Skip to main content

Model Explorer Adapter

The Model Explorer Adapter provides graph extraction and visualization conversion for ML models (TensorFlow SavedModel, GraphDef, FlatBuffer/LiteRT, StableHLO/MLIR) to Model Explorer's visualization JSON format.

It is implemented as a stable C-ABI library (libai_edge_model_explorer_adapter.so / .dylib) with a pure Python ctypes FFI wrapper for universal ABI stability across Python versions without pybind11 compile-time matrix bloat.

Install from PyPI

Install ai-edge-model-explorer-adapter via pip from PyPI. For example, in a Python virtual environment:

% python3 -m venv ~/tmp/venv
% source ~/tmp/venv/bin/activate
(venv) $ pip install ai-edge-model-explorer-adapter

Use the Package

After installation, the package can be imported directly:

import ai_edge_model_explorer_adapter as adapter

config = adapter.VisualizeConfig()
json_str = adapter.ConvertFlatbufferDirectlyToJson(config, "model.tflite")
print(json_str)

Build and Install Locally

Declarative Bazel Build

Build the Python wheel directly using Bazel:

bazel build -c opt //python/ai_edge_model_explorer_adapter:wheel

The resulting wheel is located under bazel-bin/: bazel-bin/python/ai_edge_model_explorer_adapter/

Install

Install the resulting wheel via pip:

(venv) $ pip install \
  bazel-bin/python/ai_edge_model_explorer_adapter/*.whl

Metadata

Release files for ai-edge-model-explorer-adapter 0.2.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distributions (wheels)

Table of built distributions (wheels) for ai-edge-model-explorer-adapter 0.2.1
File Interpreter ABI Platform Actions
ai_edge_model_explorer_adapter-0.2.1-py3-none-manylinux_2_27_x86_64.whl Python 3 none Linux glibc 2.27+ x86-64 Details for ai_edge_model_explorer_adapter-0.2.1-py3-none-manylinux_2_27_x86_64.whl
ai_edge_model_explorer_adapter-0.2.1-py3-none-manylinux_2_27_aarch64.whl Python 3 none Linux glibc 2.27+ ARM64 Details for ai_edge_model_explorer_adapter-0.2.1-py3-none-manylinux_2_27_aarch64.whl
ai_edge_model_explorer_adapter-0.2.1-py3-none-macosx_12_0_arm64.whl Python 3 none macOS 12.0+ ARM64 Details for ai_edge_model_explorer_adapter-0.2.1-py3-none-macosx_12_0_arm64.whl

Total release size: 329.4 MB

Release files / ai_edge_model_explorer_adapter-0.2.1-py3-none-manylinux_2_27_x86_64.whl

Download URL ai_edge_model_explorer_adapter-0.2.1-py3-none-manylinux_2_27_x86_64.whl
Size 128.5 MB
Tags Linux glibc 2.27+ x86-64 Python 3
SHA-256 checksum
How to use checksums
d31f56cea19444facb05f52553493a9d5a284e238567672e1533f14132b4326e
BLAKE2b-256 checksum
How to use checksums
a9acc5e1e530638b0dd96350c85009405e632459d688c7a6668d5fc38dfff005
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.10

Release files / ai_edge_model_explorer_adapter-0.2.1-py3-none-manylinux_2_27_aarch64.whl

Download URL ai_edge_model_explorer_adapter-0.2.1-py3-none-manylinux_2_27_aarch64.whl
Size 103.3 MB
Tags Linux glibc 2.27+ ARM64 Python 3
SHA-256 checksum
How to use checksums
041a5592a31f64a4fd3622559275ae0a495bc3b0e988c0b9a4a038b37d62905b
BLAKE2b-256 checksum
How to use checksums
b41d24cfa5ca5ea18e38bc53bd667c7b2956ec38b0e21bbdd7698e3fd71e560e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.10

Release files / ai_edge_model_explorer_adapter-0.2.1-py3-none-macosx_12_0_arm64.whl

Download URL ai_edge_model_explorer_adapter-0.2.1-py3-none-macosx_12_0_arm64.whl
Size 97.6 MB
Tags Python 3 macOS 12.0+ ARM64
SHA-256 checksum
How to use checksums
3eea643b1bb06940d33c65585a4564f617ec88e10952f26e5d3d46488770d7b3
BLAKE2b-256 checksum
How to use checksums
359b3611be543f47f7fa25c3ce4e62b46de206b9e911bfb99a4c1fcbed93b7e5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.10

Security for ai-edge-model-explorer-adapter 0.2.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page