complex batch norm2d track_running_stats=False produce error

[nisanaryal]

(1 - exponential_average_factor) self.running_mean TypeError: unsupported operand type(s) for : 'float' and 'NoneType'

There is a bug in batch normalization, when we initialize with track_running_stats=False , the parameters arent initialized(as expected) but in training it tries to update running mean and running covariance.

error occurs at this line self.running_mean = exponential_average_factor * mean \

• (1 - exponential_average_factor) * self.running_mean I think we need to keep this inside the loop checking the status of track_running_stats. And might have to change while self.training is false as well(havent checked this though).

[wavefrontshaping]

Indeed, track_running_stats was not checked correctly for eval mode. Should be good now.