Experimental tools for converting PyTorch models to ONNX
Project description
PyTorch to ONNX Exporter
Experimental torch ONNX exporter.
[!WARNING] This is an experimental project and is not designed for production use. Use
torch.onnx.exportfor 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(error_report=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?
- We need to verify torch.export coverage on Huggingface Optimum https://github.com/huggingface/optimum/tree/main/optimum/exporters/onnx; and they are not patching torch.onnx itself.
- Patch torch.onnx.export such that packages do not need to change a single line to use dynamo
- We have all operators implemented and portable
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
torch_onnx-0.0.27.tar.gz
(51.4 kB
view details)
Built Distribution
File details
Details for the file torch_onnx-0.0.27.tar.gz.
File metadata
- Download URL: torch_onnx-0.0.27.tar.gz
- Upload date:
- Size: 51.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/4.0.1 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 8195ddf0ca988cd55b72b257a2784a93fd9aa09ad35d6e4c16334d90321ff81c |
|
| MD5 | 0e799515d544b4f9f345494ffc771e96 |
|
| BLAKE2b-256 | a9f28fba808c1b4d99ac5ad8b616d4b3bc89e208d37ab773c65cc2b4cda3930b |
File details
Details for the file torch_onnx-0.0.27-py3-none-any.whl.
File metadata
- Download URL: torch_onnx-0.0.27-py3-none-any.whl
- Upload date:
- Size: 57.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/4.0.1 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 72d45efe3ae23a41c7c0b37857bf87579f2fc02121b4067037fd0362b9b4b670 |
|
| MD5 | ed760bc7c52daec49a62bf1ee3da3e97 |
|
| BLAKE2b-256 | 17022a0d971d4e7b5dcd11c2847941dd2bb287787a10f579e616c6e572e785bf |
