Great work

[ChrisProgramming2018]

Hello :),

I found your great project, one the way of also loading a Python model for a University project
Maybe you are so kind that you could send it to me
Because at the moment I don't understand why you use the 'loss'
in the CustomVision.cs line 50

Thank you very much for your help in advance

Best Regards
Chris

[VolodymyrChechel]

Did you solve this problem?

[DiegoVil]

I have the same issue. As soon as I arrive to this line : runner.AddInput(graph["Placeholder"][0], tensor).Fetch(graph["loss"][0]); I have "Object reference not set to an instance of an object." exception.This happens when I use my own model with my own labels. Maybe I am missing something. And agree is great project.

{System.NullReferenceException: Object reference not set to an instance of an object.
at CustomVisionCLI.CustomVision.Main() in C:\Users\XXXX\YYYYY\CustomVision-TensorFlow-CSharp-master\CustomVision-TensorFlow-CSharp-master\CustomVision.cs:line 50
--- End of stack trace from previous location where exception was thrown ---
at System.Runtime.ExceptionServices.ExceptionDispatchInfo.Throw()
at PowerArgs.ObjectEx.InvokeMainMethod(Object o)
at PowerArgs.Args.<>c__DisplayClass15_1.b__1()
at PowerArgs.Args.Execute[T](Func1 argsProcessingCode) at PowerArgs.Args.<>c__DisplayClass15_0.<InvokeMain>b__0(String[] a) at PowerArgs.REPL.DriveREPL[T](TabCompletion t, Func2 eval, String[] args, Func`1 defaultEval)
at PowerArgs.Args.InvokeMain(CommandLineArgumentsDefinition definition, String[] args)
at PowerArgs.Args.InvokeMain[T](String[] args)
at CustomVisionCLI.Program.Main(String[] args) in C:\Users\XXX\YYYY\CustomVision-TensorFlow-CSharp-master\CustomVision-TensorFlow-CSharp-master\Program.cs:line 8}

[DiegoVil]

Ok, I know the reason of this problem. YOu need to do the project in customvision.ai from the beginning. In my previous test I have changed one iteration to compact.

[daltskin]

Correct - this is for CustomVision.ai projects only.