Update Onnx Convert documentation, limited to ONNX-ML target platforms #505
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
CESARDELATORRE
referenced
this pull request
Jul 9, 2018
codemzs
reviewed
Jul 9, 2018
| /// you can create a model using ML.NET (or any ONNX compatible toolkit), convert it to ONNX and | ||
| /// then the ONNX model can be converted into say, CoreML, TensorFlow or WinML model | ||
| /// to run on the respective runtime. | ||
| /// you can create a model using ML.NET, export it to an ONNX-ML model file, |
There was a problem hiding this comment.
Can you please clarify here what ONNX-ML is? May be add a line before that is a superset of ONNX and some explanation to its history.
TomFinley
approved these changes
Jul 11, 2018
eerhardt
pushed a commit
to eerhardt/machinelearning
that referenced
this pull request
Jul 27, 2018
ghost
locked as resolved and limited conversation to collaborators
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR is just updating the documentation/comments for the ML.NET Convert/export to ONNX.
The ML.NET export/convert feature uses ONNX-ML (not the regular ONNX specification).
Currently, the only target platform supported by ONNX-ML is Windows ML.
The current comments in the documentation have examples mentioning Apple CoreML and TensorFlow, which are currently not supported by ONNX-ML.
This PR is simply fixing the comments/documentation.
Further details on ONNX and ONNX-ML:
ONNX is not a single specification but two different variations of the standard. The neural-network-only (DNN) ONNX variant recognizes only tensors as input and output types, while ONNX-ML is a classical Machine Learning variant.
ONNX-ML is part of the ONNX standard that provides functionality for classic ML and pipelines. It is a superset of core ONNX.
Frameworks like Caffe2 and CNTK will not support ONNX-ML since they are focused on DNN.
Apple CoreML and other ONNX backends might support ONNX-ML in the future, but they currently don't, so our example should not mention Apple CoreML and TensorFlow as sample target platforms to use after exporting the ONNX file. At least, not yet.