Azure机器学习内存异常

时间:2017-04-26 18:52:53

标签: azure machine-learning azure-machine-learning-studio

我创建了一个简单的实验,指向我要检查的数据的csv文件。 CSV文件为70MB(约800,000行)。该实验仅包含以下任务: 1.获取数据 2.选择列(从数据中删除3列) 3.清除缺失数据(为丢失的数据值输入0值) 4.拆分数据(75%/ 25%) 5.线性回归算法 6.火车模型 7.分数模型

当我运行此时,Train Model获取并且内存不足异常。我目前只使用免费版本,但我查看了这个限制,似乎并不是限制它。

列车模型步骤在出错之前运行大约10秒钟。之前的所有步骤都需要不到1分钟的时间。

为什么我会出现内存不足异常。

错误日志 记录开始于UTC 04/27/2017 13:17:40:

Run the job:"/dll "Microsoft.Analytics.Modules.TrainGenericModel.Dll, Version=6.0.0.0, Culture=neutral, PublicKeyToken=69c3241e6f0468ca;Microsoft.Analytics.Modules.TrainGenericModel.Dll.TrainGenericModel;Run" /Output0 "..\..\Trained model\Trained model.ilearner" /learner "..\..\Untrained model\Untrained model.ilearner" /trainingData "..\..\Dataset\Dataset.dataset" /labelColumnIndexOrName "%7B%22isFilter%22%3Atrue%2C%22rules%22%3A%5B%7B%22ruleType%22%3A%22ColumnNames%22%2C%22columns%22%3A%5B%22TotalInvoicedOrders%22%5D%2C%22exclude%22%3Afalse%7D%5D%2C%22ui%22%3A%7B%22withRules%22%3Atrue%7D%7D"  /ContextFile "..\..\_context\ContextFile.txt""
[Start] Program::Main
[Start]     DataLabModuleDescriptionParser::ParseModuleDescriptionString
[Stop]     DataLabModuleDescriptionParser::ParseModuleDescriptionString. Duration = 00:00:00.0041511
[Start]     DllModuleMethod::DllModuleMethod
[Stop]     DllModuleMethod::DllModuleMethod. Duration = 00:00:00.0000326
[Start]     DllModuleMethod::Execute
[Start]         DataLabModuleBinder::BindModuleMethod
[Verbose]             moduleMethodDescription Microsoft.Analytics.Modules.TrainGenericModel.Dll, Version=6.0.0.0, Culture=neutral, PublicKeyToken=69c3241e6f0468ca;Microsoft.Analytics.Modules.TrainGenericModel.Dll.TrainGenericModel;Run
[Verbose]             assemblyFullName Microsoft.Analytics.Modules.TrainGenericModel.Dll, Version=6.0.0.0, Culture=neutral, PublicKeyToken=69c3241e6f0468ca
[Start]             DataLabModuleBinder::LoadModuleAssembly
[Verbose]                 Loaded moduleAssembly Microsoft.Analytics.Modules.TrainGenericModel.Dll, Version=6.0.0.0, Culture=neutral, PublicKeyToken=69c3241e6f0468ca
[Stop]             DataLabModuleBinder::LoadModuleAssembly. Duration = 00:00:00.0092214
[Verbose]             moduleTypeName Microsoft.Analytics.Modules.TrainGenericModel.Dll.TrainGenericModel
[Verbose]             moduleMethodName Run
[Information]             Module FriendlyName : Train Model
[Information]             Module Release Status : Release
[Stop]         DataLabModuleBinder::BindModuleMethod. Duration = 00:00:00.0121124
[Start]         ParameterArgumentBinder::InitializeParameterValues
[Verbose]             parameterInfos count = 3
[Verbose]             parameterInfos[0] name = learner , type = Microsoft.Analytics.MachineLearning.ILearner
[Start]             CustomSerializationHandler::HandleArgumentString
[Start]                 DotNetSerializationHandler::HandleArgumentString
[Stop]                 DotNetSerializationHandler::HandleArgumentString. Duration = 00:00:00.0085176
