-
Notifications
You must be signed in to change notification settings - Fork 1.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
ConvertToOnnx
should also accept DataViewSchema
#6448
Comments
So the call to Are you seeing something that is showing its actually doing data processing there? |
This issue has been marked |
Replied at #6449 (comment) |
Is your feature request related to a problem? Please describe.
Currently, saving a model to zip file only requires a
DataViewSchema
, but saving a model to ONNX requiresIDataView
.Inside
ConvertToOnnxProtobufCore
, a prediction was performed (transform.Transform(inputData)
), which may be expensive if the training data set is large.Describe the solution you'd like
ConvertToOnnx
should have overloads that acceptDataViewSchema
, then convert theDataViewSchema
to an emptyIDataView
, and pass the emptyIDataView
to the methods acceptingIDataView
.The performance of methods accepting
IDataView
may be improved ifEmptyDataView
is created from the Schema of the IDataView and passed toConvertToOnnxProtobuf
, instead of full data.Describe alternatives you've considered
Nil
Additional context
I have implemented the proposed solution and that seems working well. It is unfortunate that
EmptyDataView
is aninternal
class, so I have to implement my ownEmptyDataView
.The text was updated successfully, but these errors were encountered: