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(report=True, verify=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-0.1.3.tar.gz
(57.6 kB
view details)
Built Distribution
File details
Details for the file torch_onnx-0.1.3.tar.gz.
File metadata
- Download URL: torch_onnx-0.1.3.tar.gz
- Upload date:
- Size: 57.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/4.0.1 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | ccad5497fb65f8492f322d7579049479d228e3e60ffa36b3a672db6d742cb5f5 |
|
| MD5 | 722b77a58ba40bfbdd5150c3ae6375fd |
|
| BLAKE2b-256 | f2a56de023cbbef3e337b449315e7a015d754340a217fa60b67ef7695a75a954 |
File details
Details for the file torch_onnx-0.1.3-py3-none-any.whl.
File metadata
- Download URL: torch_onnx-0.1.3-py3-none-any.whl
- Upload date:
- Size: 64.3 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 | 7f1aa3f40bc6d11ee5251e88df688d3bc8127d2cd2de38c7d868aad8004f54aa |
|
| MD5 | c2e5f4b3ed8b474b3c747b435c73c5d1 |
|
| BLAKE2b-256 | 98387526449a502e1337d1c184b6c7c30fddc5d63e5d58697aee8bdc57279b3a |
