Skip to main content

Qualcomm AI Runtime visualization application for AI models and runtime metrics.

Project description

Qualcomm AI Runtime Visualizer

[Docs] [Discord Forums]

Qualcomm AI Runtime Visualizer (QAIRT Visualizer) is a tool to provide visualization for AI models and runtime metrics. This includes:

  • Model visualization: an acyclic graph representation of ML graphs
  • Report/Metrics analysis: performance and accuracy metrics such as optrace, AI accelerator analysis report, layer-wise accuracy, etc.

QAIRT Visualizer can be launched and used through two different ways:

  • CLI: a lightweight wrapper to launch the standalone visualization application
    • Running the CLI without options will open full application
    • Alternatively, the CLI also allows passing models and report files to visualize each in own window
  • Python API: interface for displaying model and report objects

Install

QAIRT Visualizer is available via pip:

# NOTE for Snapdragon X Elite users:
# Only AMDx64 (64-bit) Python is supported on Windows.
# Installation will fail when using Windows ARM64 Python.

pip install qairt-visualizer

Getting Started

QAIRT Visualizer documentation can be found here

Need help?

LICENSE

Qualcomm AI Runtime Visualizer is Proprietary licensed. See LICENSE.pdf for further details.

Project details


Download files

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

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

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

qairt_visualizer-0.1.0-py3-none-macosx_11_0_arm64.whl (41.9 MB view details)

Uploaded Python 3macOS 11.0+ ARM64

File details

Details for the file qairt_visualizer-0.1.0-py3-none-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for qairt_visualizer-0.1.0-py3-none-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 e7ece217212d98b939cf51ff0f0f1e313e73d10ec618c6cd4ef6a7d2da5b0b99
MD5 0ae2d7384acbbd2e6a406ded5cade4ee
BLAKE2b-256 e6bc97c7e18f1f82e6b51b759363137a13610f0a01152ae9d5338aa9227accdd

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