the maskRCNN model seems not be able to trace correctly?

[healthmatrice]

We get warnings like this

fast_rcnn.py:155: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
  if num_bbox_reg_classes == 1:

the num_bbox_reg_classes should varied according to different input