// load/define networks
// The naming conversion is different from those used in the paper
// Code (paper): G_A (G), G_B (F), D_A (D_Y), D_B (D_X)
self.netG_A = networks.define_G(opt.input_nc, opt.output_nc,
opt.ngf, opt.which_model_netG, opt.norm, not opt.no_dropout, opt.init_type, self.gpu_ids)
self.netG_B = networks.define_G(opt.output_nc, opt.input_nc,
opt.ngf, opt.which_model_netG, opt.norm, not opt.no_dropout, opt.init_type, self.gpu_ids)
if self.isTrain:
use_sigmoid = opt.no_lsgan
self.netD_A = networks.define_D(opt.output_nc, opt.ndf,
opt.which_model_netD,
opt.n_layers_D, opt.norm, use_sigmoid, opt.init_type, self.gpu_ids)
self.netD_B = networks.define_D(opt.input_nc, opt.ndf,
opt.which_model_netD,
opt.n_layers_D, opt.norm, use_sigmoid, opt.init_type, self.gpu_ids)
if not self.isTrain or opt.continue_train:
which_epoch = opt.which_epoch
self.load_network(self.netG_A, "G_A", which_epoch)
self.load_network(self.netG_B, "G_B", which_epoch)
if self.isTrain:
self.load_network(self.netD_A, "D_A", which_epoch)
self.load_network(self.netD_B, "D_B", which_epoch)
if self.isTrain:
self.fake_A_pool = ImagePool(opt.pool_size)
self.fake_B_pool = ImagePool(opt.pool_size)
// define loss functions
After Change
def name(self):
return "CycleGANModel"
def initialize(self, opt):
BaseModel.initialize(self, opt)
// specify the training losses you want to print out. The program will call base_model.get_current_errors
self.loss_names = ["D_A", "G_A", "cycle_A", "idt_A", "D_B", "G_B", "cycle_B", "idt_B"]
// specify the images you want to save/display. The program will call base_model.get_current_visuals
visual_names_A = ["real_A", "fake_B", "rec_A"]
visual_names_B = ["real_B", "fake_A", "rec_B"]
if self.isTrain and self.opt.lambda_identity > 0.0:
visual_names_A.append("idt_A")
visual_names_B.append("idt_B")
self.visual_names = visual_names_A + visual_names_B
// specify the models you want to save to the disk. The program will call base_model.save
if self.isTrain:
self.model_names = ["G_A", "G_B", "D_A", "D_B"]
else: // during test time, only load Gs
self.model_names = ["G_A", "G_B"]
// load/define networks
// The naming conversion is different from those used in the paper
// Code (paper): G_A (G), G_B (F), D_A (D_Y), D_B (D_X)
self.netG_A = networks.define_G(opt.input_nc, opt.output_nc,
opt.ngf, opt.which_model_netG, opt.norm, not opt.no_dropout, opt.init_type, self.gpu_ids)
self.netG_B = networks.define_G(opt.output_nc, opt.input_nc,
opt.ngf, opt.which_model_netG, opt.norm, not opt.no_dropout, opt.init_type, self.gpu_ids)
if self.isTrain:
use_sigmoid = opt.no_lsgan
self.netD_A = networks.define_D(opt.output_nc, opt.ndf,
opt.which_model_netD,
opt.n_layers_D, opt.norm, use_sigmoid, opt.init_type, self.gpu_ids)
self.netD_B = networks.define_D(opt.input_nc, opt.ndf,
opt.which_model_netD,
opt.n_layers_D, opt.norm, use_sigmoid, opt.init_type, self.gpu_ids)
if not self.isTrain or opt.continue_train:
self.load_networks(opt.which_epoch)
if self.isTrain:
self.fake_A_pool = ImagePool(opt.pool_size)
self.fake_B_pool = ImagePool(opt.pool_size)
