Refactoring of Samples: Here are the list of backlog items created on MachineLearning Samples. Feel free to add any tasks that you want to add for refactoring of samples.
| S.No | Backlog item | Priority | Status | Assigned to |
|---|---|---|---|---|
| 1 | Add a sample on training on large datasets. The dataset should contain hundreds of columns, contain miliions of rows and size can be between 1gb and 100gb. The dataset should be used for MultiClass classification or Regression. | p0 | Done | Prathyusha Korrapati(v-prkor) |
| 2 | Add a sample on Ranking | p1 | Done | Nicole Haugen (nicolela) |
| 3 | Add Microsoft.Extensions ScalableML integration package to End-to-End apps to remove Object pooling in samples SalesDashboard etc | p0 | Done | Prathyusha Korrapati(v-prkor) |
| 4 | Update exisitng sample on Loading images from in-memory instead of files using ONNX model | p1 | Done | Prathyusha Korrapati(v-prkor) |
| 5 | Add a sample on Loading images from in-memory instead of files using TensorFlow model -->First Migrate the Cesar/TensorFlowImagaClassficationWebAPI app to 1.0.0 and also migrate using Microsoft.Extensions.ML DI package -->then use loading in-memory images | p1 | Done | Cesar De la Torre(cesardl) |
| 6 | Add Large dataset stored in SQL server for Database sample instead of sql lite and small dataset. -->Use the Credit card Fraud detection dataset. Export it to SQL server and use the existing Binary Classification algorithm | p1 | trying to comapre with loading large dataset from file. But got OutOfMemory exception.Created an issue. | Prathyusha Korrapati(v-prkor) |
| 7 | Restructure the project folders in samples according to CLI generated sample | p1 | Prathyusha Korrapati(v-prkor) | |
| 8 | Run the preview code only in debugger mode.not in prod environment | p0 | Done | Prathyusha Korrapati(v-prkor) |
| 9 | Add a sample on Model Expalinability (using Taxi Fare sample) | p1 | Cesar De La Torre(cesardl)/Prathyusha Korrapati(v-prkor) | |
| 10 | Sample using an .IDV format dataset for performace (TBD what app sample) - Check this PR/code for it: dotnet/machinelearning#3745 | p1 | Prathyusha Korrapati(v-prkor) | |
| 11 | Binary Classification: Flight delay prediction. Migrate from Azure ML Studio: https://gallery.azure.ai/Experiment/Binary-Classification-Flight-delay-prediction-3 | p1 | Prathyusha Korrapati(v-prkor) | |
| 12 | Anomaly Detection for Fraud, something that could break, etc. AnomalyDetection-PCA | p1 | Colby Williams(Colby.Williams) | |
| 13 | Fix the pedigreescan results | p1 | Have some questions.waiting for Richard to clarify | Prathyusha Korrapati(v-prkor) |
| 14 | Up-to-date Azure Functions sample scoring an ML.NET model | p2 | ||
| 15 | Add a link in ReadMe file for the LargeDataset sample once icon is finalized | p1 | done | Prathyusha Korrapati(v-prkor) |
| 16 | Use latest version of Inception 5h model in TensorFlow samples | p2 | Prathyusha Korrapati(v-prkor) | |
| 17 | Create Image Classification/Clustering Sample w/ DnnImageFeaturizerTransform(check this issue dotnet#225) | p2 | Prathyusha Korrapati(v-prkor) | |
| 18 | Add a sample on Timeseries for sales Forecast to use a trainer based on Time Series instead of Regression - check this SAMPLE https://github.com/dotnet/machinelearning/blob/main/docs/samples/Microsoft.ML.Samples/Dynamic/Transforms/TimeSeries/Forecasting.cs | p0 | TBD | |
| 19 | Migrate all the samples to ML.Net 1.1 | p0 | done | Prathyusha Korrapati(v-prkor) |
| 20 | Create an UWP app to detection objects in camera -->Check the performance of ML.Net with Live streaming of images -->In future convert this UWP app to WPF as UWP does not support in production env | p0 | Prathyusha Korrapati(v-prkor) | |
| 22 | Custom training the model with your own images instead of pretrained model and pretrained images: By using Cusrom Vision pretrained model you can train your own images and create a new model either a. TensorFlow model .pb or b. Onnx Model -->Use this model to predict the images. | p2 | Prathyusha Korrapati(v-prkor) |