About the reltol parameter

[MayuOshima]

Hello, thanks for your excellent work!
But I have one question.
In model/pred_illuDecomp_layer.py, there is a function pinv(A, reltol=1e-6). I found that if I reserve this line:
s = tf.boolean_mask(s, s>atol)
the shape of s may become (2,) and then the shape of s_inv becomes (2, 2), which will raise error when do
tf.matmul(s_inv, tf.transpose(u))

So I want to know why need to clear entries lower than reltols_max ?
Does it matter if I don't clear entries lower than reltols_max ?

Thank you!

[MayuOshima]

Oh, it maybe because the mask I put into the network is 0,1 form. After I convert it to 255 form, the problem does not happen anymore.