Classification callbacks
Note:
Starting in Maximo® Visual Inspection 8.7, custom models are not supported. Custom models are still supported in Maximo Visual Inspection 8.6 and earlier versions.
Use this callback when the custom model is trained for image classification.
def updateTrainMetrics(current_iter, max_iter, loss, epoch)
Handler for status updates from the training process. This handler should be called actively by your custom code to post the training status to the IBM® Maximo Visual Inspection user interface.
- Input
-
- current_iter (int)
- Current iteration in the epoch
- max_iter (int)
- Maximum iterations in one epoch
- loss (float)
- Training loss
- epoch (int)
- Current training epoch
- Example
-
monitor_handler.updateTrainMetrics(current_iter, max_iter, loss, epoch) - Output
- None
def updateTestMetrics(current_iter, accuracy, loss, epoch)
Handler for status updates from the testing process. This handler should be called actively by your custom code to post the testing status to the IBM Maximo Visual Inspection user interface.
- Input
-
- current_iter (int)
- Current iteration in the epoch
- accuracy (float)
- Testing accuracy
- loss (float)
- Training loss
- epoch (int)
- Current training epoch
- Example
monitor_handler.updateTrainMetrics(iter_num, accuracy, loss, epoch_num)- Output
- None