search

dotnet / machinelearning-samples

Samples for ML.NET, an open source and cross-platform machine learning framework for .NET.
https://dot.net/ml
MIT License
4.49k stars 2.69k forks source link

Models deployed in Windows 2019 server gets stuck in model.load #1021

Open ManuK001 opened 9 months ago

ManuK001 commented 9 months ago

Hi ML.net Team, I have an issue reported from another customer reported here on Azure support channel by Mistake. I suggested to report issue here, but it seems customer has not reported yet.

Customer is complaining that after upgrading to windows 19 server (Does not work) from windows 12 server(works) Their model deployment is not working and gets an exception in middle while loading the model.

Errors Error: Tensorflow exception triggered while loading model. at Microsoft.ML.TensorFlow.TensorFlowUtils.LoadTFSessionByModelFilePath(IExceptionContext ectx, String modelFile, Boolean metaGraph) at Microsoft.ML.TensorFlow.TensorFlowUtils.GetSession(IHostEnvironment env, String modelPath, Boolean metaGraph) at Microsoft.ML.Vision.ImageClassificationTrainer.LoadTensorFlowSessionFromMetaGraph(IHostEnvironment env, Architecture arch) at Microsoft.ML.Vision.ImageClassificationTrainer.InitializeTrainingGraph(IDataView input) at Microsoft.ML.Vision.ImageClassificationTrainer.TrainModelCore(TrainContext trainContext) at Microsoft.ML.Trainers.TrainerEstimatorBase2.TrainTransformer(IDataView trainSet, IDataView validationSet, IPredictor initPredictor) at Microsoft.ML.Trainers.TrainerEstimatorBase2.Fit(IDataView input) at Microsoft.ML.Data.EstimatorChain`1.Fit(IDataView input) at TestImageClassificationCore.ImageClassificationClass.TrainImages(XmlDocument qualityXML) in C:\Users\1012377\source\repos\TestImageClassificationCore\ImageClassificationClass.cs:line 359

ITransformer trainedModel = trainingPipeline.Fit(trainSet)

Could you please share any insights or remedials for above issue