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.
- 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-0.0.22.tar.gz
(48.1 kB
view details)
Built Distribution
File details
Details for the file torch_onnx-0.0.22.tar.gz.
File metadata
- Download URL: torch_onnx-0.0.22.tar.gz
- Upload date:
- Size: 48.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/4.0.1 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | b2c1e54d9b963aead244ddb576db1eeecb62c070ded33f1a00a4b65e62f871ca |
|
| MD5 | 73c2de1bf4b84ba01d158197d80e4802 |
|
| BLAKE2b-256 | 8c5cac5e1290116ea529ccbf28d8faf27fecfc6576c2bfbc6fa1131ca07ca604 |
File details
Details for the file torch_onnx-0.0.22-py3-none-any.whl.
File metadata
- Download URL: torch_onnx-0.0.22-py3-none-any.whl
- Upload date:
- Size: 53.8 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 | 9d2cb17481ee8261c299ef2cfcc127b8a2c0c17f0df29d66eab894821c71762a |
|
| MD5 | f685ed34e74dfeb7e84a6f7110dd81e6 |
|
| BLAKE2b-256 | 9af4a1aacfcf1954f204e773e02be71c9f64638fa69c2e4a585be5b621937c9c |
