Skip to content

Latest commit

 

History

History

dcgan

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 
 
 
 
 

Deep Convolutional Generative Adversarial Networks

Loss Function

  • used sce loss at D/G nets.

Architecture Networks

  • Same as DCGAN paper.
DIFFS DCGAN Paper ME
Weight initializer normal dist HE initializer
z noise 100 128

Normal Distribution Initializer : (µ = 0, σ = 0.02)
HE Initializer parameters : (factor = 1, FAN_AVG, uniform)

Tensorboard

result

Elapsed Time : 3h 5m 32s with GTX 1060 6GB x 1

Result

Name Global Step 5k Global Step 10k Global Step 20k
DCGAN img img img

To-Do