Generator outputs of StackedGAN
After training the StackedGAN for 10,000 steps, the Generator0 and Generator1 models are saved on files. Stacked together, Generator0 and Generator1 can synthesize fake images conditioned on label and noise codes, z0 and z1.
The StackedGAN generator can be qualitatively validated by:
Varying the discrete labels from 0 to 9 with both noise codes, z0 and z1 sampled from a normal distribution with a mean of 0.5 and standard -deviation of 1.0. The results are shown in Figure 6.2.9. We're able to see that the StackedGAN discrete code can control the digits produced by the generator:
python3 stackedgan-mnist-6.2.1.py --generator0=stackedgan_mnist-gen0.h5 --generator1=stackedgan_mnist-gen1.h5 --digit=0 python3 stackedgan-mnist-6.2.1.py --generator0=stackedgan_mnist-gen0.h5 --generator1=stackedgan_mnist-gen1.h5 --digit=9
to
Varying the first noise code, z0, as a constant vector from -4.0 to 4.0 for digits 0 to 9 as shown as follows. The second noise...
