Open DiegoVil opened 5 years ago
I haven't tried this with object detection. But something along the lines of this might help?
runner.AddInput(graph["Placeholder"][0], tensor).Fetch("model_outputs");
var output = runner.Run();
var result = output[0];
var boxes = (float[][][][])result.GetValue(jagged: true);
Did you get anywhere with this?
No. This approach did not work for me. The problem is how to get the probabilities...
This is not an issue, just an idea. How I should handle the object detection from the customvision.ai model? I define this input :
runner.AddInput(graph["Placeholder"][0], tensor).Fetch(graph["model_outputs"][0]);
but I have no idea on how to handle it.