1.0.tar.gz
Algorithm Hash digest
SHA256 69034094d7faf68826a0d8cdfab833ada1430cf757f264ed8a290b7f006d71e9
MD5 12159faecbf10f1fa217fa31c314e233
BLAKE2b-256 63ddeae99e5d9a6fc89fb6c419fddbecb6d4e6d5e9bb6aaf7654ba24720cc67d

See more details on using hashes here.

File details

Details for the file crazy_vision-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: crazy_vision-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 6.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.6

File hashes

Hashes for crazy_vision-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 aa179a5ef6f3ad112e208bf1bdbe85778436f8b707de61d08aa739a367e5c66a
MD5 f0066d7e7a5d6b67f7fc1deecffe5aba
BLAKE2b-256 e8783eff5d2fe20206da1aaccbc8f49da59768a6a3b0403c0844da24415547be

See more details on using hashes here.

Supported by

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