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-0.0.3.tar.gz
(8.9 kB
view details)
Built Distribution
File details
Details for the file torch_onnx-0.0.3.tar.gz.
File metadata
- Download URL: torch_onnx-0.0.3.tar.gz
- Upload date:
- Size: 8.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/4.0.1 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 19ae00d516a3862ac0ff992ca373f7c171e8d37f7828c2b075256808c791b9db |
|
| MD5 | 2e674292c26cf79c5c45872c70eb78f4 |
|
| BLAKE2b-256 | 4fbf78b221e6abd1d065a932cb9b86c41585a04c4182c6cc2a76beaf85d23057 |
File details
Details for the file torch_onnx-0.0.3-py3-none-any.whl.
File metadata
- Download URL: torch_onnx-0.0.3-py3-none-any.whl
- Upload date:
- Size: 8.6 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 | 6c516ec6a913a3ec4c51eddcc9a8f4d784c47fdad374c0a1caf566054cf81ba1 |
|
| MD5 | dc550328c8c0969aaaddfc30e300a743 |
|
| BLAKE2b-256 | d2bc180fe262521a9107d8b6a79ac109e59ac9f0baf489684e5a90be4d2e7165 |
