Condensation Criterion in the Learned Group Convolution

[showgood163]

In model.py, line 131, the condensation criterion:

wis = tf.reduce_sum(wi, axis=-1) # (w_in,)

probably should be:

wis = tf.reduce_sum(tf.abs(wi), axis=-1) # (w_in,)

Beacuse in the original paper authors uses 'the averaged absolute value of weights'.

[markdtw]

Hi,

Sorry for the late reply. The weights are the absolute values already because of this line.

Thanks!