dotnet / dotnet/machinelearning-modelbuilder

Training the model failed for data classfication scenario

Aperta
#2,641 3 commenti 0 reazioni 0 assegnatari Vedi su GitHub
GS Tutorial Stale
Lingua principale
Dockerfile
Stelle
285
Fork
66
Metriche di merge delle PR
Nessuna PR unita negli ultimi 30g

Descrizione

**System Information (please complete the following information):**
- Model Builder or CLI Version: https://dotnet.microsoft.com/en-us/learn/ml-dotnet/get-started-tutorial/train
- Visual Studio Version (if applicable): Version 17.4.5

**Describe the bug**
- On which page of the tutorial did you run into an issue (URL): https://dotnet.microsoft.com/en-us/learn/ml-dotnet/get-started-tutorial/train
- Clear description of the problem: 2023-05-18 11:17:57.4956 INFO Set log file path to C:\Users\Balaji N\AppData\Local\Temp\MLVSTools\logs\SentimentModel-7A2V9M.txt (Microsoft.ML.ModelBuilder.Utils.Logger.Info)
2023-05-18 11:18:53.0393 DEBUG Start AutoMLService pid: 7448 (Microsoft.ML.ModelBuilder.Utils.Logger.Debug)
2023-05-18 11:18:53.4588 INFO start multiclass classification (Microsoft.ML.ModelBuilder.Utils.Logger.Info)
2023-05-18 11:18:53.4588 INFO Evaluate Metric: MacroAccuracy (Microsoft.ML.ModelBuilder.Utils.Logger.Info)
2023-05-18 11:18:53.4588 INFO Available Trainers: LGBM,FASTFOREST,FASTTREE,LBFGS,SDCA (Microsoft.ML.ModelBuilder.Utils.Logger.Info)
2023-05-18 11:18:53.4588 INFO Training time in second: 60 (Microsoft.ML.ModelBuilder.Utils.Logger.Info)
2023-05-18 11:19:52.6313 INFO [Source=AutoMLExperiment, Kind=Info] cancel training because cancellation token is invoked... (Microsoft.ML.ModelBuilder.Utils.Logger.Info)
2023-05-18 11:19:52.7308 DEBUG Training time finished without completing a successful trial. Either no trial completed or the metric for all completed trials are NaN or Infinity
at Microsoft.ML.AutoML.AutoMLExperiment.d__24.MoveNext()
--- End of stack trace from previous location where exception was thrown ---
at System.Runtime.ExceptionServices.ExceptionDispatchInfo.Throw()
at System.Runtime.CompilerServices.TaskAwaiter.HandleNonSuccessAndDebuggerNotification(Task task)
at Microsoft.ML.ModelBuilder.AutoMLService.Experiments.MultiClassificationExperiment.d__14.MoveNext() in /_/src/Microsoft.ML.ModelBuilder.AutoMLService/Experiments/MultiClassificationExperiment.cs:line 134
--- End of stack trace from previous location where exception was thrown ---
at System.Runtime.ExceptionServices.ExceptionDispatchInfo.Throw()
at System.Runtime.CompilerServices.TaskAwaiter.HandleNonSuccessAndDebuggerNotification(Task task)
at Microsoft.ML.ModelBuilder.AutoMLEngine.d__21.MoveNext() in /_/src/Microsoft.ML.ModelBuilder.AutoMLService/AutoMLEngineService/AutoMLEngine.cs:line 161 (Microsoft.ML.ModelBuilder.Utils.Logger.Debug)

**To Reproduce**
Steps to reproduce the behavior:
1. I followed the steps mentioned when clicked on "Train".
2. We are getting the following error. Please find below screenshot
![image](https://github.com/dotnet/machinelearning-modelbuilder/assets/67501998/c8be73d0-578f-4d66-b019-c9981bd392fb)

**Expected behavior**
2023-05-18 11:17:57.4956 INFO Set log file path to C:\Users\Balaji N\AppData\Local\Temp\MLVSTools\logs\SentimentModel-7A2V9M.txt (Microsoft.ML.ModelBuilder.Utils.Logger.Info)
2023-05-18 11:18:53.0393 DEBUG Start AutoMLService pid: 7448 (Microsoft.ML.ModelBuilder.Utils.Logger.Debug)
2023-05-18 11:18:53.4588 INFO start multiclass classification (Microsoft.ML.ModelBuilder.Utils.Logger.Info)
2023-05-18 11:18:53.4588 INFO Evaluate Metric: MacroAccuracy (Microsoft.ML.ModelBuilder.Utils.Logger.Info)
2023-05-18 11:18:53.4588 INFO Available Trainers: LGBM,FASTFOREST,FASTTREE,LBFGS,SDCA (Microsoft.ML.ModelBuilder.Utils.Logger.Info)
2023-05-18 11:18:53.4588 INFO Training time in second: 60 (Microsoft.ML.ModelBuilder.Utils.Logger.Info)
2023-05-18 11:19:52.6313 INFO [Source=AutoMLExperiment, Kind=Info] cancel training because cancellation token is invoked... (Microsoft.ML.ModelBuilder.Utils.Logger.Info)
2023-05-18 11:19:52.7308 DEBUG Training time finished without completing a successful trial. Either no trial completed or the metric for all completed trials are NaN or Infinity
at Microsoft.ML.AutoML.AutoMLExperiment.d__24.MoveNext()
--- End of stack trace from previous location where exception was thrown ---
at System.Runtime.ExceptionServices.ExceptionDispatchInfo.Throw()
at System.Runtime.CompilerServices.TaskAwaiter.HandleNonSuccessAndDebuggerNotification(Task task)
at Microsoft.ML.ModelBuilder.AutoMLService.Experiments.MultiClassificationExperiment.d__14.MoveNext() in /_/src/Microsoft.ML.ModelBuilder.AutoMLService/Experiments/MultiClassificationExperiment.cs:line 134
--- End of stack trace from previous location where exception was thrown ---
at System.Runtime.ExceptionServices.ExceptionDispatchInfo.Throw()
at System.Runtime.CompilerServices.TaskAwaiter.HandleNonSuccessAndDebuggerNotification(Task task)
at Microsoft.ML.ModelBuilder.AutoMLEngine.d__21.MoveNext() in /_/src/Microsoft.ML.ModelBuilder.AutoMLService/AutoMLEngineService/AutoMLEngine.cs:line 161 (Microsoft.ML.ModelBuilder.Utils.Logger.Debug)

**Screenshots**
![image](https://github.com/dotnet/machinelearning-modelbuilder/assets/67501998/f8470e34-162a-417a-b5f6-342940e67eb9)

Guida per i contributori

Nessuna guida per i contributori indicizzata per questo repository

Direzione di ricerca

Inizia con il tutorial di training collegato e riproduci l'esecuzione di classificazione multiclass utilizzando l'output di log fornito. Esamina MultiClassificationExperiment.cs alla riga 134 e AutoMLEngine.cs alla riga 161, quindi determina perché nessuna prova completata con successo giunge al termine; il lavoro è considerato concluso quando il flusso di training del tutorial termina correttamente invece di segnalare che tutte le metriche sono NaN o Infinity.

Scritto dal modello di indicizzazione a partire dal testo della issue.

Valutazione

Stack tecnologico
machine-learning
Ambito
machine-learning
Tipo di issue
Bug
Difficoltà
4/5
Tempo stimato
3-5 giorni
Stato di attività
Ferma
Chiarezza
Da chiarire
Idoneità per principianti
25/100

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.