np.transpose(
vutils.make_grid(real_batch[0][0:64], padding=2, normalize=True),
(1, 2, 0)))
plt.show()
fig.savefig('genImages/trainImages-ts{}.png'.format(int(time.time())))
#Discriminator
discriminator = Discriminator.DNet(ngpu).to(device)
# Handle multi-gpu if desired
if (device.type == 'cuda') and (ngpu > 1):
discriminator = nn.DataParallel(discriminator, list(range(ngpu)))
#-------------------------------------#
#Generator
#Generating images from noise
generator = Generator.GNet(ngpu).to(device)
# Handle multi-gpu if desired
if (device.type == 'cuda') and (ngpu > 1):
generator = nn.DataParallel(generator, list(range(ngpu)))
gimageList = []
fixedNoise = torch.randn(8, 100, 1, 1, device=device)
loss_fuction = nn.BCELoss()
gOptimizer = optim.Adam(generator.parameters(), lr=0.0002, betas=(0.5, 0.999))
dOptimizer = optim.Adam(discriminator.parameters(),
lr=0.0002,
betas=(0.5, 0.999))
errG = []
