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 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)
# This will give you an ATen dialect graph (un-lowered ONNX graph with ATen ops)
onnx.save(proto, "model.onnx")
Design
{ExportedProgram, jit} -> {ONNX IR} -> {torchlib} -> {ONNX}
- 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
- Use ExportedProgram
- Rely on robustness of the torch.export implementation
- This does not solve dynamo limitations, but it avoids introducing additional breakage by running fx passes
- Build graph eagerly, in place
- Expose shape and dtype information to the op functions; build with IR
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.
- Path 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-0.0.1.tar.gz
(8.2 kB
view details)
Built Distribution
File details
Details for the file torch_onnx-0.0.1.tar.gz.
File metadata
- Download URL: torch_onnx-0.0.1.tar.gz
- Upload date:
- Size: 8.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/4.0.1 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | b59e97d25c6d951174646ee04f2ceb7f5787b44a70928c4f0c13646114a4b7e7 |
|
| MD5 | 0dc53617760dc32d9bc79becbb8d0019 |
|
| BLAKE2b-256 | 75bcb5458199ef85501314a47cd2d9f2cc3637650f55e29ea811e8f3ad3258dc |
File details
Details for the file torch_onnx-0.0.1-py3-none-any.whl.
File metadata
- Download URL: torch_onnx-0.0.1-py3-none-any.whl
- Upload date:
- Size: 7.8 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 | 5ede787183363eefd29bb78dc311e8ec1af8e7ae70ed10ffede7ff56f51f33ae |
|
| MD5 | fe5506d4d8896c131cd5bced9a90a57f |
|
| BLAKE2b-256 | c2000f206c95430c9e7ea68cf8492fa5a12f64ac93e978d8a0e00c7980033d98 |
