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-0.0.20.tar.gz
(38.8 kB
view details)
Built Distribution
File details
Details for the file torch_onnx-0.0.20.tar.gz.
File metadata
- Download URL: torch_onnx-0.0.20.tar.gz
- Upload date:
- Size: 38.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/4.0.1 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | fc1edda86e4b1a8250204c756953fb2665a78fc85f89caeb88ab7bab2296c186 |
|
| MD5 | 690e8d94af5ecb7d85a0fa2b28d5a96b |
|
| BLAKE2b-256 | 041cc49df395c00b182e7251cac0f0ce2a1c3eacbaad06fdeb524bbff1df25e6 |
File details
Details for the file torch_onnx-0.0.20-py3-none-any.whl.
File metadata
- Download URL: torch_onnx-0.0.20-py3-none-any.whl
- Upload date:
- Size: 44.1 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 | 82230a48bae7879a43b77aecff79599390fa4792838d14ac4e7db519b40e57ea |
|
| MD5 | 2e5390d4f2bc973870c15462bb4a28dc |
|
| BLAKE2b-256 | f501053c0054ab5b4a48ffd8bde0cd81b006efcaf1a761eabe9b39a018ec4942 |
