yujunjun/autogen
1
0
Fork 0
mirror of https://github.com/microsoft/autogen.git synced 2025-09-26 00:24:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'microsoft:main' into main

Browse Source
This commit is contained in:
Jing Dong 2022-12-16 14:31:08 +08:00 committed by GitHub
commit c1872861b6
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 15 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -55,7 +55,7 @@ Use the following guides to get started with FLAML in .NET:
- [Install Model Builder](https://docs.microsoft.com/dotnet/machine-learning/how-to-guides/install-model-builder?tabs=visual-studio-2022)
- [Install ML.NET CLI](https://docs.microsoft.com/dotnet/machine-learning/how-to-guides/install-ml-net-cli?tabs=windows)
- [Microsoft.AutoML](https://www.nuget.org/packages/Microsoft.ML.AutoML/0.20.0-preview.22313.1)
- [Microsoft.AutoML](https://www.nuget.org/packages/Microsoft.ML.AutoML/0.20.0)
## Quickstart
@ -107,7 +107,7 @@ In addition, you can find:
- Contributing guide [here](https://microsoft.github.io/FLAML/docs/Contribute).
- ML.NET documentation and tutorials for [Model Builder](https://docs.microsoft.com/dotnet/machine-learning/tutorials/predict-prices-with-model-builder), [ML.NET CLI](https://docs.microsoft.com/en-us/dotnet/machine-learning/tutorials/sentiment-analysis-cli), and [AutoML API](https://github.com/dotnet/csharp-notebooks/blob/main/machine-learning/03-Training%20and%20AutoML.ipynb).
- ML.NET documentation and tutorials for [Model Builder](https://learn.microsoft.com/dotnet/machine-learning/tutorials/predict-prices-with-model-builder), [ML.NET CLI](https://learn.microsoft.com/dotnet/machine-learning/tutorials/sentiment-analysis-cli), and [AutoML API](https://learn.microsoft.com/dotnet/machine-learning/how-to-guides/how-to-use-the-automl-api).
## Contributing

13
website/docs/FAQ.md
View File

@ -66,3 +66,16 @@ Packages such as `azureml-interpret` and `sklearn.inspection.permutation_importa
Model explanation is frequently asked and adding a native support may be a good feature. Suggestions/contributions are welcome.
Optimization history can be checked from the [log](Use-Cases/Task-Oriented-AutoML#log-the-trials). You can also [retrieve the log and plot the learning curve](Use-Cases/Task-Oriented-AutoML#plot-learning-curve).
### How to resolve out-of-memory error in `AutoML.fit()`
* Set `free_mem_ratio` a float between 0 and 1. For example, 0.2 means try to keep free memory above 20% of total memory. Training may be early stopped for memory consumption reason when this is set.
* Set `model_history` False.
* If your data are already preprocessed, set `skip_transform` False. If you can preprocess the data before the fit starts, this setting can save memory needed for preprocessing in `fit`.
* If the OOM error only happens for some particular trials:
- set `use_ray` True. This will increase the overhead per trial but can keep the AutoML process running when a single trial fails due to OOM error.
- provide a more accurate [`size`](reference/automl/model#size) function for the memory bytes consumption of each config for the estimator causing this error.
- modify the [search space](Use-Cases/Task-Oriented-AutoML#a-shortcut-to-override-the-search-space) for the estimators causing this error.
- or remove this estimator from the `estimator_list`.
* If the OOM error happens when ensembling, consider disabling ensemble, or use a cheaper ensemble option. ([Example](Use-Cases/Task-Oriented-AutoML#ensemble)).