[Stop]             CustomSerializationHandler::HandleArgumentString. Duration = 00:00:00.0114152
[Verbose]             parameterInfos[1] name = trainingData , type = Microsoft.Numerics.Data.Local.DataTable
[Start]             DataTableDatasetHandler::HandleArgumentString
[Stop]             DataTableDatasetHandler::HandleArgumentString. Duration = 00:00:02.8392062
[Verbose]             parameterInfos[2] name = labelColumnIndexOrName , type = Microsoft.Analytics.Modules.Common.Dll.ColumnSelection
[Stop]         ParameterArgumentBinder::InitializeParameterValues. Duration = 00:00:03.1559096
[Verbose]         Begin invoking method Run ... 
[ModuleOutput] LearnerDetails
[ModuleOutput] 
[ModuleOutput] {
[ModuleOutput]  "InputName":Untrained model
[ModuleOutput]  "LearnerKind":Microsoft.Analytics.MachineLearning.Local.BatchLinearRegressor
[ModuleOutput] }
[ModuleOutput] InputDataStructure
[ModuleOutput] 
[ModuleOutput] {
[ModuleOutput]  "InputName":Dataset
[ModuleOutput]  "Rows":621312
[ModuleOutput]  "Cols":16
[ModuleOutput]  "ColumnTypes":System.String,12,System.Int32,4
[ModuleOutput] }
[Stop]     DllModuleMethod::Execute. Duration = 00:00:06.7340783
[Critical]     Error: Error 0138: Memory has been exhausted, unable to complete running of module.
[Critical]     {"InputParameters":{"DataTable":[{"Rows":621312,"Columns":16,"estimatedSize":364380160,"ColumnTypes":{"System.String":12,"System.Int32":4},"IsComplete":true,"Statistics":{"0":[36,0],"1":[3,0],"2":[8,0],"3":[6.3737912675113311,6.0,0.0,12.0,3.6860947075263715,13.0,0.0],"4":[608.87559390451179,312.0,0.0,2057.0,629.92222860055733,210.0,0.0],"5":[63210657.808690317,87803073.0,0.0,99429245.0,40023846.6134889,2314.0,0.0],"6":[11.006466960238978,8.0,0.0,35.0,8.3750399881698172,25.0,0.0],"7":[15630,0],"8":[34078,0],"9":[6912,0],"10":[7132,0],"11":[12459,0],"12":[17,0],"13":[2693,0],"14":[4481,0],"15":[4481,0]}}],"Learner":[{"LearnerKind":"learner","LearnerSettings":{"name":"BatchLinearRegressor","isTrained":false,"settings":[["Bias","True"],["Regularization","0.001"],["AllowUnknownLevels","True"],["RandomNumberSeed",""]],"weights":[]}}],"Generic":{"labelColumnIndexOrName":"{\"isFilter\":true,\"rules\":[{\"ruleType\":\"ColumnNames\",\"columns\":[\"TotalInvoicedOrders\"],\"exclude\":false}],\"ui\":{\"withRules\":true}}"}},"OutputParameters":[],"ModuleType":"Microsoft.Analytics.Modules.TrainGenericModel.Dll","ModuleVersion":" Version=6.0.0.0","AdditionalModuleInfo":"Microsoft.Analytics.Modules.TrainGenericModel.Dll, Version=6.0.0.0, Culture=neutral, PublicKeyToken=69c3241e6f0468ca;Microsoft.Analytics.Modules.TrainGenericModel.Dll.TrainGenericModel;Run","Errors":"Microsoft.Analytics.Exceptions.ErrorMapping+ModuleException: Error 0138: Memory has been exhausted, unable to complete running of module.","Warnings":[],"Duration":"00:00:06.7274218"}
Module finished after a runtime of 00:00:07.2184726 with exit code -2
Module failed due to negative exit code of -2

Record Ends at UTC 04/27/2017 13:17:48.

0 个答案:

没有答案