found it.
` fpr, tpr, thresholds = my_roc_calc(my_input)
t = Task.get_task(my_task_id)
t.get_logger().report_scatter2d("ROC", "MyModel",iteration=1, scatter=list(zip(fpr, tpr))) `
Is there a way to upload an ROC curve with its underlying data?
The use-case: I have trained several models and I want to compare their different working points and curves
found it.
` fpr, tpr, thresholds = my_roc_calc(my_input)
t = Task.get_task(my_task_id)
t.get_logger().report_scatter2d("ROC", "MyModel",iteration=1, scatter=list(zip(fpr, tpr))) `