low-end GPU VRAM full causing onnxruntime Integer overflow

[takov751]

Describe the bug I have tested GPU support on a laptop with geforce 840m 2GB VRAM. After 6-8 times mimic3 starts showing errors. After short investigation turned out GPU memory is full as application size in VRAM only grows.

To Reproduce Steps to reproduce the behavior:

1. Run tests ony mimic3
2. Watch GPU VRAM goes up

Expected behavior VRAM size should be considered, while app running.

Log files

onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running Conv node. Name:'Conv_5953' Status Message: /onnxruntime_src/onnxruntime/core/common/safeint.h:17 static void SafeIntExceptionHandler<onnxruntime::OnnxRuntimeException>::SafeIntOnOverflow() Integer overflow

You may also include screenshots, however screenshots of log files are often difficult to read and parse.

If you are running Mycroft, the Support Skill helps to automate gathering this information. Simply say "Create a support ticket" and the Skill will put together a support package and email it to you.

Environment (please complete the following information):

• Device type: Laptop CPU i3-4020U , gefore 840m 2GB, 8GB RAM
• OS: Ubuntu 22.04
• Mycroft-core version: docker-gpu
• Other versions: git main as it was built

Additional context

[takov751]

Not a bug. 2gb vram not enough for any Machine Learning project with this configuration.