Skip to main content

ONNX-based OCR (PP-OCRv5) inference pipeline with DirectML support.

Project description

这是 https://github.com/jingsongliujing/OnnxOCR 的fork

  • 发布了到PIP上
  • 支持dml
  • 仅依赖无版本限制的 pyclipper, shapely, pillow
  • onnx可以根据自己需要安装cpu, gpu或directml
  • 仅打包了"models/ppocrv5/det/det.onnx" "models/ppocrv5/rec/rec.onnx", 没有cls模型
pip install onnxocr-ppocrv5
pip install onnxocr-ppocrv4
# 新增use_dml
model = ONNXPaddleOcr(use_angle_cls=False, use_gpu=False, use_dml=True)

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

onnxocr_ppocrv4-0.0.5.tar.gz (14.4 MB view details)

Uploaded Source

Built Distribution

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

onnxocr_ppocrv4-0.0.5-py3-none-any.whl (14.4 MB view details)

Uploaded Python 3

File details

Details for the file onnxocr_ppocrv4-0.0.5.tar.gz.

File metadata

  • Download URL: onnxocr_ppocrv4-0.0.5.tar.gz
  • Upload date:
  • Size: 14.4 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for onnxocr_ppocrv4-0.0.5.tar.gz
Algorithm Hash digest
SHA256 003b8c53556ea08680805984f7f6b33f323b842d7fa7e3681510002196dafd31
MD5 ee22f26c95c1f2c6f028af3ee1f78e01
BLAKE2b-256 5807cb4bb51db2698db9663ac4c2cb2b1dd7430e2ca1a64c9e82b352146ddd6d

See more details on using hashes here.

File details

Details for the file onnxocr_ppocrv4-0.0.5-py3-none-any.whl.

File metadata

File hashes

Hashes for onnxocr_ppocrv4-0.0.5-py3-none-any.whl
Algorithm Hash digest
SHA256 c7c85e7bed54bba8e846f30a75885e439bd0184a776009a055d95ded74a59dac
MD5 edec0c3d3d5025b2524eea1a9fb390d0
BLAKE2b-256 1d2692a01534f182577e87226637df0ee42c8442c9fdfc41b81ebb1caabf54d6

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