Update OnnxTransformer Docs #5296
Conversation
Codecov Report
@@ Coverage Diff @@
## master #5296 +/- ##
=======================================
Coverage 73.68% 73.68%
=======================================
Files 1022 1022
Lines 190366 190366
Branches 20474 20474
=======================================
+ Hits 140265 140279 +14
+ Misses 44568 44560 -8
+ Partials 5533 5527 -6
|
| /// </summary> | ||
| /// <remarks> | ||
| /// The name/type of input columns must exactly match name/type of the ONNX model inputs. | ||
| /// The name/type of the produced output columns will match name/type of the ONNX model outputs. | ||
| /// </remarks> | ||
| /// <param name="catalog">The transform's catalog.</param> | ||
| /// <param name="modelFile">The path of the file containing the ONNX model.</param> | ||
| /// <param name="shapeDictionary">ONNX shape should be used to over those loaded from <paramref name="modelFile"/>.</param> | ||
| /// <param name="shapeDictionary">ONNX shapes to be used over those loaded from <paramref name="modelFile"/>. |
There was a problem hiding this comment.
Would it be useful to add an example here? Or do we already have one in the samples?
There was a problem hiding this comment.
We don't have samples for this.
I guess I can make one, but for that I'll need to find a model that requires it and upload it somewhere outside ML.NET repo so that it can be added to the sample?
There was a problem hiding this comment.
In the meantime, do you have any other suggestion on the docs, @natke ? maybe we can merge this PR just to see if this forces the staged docs to update... and add that sample on another PR
There was a problem hiding this comment.
Ok, I'm pushing this now to see if this unblocks the staging docs.
EDIT: Ok, I can't push it because the CI is stuck. I'll have to rerun the CI manually and after that I'll push.
|
/azp run |
|
Azure Pipelines successfully started running 2 pipeline(s). |
|
Closing and re-openning this PR as it seems the CI is stuck; hopefully doing this will fix that. |
ghost
locked as resolved and limited conversation to collaborators
Address Using OnnxTransformer throws TypeInitializationException #5262 (comment) : Users find it confusing not knowing where to find the info related to the dependencies of Onnx and how to make it work on the GPU. So I think it's best to keep this info in the docs of the
OnnxScoringEstimatorand add a note on everyApplyOnnxModel()overload and toOnnxTransformerpointing to the Estimator's docs.Address Opaque disruptive handling of variable axes of ONNX-models #5293 : About the confusing nature of the
shapeDictionaryparameter. I've updated the docs for this parameter based on the explicit suggestion made by the user.Added a couple of details about how the
gpuDeviceIdandfallbackToCpuinteract with each other.Note: As stated in #5262 (comment) for some reason the published docs for OnnxTransformer are outdated, and for some reason it includes info that was deleted on the ML.NET 1.5.0 release (or maybe before that). @natke thinks this is a bug in the tools that generate the published docs, and is seeking for help on this, as this tools are outside of the ML.NET repo itself. In the meantime, we'll try to see if updating this docs on this PR will force the tool to actually generate the correct updated docs.