ARCHIVED: Contains historical course materials/Homework materials for the FREE MOOC course on "Creative Applications of Deep Learning w/ Tensorflow" #CADL
In the code for the VAE function (lines 97-102 as per bcdb0191ce65c29e8434243aab2016dd89a1b752) appears to be a bug that prevents the usage of corrupted inputs:
if denoising:
current_input = utils.corrupt(x) * corrupt_prob + x * (1 - corrupt_prob)
# 2d -> 4d if convolution
x_tensor = utils.to_tensor(x) if convolutional else x
current_input = x_tensor
Here, the current_input tensor is directly overwritten by x_tensor. It appears to be the case for all sessions.
In the code for the
VAE
function (lines 97-102 as per bcdb0191ce65c29e8434243aab2016dd89a1b752) appears to be a bug that prevents the usage of corrupted inputs:Here, the
current_input
tensor is directly overwritten byx_tensor
. It appears to be the case for all sessions.