Task1: clarification of axis used in BatchNormalization layer

DCASE-REPO / dcase2018_baseline

DCASE 2018 Baseline systems

MIT License

128 stars 78 forks source link

Task1: clarification of axis used in BatchNormalization layer #18

Closed SyedNaser closed 5 years ago

SyedNaser commented 5 years ago

The input format used in this task is "channel_last", i.e., input(Batch, MelBands, Time, 1), and the batch normalization is performed on "axis=1". The Keras documentation states that with data_format="channel_first" use "axis=1".

I am a bit confused about the axis used in batch normalization.

toni-heittola commented 5 years ago

Yes, this is a bug in the parameter file. Correct axis for the batch normalization is of course the last axis, i.e. axis=-1.

Fortunately this will not change results of the system much. Classification accuracy for development dataset was 59.7 +/- 0.7 (over 10 independent trials), and after the axis-fix it is 59.9 +/- 1.3.