Missing parenthesis in loss

[ctiennot]

Hi again,

In the file model.py at line 46, shouldn't:
cost = tf.reduce_mean(sum_square_d / 55.0*74.0 - 0.5*sqare_sum_d / math.pow(55*74, 2))

be replaced by
cost = tf.reduce_mean(sum_square_d / (55.0*74.0) - 0.5*sqare_sum_d / math.pow(55*74, 2))

to match equation (4) form the paper? (I think you just forgot the parenthesis).

Best,

Clement

[drstarson]

@ctiennot Did you succeed training the model and getting the results after adding the parenthesis. It looks like the parenthesis are needed, but after adding them, the system doesn't seem to be training well. I'm getting low loss (~0.2), but the resulting depth images are all black. Would appreciate any advice or additional info.

[josslynZcn]

@drstarson i have experience the same problem with you. and i wonder if you solve this problem .would appreciate with the solution about this problen. i would be so thankful if you connect with me [email protected]