Experimental tools for converting PyTorch models to ONNX

Navigation

Verified details

These details have been verified by PyPI
Project links
GitHub Statistics
Maintainers
Avatar for justinchuby from gravatar.com justinchuby

Unverified details

These details have not been verified by PyPI
Meta
  • License: MIT License (MIT License)
  • Author: Justin Chu
  • Tags onnx, pytorch, converter, convertion, exporter
  • Requires: Python >=3.8
Classifiers

Project description

PyTorch to ONNX Exporter

PyPI version

Experimental torch ONNX exporter. Compatible with torch>=2.1.

[!WARNING] This is an experimental project and is not designed for production use. Use torch.onnx.export for these purposes.

Installation

pip install --upgrade torch-onnx

Usage

import torch
import torch_onnx
from onnxscript import ir
import onnx

# Get an exported program with torch.export
exported = torch.export.export(...)
model = torch_onnx.exported_program_to_ir(exported)
proto = ir.to_proto(model)
onnx.save(proto, "model.onnx")

# Or patch the torch.onnx export API
# Set error_report=True to get a detailed error report if the export fails
torch_onnx.patch_torch(report=True, verify=True, profile=True)
torch.onnx.export(...)

# Use the analysis API to print an analysis report for unsupported ops
torch_onnx.analyze(exported)

Design

{dynamo/jit} -> {ExportedProgram} -> {torchlib} -> {ONNX IR} -> {ONNX}

  • Use ExportedProgram
    • Rely on robustness of the torch.export implementation
    • Reduce complexity in the exporter
    • This does not solve dynamo limitations, but it avoids introducing additional breakage by running fx passes
  • Flat graph; Scope info as metadata, not functions
    • Because existing tools are not good at handling them
  • Eager optimization where appropriate
    • Because exsiting tools are not good at optimizing
  • Drop in replacement for torch.onnx.export
    • Minimum migration effort
  • Build graph eagerly in the exporter
    • Give the exporter full control over the graph being built

Why is this doable?

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