def save_samples(gan, i_iter):
gan.netG.eval()
if 'noise' not in save_samples.__dict__:
save_samples.noise = Variable(gan.gen_latent_noise(410, opt.nz))
if not os.path.exists(opt.path + 'tmp/'):
os.makedirs(opt.path + 'tmp/')
y = np.repeat(np.arange(41), 10)
y = torch.autograd.Variable(torch.from_numpy(y))
if gan.opt.cuda:
y = y.cuda()
noise = save_samples.noise
noise = gan.join_xy((noise, y))
fake = netG(noise)
fake = fake.view(-1, 2, 48, 80)
fake_01 = torch.FloatTensor(len(fake), 3, 48, 80).fill_(-1)
fake_01[:, :2, :, :] = (fake.data.cpu() + 1.0) * 0.5
# print(fake_01.min(), fake_01.max())
save_image(fake_01,
opt.path + 'tmp/' + '{:0>5}.png'.format(i_iter),
nrow=10)
# alkjfd
gan.netG.train()
def save_samples(gan, i_iter):
if 'noise' not in save_samples.__dict__:
save_samples.noise = Variable(gan.gen_latent_noise(64, opt.nz))
if not os.path.exists(opt.path + 'tmp/'):
os.makedirs(opt.path + 'tmp/')
fake = gan.gen_fake_data(64, opt.nz, noise=save_samples.noise)
# fake = next(data_iter)
fake_01 = (fake[0].data.cpu() + 1.0) * 0.5
save_image(fake_01, opt.path + 'tmp/' + '{:0>5}.jpeg'.format(i_iter))
def save_samples(gan, i_iter):
gan.netG.eval()
if 'noise' not in save_samples.__dict__:
save_samples.noise = Variable(gan.gen_latent_noise(41 * 34, opt.nz))
if not os.path.exists(opt.path + 'tmp/'):
os.makedirs(opt.path + 'tmp/')
y1 = np.repeat(np.arange(41), 34)
# go = np.array((41*34, 295))
# for i, y in enumerate(y1):
# go[i,:] = data.go_dict[data.id2prt[y1[i]]]
# go = torch.autograd.Variable(torch.from_numpy(go))
y1 = torch.autograd.Variable(torch.from_numpy(y1))
if gan.opt.cuda:
y1 = y1.cuda()
y2 = np.tile(np.arange(34), 41)
y2 = torch.autograd.Variable(torch.from_numpy(y2))
if gan.opt.cuda:
y2 = y2.cuda()
noise = save_samples.noise
# noise = gan.join_xy((noise, y))
fake = netG(noise, y1, y2)
# fake = netG(noise)
fake = fake.view(-1, 2, 48, 128)
fake_01 = torch.FloatTensor(len(fake), 3, 48, 128).fill_(-1)
fake_01[:, :2, :, :] = (fake.data.cpu() + 1.0) * 0.5
# print(fake_01.min(), fake_01.max())
save_image(fake_01,
opt.path + 'tmp/' + '{:0>5}.png'.format(i_iter),
nrow=34)
# alkjfd
gan.netG.train()
def save_samples(gan, i_iter):
gan.netG.eval()
if 'noise' not in save_samples.__dict__:
save_samples.noise = Variable(gan.gen_latent_noise(64, opt.nz))
if not os.path.exists(opt.path + 'tmp/'):
os.makedirs(opt.path + 'tmp/')
fake = gan.gen_fake_data(64, opt.nz, noise=save_samples.noise)
# fake = next(data_iter)
# print(fake.min(), fake.max())
fake = fake.view(-1, 3, 32, 32)
fake_01 = (fake.data.cpu() + 1.0) * 0.5
# print(fake_01.min(), fake_01.max())
save_image(fake_01, opt.path + 'tmp/' + '{:0>5}.jpeg'.format(i_iter))
# alkjfd
gan.netG.train()
def save_samples(gan, i_iter):
gan.netG.eval()
if 'noise' not in save_samples.__dict__:
save_samples.noise = Variable(gan.gen_latent_noise(64, opt.nz))
if not os.path.exists(opt.path + 'tmp/'):
os.makedirs(opt.path + 'tmp/')
fake = gan.gen_fake_data(64, opt.nz, noise=save_samples.noise)
# fake = next(data_iter)
fake_list = []
for i in range(len(fake)):
for j in range(41):
img = torch.stack([fake[i, 0, :, :], fake[i, j + 1, :, :]], dim=0)
fake_list.append(img)
fake = torch.FloatTensor(len(fake_list), 3, 48, 80)
fake_tensor = torch.stack(fake_list, dim=0)
# print(type(fake_tensor))
# print(type(fake))
fake[:, :2, :, :] = fake_tensor.data
fake[:, 2, :, :] = -1
# fake = next(data_iter)
# print(fake.min(), fake.max())
# fake = fake.view(-1, 3, 32, 32)
fake_01 = (fake.cpu() + 1.0) * 0.5
# print(fake_01.min(), fake_01.max())
save_image(fake_01,
opt.path + 'tmp/' + '{:0>5}.png'.format(i_iter),
nrow=41)
gan.netG.train()
