h2oai / h2o-3

H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.
http://h2o.ai
Apache License 2.0
6.87k stars 2k forks source link

Unsupported MOJO type #7932

Open exalate-issue-sync[bot] opened 1 year ago

exalate-issue-sync[bot] commented 1 year ago

I initially posted the bug here: [https://github.com/onnx/onnxmltools/issues/409|https://github.com/onnx/onnxmltools/issues/409]

But I am in doubt now, I think maybe the problem is H2O itself.

When I do a {{aml_lead = aml.leader.download_mojo(path="/tmp/")}} the output is the same as if I issue {{aml_lead = aml.download_mojo(path="/tmp/")}}. And I can not see the binaries in the resulting zip file.

If anyone, for example, exports a trained GBM model, it would be exported as an ONNX successfully. Inside the zip, you would find the .bin files inside the /trees/ folder But I am unable to export a model which has previously been trained through AutoML. If I try to export the Ensemble, XGBoost or GLM models, it will not work.

h2o-ops commented 1 year ago

JIRA Issue Migration Info

Jira Issue: PUBDEV-7707 Assignee: New H2O Bugs Reporter: Sergio Fernández State: Open Fix Version: N/A Attachments: N/A Development PRs: N/A