dotnet / dotnet/machinelearning
large models loading with mlcontext.model.load ends up OutOfMemoryException
- Dominant language
- C#
- Stars
- 9.4k
- Forks
- 2k
- Avg merge
- 2d 20h
- Merged PRs (30d)
- 11
Description
**System Information (please complete the following information):**
- OS & Version: Windows 11 Pro 23H2 64GB RAM
- ML.NET Version: Microsoft.ML Ver3.0.0, Microosft.ML.AutoML Ver0.21.0
- .NET Version: .NET 8
**Describe the bug**
When loading models which size are over 100MB, mlcontext.model.load throws Exception.
Viewing stack tace, 'System.Reflection.TargetInvocationException' (Microsoft.ML.Core.dll)
System.Reflection.TargetInvocationException: Exception has been thrown by the target of an invocation.
---> System.Reflection.TargetInvocationException: Exception has been thrown by the target of an invocation.
---> System.Reflection.TargetInvocationException: Exception has been thrown by the target of an invocation.
---> System.OutOfMemoryException: Exception of type 'System.OutOfMemoryException' was thrown.
**Additional context**
When loading models which size are less than 100MB, no problem.
Contributor guide
Assessment
This issue has not been assessed yet.