MLContext.Data.LoadFromEnumerable() not working in Unity for netstandard2.0 api

[KrasnovPavel]

System information

• WIndows 10
• Unity 2021.1.2f1, backend: mono, api level: netstandard2.0
• dotnet --info :

 Version:   5.0.201
 Commit:    a09bd5c86c

Runtime Environment:
 OS Name:     Windows
 OS Version:  10.0.19042
 OS Platform: Windows
 RID:         win10-x64
 Base Path:   C:\Program Files\dotnet\sdk\5.0.201\

Host (useful for support):
  Version: 5.0.4
  Commit:  f27d337295

.NET SDKs installed:
  5.0.201 [C:\Program Files\dotnet\sdk]

.NET runtimes installed:
  Microsoft.AspNetCore.All 2.1.26 [C:\Program Files\dotnet\shared\Microsoft.AspNetCore.All]
  Microsoft.AspNetCore.App 2.1.26 [C:\Program Files\dotnet\shared\Microsoft.AspNetCore.App]
  Microsoft.AspNetCore.App 3.1.13 [C:\Program Files\dotnet\shared\Microsoft.AspNetCore.App]
  Microsoft.AspNetCore.App 5.0.4 [C:\Program Files\dotnet\shared\Microsoft.AspNetCore.App]
  Microsoft.NETCore.App 2.1.26 [C:\Program Files\dotnet\shared\Microsoft.NETCore.App]
  Microsoft.NETCore.App 3.1.13 [C:\Program Files\dotnet\shared\Microsoft.NETCore.App]
  Microsoft.NETCore.App 5.0.4 [C:\Program Files\dotnet\shared\Microsoft.NETCore.App]
  Microsoft.WindowsDesktop.App 3.1.13 [C:\Program Files\dotnet\shared\Microsoft.WindowsDesktop.App]
  Microsoft.WindowsDesktop.App 5.0.4 [C:\Program Files\dotnet\shared\Microsoft.WindowsDesktop.App]

Issue

• What did you do?
  I have read ML.NET and Unity #1886.
  I have added all necessary dlls to Assets/Plugin folder. And tested that my model working on data from text file.
  Now I want to load data from collection using MLContext.Data.LoadFromEnumerable() function.

• What happened?
  It works in editor, but in standalone build i get PlutformNotSupported Excepetion.

• What did you expect?
  Load data without exception.
  It works if i set api level to .Net4.x. Thats why it works in editor, but unfortunatly in real project i have to use .netstandard2.0 for my other dependencies.

Source code / logs

Minimal example:

using System.Linq;
using Microsoft.ML;
using UnityEngine;
using Random = UnityEngine.Random;

public class Clusterisator : MonoBehaviour
{
    void Start()
    {
        Calculate();
    }

    class Point
    {
        public float X, Y, Z;
    }

    public static void Calculate()
    {
        var points = Enumerable.Range(0, 100)
                .Select(_ => new Point {X = Random.value, Y = Random.value, Z = Random.value})
                .ToList();

        var mlContext = new MLContext(seed: 0);
        var dataView = mlContext.Data.LoadFromEnumerable(points);

        var pipeline = mlContext.Transforms
                .Concatenate("Features", "X", "Y", "Z")
                .Append(mlContext.Clustering.Trainers.KMeans(numberOfClusters: 5));

        var transformed = pipeline.Fit(dataView).Transform(dataView);
        var clusterColumn = transformed.Schema.GetColumnOrNull("PredictedLabel").Value;
        var cursor = transformed.GetRowCursor(new[] {clusterColumn});
        var clusterizatorResult = cursor.GetGetter<uint>(clusterColumn);

        while (cursor.MoveNext())
        {
            uint cluster = 0;
            clusterizatorResult(ref cluster);
            Debug.Log(cluster);
        }
    }
}

Exception stack trace:

PlatformNotSupportedException: Operation is not supported on this platform.
  at Microsoft.ML.ApiUtils.GeneratePeek[TOwn,TRow,TValue] (System.Reflection.FieldInfo fieldInfo, System.Reflection.Emit.OpCode assignmentOpCode) [0x00040] in <b2a9703d9c7542afbe2c6d1a607e584a>:0 
  at (wrapper managed-to-native) System.Reflection.MonoMethod.InternalInvoke(System.Reflection.MonoMethod,object,object[],System.Exception&)
  at System.Reflection.MonoMethod.Invoke (System.Object obj, System.Reflection.BindingFlags invokeAttr, System.Reflection.Binder binder, System.Object[] parameters, System.Globalization.CultureInfo culture) [0x00032] in <a1e9f114a6e64f4eacb529fc802ec93d>:0 
Rethrow as TargetInvocationException: Exception has been thrown by the target of an invocation.
  at System.Reflection.MonoMethod.Invoke (System.Object obj, System.Reflection.BindingFlags invokeAttr, System.Reflection.Binder binder, System.Object[] parameters, System.Globalization.CultureInfo culture) [0x0004b] in <a1e9f114a6e64f4eacb529fc802ec93d>:0 
  at System.Reflection.MethodBase.Invoke (System.Object obj, System.Object[] parameters) [0x00000] in <a1e9f114a6e64f4eacb529fc802ec93d>:0 
  at Microsoft.ML.Internal.Utilities.Utils.MarshalInvoke[TArg1,TArg2,TResult] (Microsoft.ML.Internal.Utilities.FuncStaticMethodInfo3`3[T1,T2,TResult] func, System.Type genArg1, System.Type genArg2, System.Type genArg3, TArg1 arg1, TArg2 arg2) [0x0000a] in <52c676b9d07a49dd94084172a2250221>:0 
  at Microsoft.ML.ApiUtils.GeneratePeek[TOwn,TRow] (Microsoft.ML.Data.InternalSchemaDefinition+Column column) [0x0003a] in <b2a9703d9c7542afbe2c6d1a607e584a>:0 
  at Microsoft.ML.Data.DataViewConstructionUtils+DataViewBase`1[TRow]..ctor (Microsoft.ML.Runtime.IHostEnvironment env, System.String name, Microsoft.ML.Data.InternalSchemaDefinition schemaDefn) [0x00060] in <b2a9703d9c7542afbe2c6d1a607e584a>:0 
  at Microsoft.ML.Data.DataViewConstructionUtils+StreamingDataView`1[TRow]..ctor (Microsoft.ML.Runtime.IHostEnvironment env, System.Collections.Generic.IEnumerable`1[T] data, Microsoft.ML.Data.InternalSchemaDefinition schemaDefn) [0x00000] in <b2a9703d9c7542afbe2c6d1a607e584a>:0 
  at Microsoft.ML.Data.DataViewConstructionUtils.CreateFromEnumerable[TRow] (Microsoft.ML.Runtime.IHostEnvironment env, System.Collections.Generic.IEnumerable`1[T] data, Microsoft.ML.Data.SchemaDefinition schemaDefinition) [0x00026] in <b2a9703d9c7542afbe2c6d1a607e584a>:0 
  at Microsoft.ML.DataOperationsCatalog.LoadFromEnumerable[TRow] (System.Collections.Generic.IEnumerable`1[T] data, Microsoft.ML.Data.SchemaDefinition schemaDefinition) [0x00011] in <b2a9703d9c7542afbe2c6d1a607e584a>:0 
  at Clusterisator.Calculate () [0x0003f] in C:\Users\User\RiderProjects\Minimal ML Test\Assets\Clusterisator.cs:25 
  at Clusterisator.Start () [0x00001] in C:\Users\User\RiderProjects\Minimal ML Test\Assets\Clusterisator.cs:10 

Minimal Unity project:
Minimal ML Test.zip