ZeroDivisionError when validating the trained model

[VedantKhairnar]

This is with respect to this Colab file
After training the model, when it is to be validated using

accuracy, class_based_accuracy = gtf.Evaluate();

ZeroDivision Error was observed
Following is the exact log

--------------------------------------------------------------------------- ZeroDivisionError Traceback (most recent call last) <ipython-input-281-e9c57d0b7fc4> in <module>() 1 # Run validation ----> 2 accuracy, class_based_accuracy = gtf.Evaluate(); monk_v1/monk/system/imports.py in decorator_wrapper(*function_args, **function_args_dicts) monk_v1/monk/gluon/finetune/level_14_master_main.py in Evaluate(self) monk_v1/monk/system/imports.py in decorator_wrapper(*function_args, **function_args_dicts) monk_v1/monk/gluon/finetune/level_4_evaluation_base.py in set_evaluation_final(self) ZeroDivisionError: division by zero

How can this be resolved?

[abhi-kumar]

Please verify the number of classes in training and validation are the same.

[VedantKhairnar]

They are 15 classes in both training and validation.

[abhi-kumar]

in both the training and inference times, print

ptf.system_dict["dataset"]["params"]["classes"]

And check if there's a blank class in it or not