RadeonML
RadeonML copied to clipboard
GPUOpen-LibrariesAndSDKs
**Hello Running GetOutputInfo funtion of rml::Model will throw a error, when onnx model has more than three ConvTranspose2d. My test model structure is very simple and consists of multiple blocks,...
Hi, how I can force rmlCreateDefaultContext to use my "Radeon Frontier" and not the NVidia GPU ?
[This ONNX model](https://github.com/microsoft/DNS-Challenge/blob/master/NSNet2-baseline/nsnet2-20ms-baseline.onnx) cannot be ingested by the RML: ``` rml::Context context = rml::CreateDefaultContext(); std::wstring model_path(L"C:\\path\\to\\nsnet2-20ms-baseline.onnx"); rml::Graph graph = rml::LoadGraphFromFile(model_path); // throws exception ``` The specific error is: ``` INFO:...
Hi, I am using RadeonML on windows 10 , trying to run mobilnetv2 and fails, although mobilnetv2 is listed as supported by MIopen the error I get : Unsupported GPU...
It seems there hasn't been an update in months. Is there hope for Windows-OpenCL users to gain access to MIOpen functionality? What is AMD plan?
I am working with the following onnx file: [link ](https://1drv.ms/u/s!ApkpQgJnXKOBgppBflpVMYhjOjcW4g?e=Zivktn) I successfully initialized rml context from an OpenCL command_queue and tried to build a graph. It fails due to the...
Hi, with the MaskRnn model from https://github.com/onnx/models/tree/master/vision/object_detection_segmentation/mask-rcnn rmlLoadModel returns the error "Unsupported attribute type: 4" With my own model I get the same error. What must I change In in...
Hi, I think there is a chaos with the macro RML_CHECK und CHECK. The sample exit when the RML function are returning RML_OK, because the macro RML_CHECK is called with...
Hi, my model has multiple outputs, and it would be fine if there are functions for get the number of outputs and there names. Like it is already implemented for...