def define_C(gpu_ids=[]):
use_gpu = len(gpu_ids) > 0
if use_gpu:
assert (torch.cuda.is_available())
netC = Classifier()
if use_gpu:
netC.cuda(device=gpu_ids[0])
#netC.apply(weights_init)
return netC
def define_C(gpu_ids=[]):
"""
gender preserving classifier
:param gpu_ids:
:return:
"""
use_gpu = len(gpu_ids) > 0
if use_gpu:
assert (torch.cuda.is_available())
netC = Classifier()
if use_gpu:
netC.cuda(device=gpu_ids[0])
# netC.apply(weights_init)
return netC
def get_modules(opt):
modules = {}
disc = Discriminator()
gen = Generator()
clf = Classifier()
if opt.cuda:
disc = disc.cuda()
gen = gen.cuda()
clf = clf.cuda()
modules['Discriminator'] = disc
modules['Generator'] = gen
modules['Classifier'] = clf
return modules
data_itr_tgt = get_data_iter("USPS", train=True)
pos_labels = Variable(torch.Tensor([1]))
neg_lables = Variable(torch.Tensor([-1]))
g_step = 0
g_loss_durations = []
d_loss_durations = []
c_loss_durations = []
# take variable into cuda
if use_cuda:
generator.cuda()
generator_larger.cuda()
critic.cuda()
classifier.cuda()
pos_labels = pos_labels.cuda()
neg_lables = neg_lables.cuda()
# for 循环
for epoch in range(params.num_epochs):
# break
# 训练 鉴别器
# 开启求 鉴别器的梯度
for p in critic.parameters():
p.requires_grad = True
# 设置 鉴别器的训练步数
if g_step < 25 or g_step % 500 == 0:
# this helps to start with the critic at optimum
# even in the first iterations.
critic_steps = 100