def main(): # init random seed init_random_seed(params.manual_seed) # Load dataset mnist_data_loader = get_mnist(train=True, download=True) mnist_data_loader_eval = get_mnist(train=False, download=True) usps_data_loader = get_usps(train=True, download=True) usps_data_loader_eval = get_usps(train=False, download=True) # Model init Revgard tgt_encoder = model_init(Encoder(), params.tgt_encoder_revgrad_path) critic = model_init(Discriminator(), params.disc_revgard_path) clf = model_init(Classifier(), params.clf_revgrad_path) # Train models print("====== Training source encoder and classifier in MNIST and USPS domains ======") if not (tgt_encoder.pretrained and clf.pretrained and critic.pretrained and params.model_trained): tgt_encoder, clf, critic = train_revgrad(tgt_encoder, clf, critic, mnist_data_loader, usps_data_loader, robust=False) # Eval target encoder on test set of target dataset print("====== Evaluating classifier for encoded MNIST and USPS domain ======") print("-------- MNIST domain --------") eval_tgt(tgt_encoder, clf, mnist_data_loader_eval) print("-------- USPS adaption --------") eval_tgt(tgt_encoder, clf, usps_data_loader_eval)
def main(): # init random seed init_random_seed(params.manual_seed) # Load dataset svhn_data_loader = get_svhn(split='train', download=True) svhn_data_loader_eval = get_svhn(split='test', download=True) mnist_data_loader = get_mnist(train=True, download=True) mnist_data_loader_eval = get_mnist(train=False, download=True) # Model init WDGRL tgt_encoder = model_init(Encoder(), params.encoder_wdgrl_path) critic = model_init(Discriminator(in_dims=params.d_in_dims, h_dims=params.d_h_dims, out_dims=params.d_out_dims), params.disc_wdgrl_path) clf = model_init(Classifier(), params.clf_wdgrl_path) # Train critic to optimality print("====== Training critic ======") if not (critic.pretrained and params.model_trained): critic = train_critic_wdgrl(tgt_encoder, critic, svhn_data_loader, mnist_data_loader) # Train target encoder print("====== Training encoder for both SVHN and MNIST domains ======") if not (tgt_encoder.pretrained and clf.pretrained and params.model_trained): tgt_encoder, clf = train_tgt_wdgrl(tgt_encoder, clf, critic, svhn_data_loader, mnist_data_loader, robust=False) # Eval target encoder on test set of target dataset print("====== Evaluating classifier for encoded SVHN and MNIST domains ======") print("-------- SVHN domain --------") eval_tgt(tgt_encoder, clf, svhn_data_loader_eval) print("-------- MNIST adaption --------") eval_tgt(tgt_encoder, clf, mnist_data_loader_eval)
def main(): # init random seed init_random_seed(params.manual_seed) # Load dataset mnist_data_loader = get_mnist(train=True, download=True) mnist_data_loader_eval = get_mnist(train=False, download=True) usps_data_loader = get_usps(train=True, download=True) usps_data_loader_eval = get_usps(train=False, download=True) # Model init WDGRL tgt_encoder = model_init(Encoder(), params.encoder_wdgrl_rb_path) critic = model_init(Discriminator(), params.disc_wdgrl_rb_path) clf = model_init(Classifier(), params.clf_wdgrl_rb_path) # Train target encoder print("====== Robust Training encoder for both MNIST and USPS domains ======") if not (tgt_encoder.pretrained and clf.pretrained and params.model_trained): tgt_encoder, clf = train_tgt_wdgrl(tgt_encoder, clf, critic, mnist_data_loader, usps_data_loader, usps_data_loader_eval, robust=True) # Eval target encoder on test set of target dataset print("====== Evaluating classifier for encoded MNIST and USPS domains ======") print("-------- MNIST domain --------") eval_tgt_robust(tgt_encoder, clf, mnist_data_loader_eval) print("-------- USPS adaption --------") eval_tgt_robust(tgt_encoder, clf, usps_data_loader_eval)
def test(model_config): mode = 'test' batch_size = 1 dataset = ShakespeareModern(train_shakespeare_path, test_shakespeare_path, train_modern_path, test_modern_path, mode=mode) dataloader = DataLoader(dataset, batch_size=batch_size, shuffle=False) shakespeare_disc = Discriminator(model_config['embedding_size'], model_config['hidden_dim'], len(dataset.vocab)).cuda() shakespeare_disc.load_state_dict(torch.load('./shakespeare_disc.pth')) shakespeare_disc.eval() num_correct = 0 total_samples = 0 for idx, (s, s_addn_feats, m, m_addn_feats) in tqdm(enumerate(dataloader)): s = s.transpose(0, 1) m = m.transpose(0, 1) total_samples += 2 s = Variable(s).cuda() s_output = shakespeare_disc(s, s_addn_feats) if round(s_output.item()) == 1.0: num_correct += 1 m = Variable(m).cuda() m_output = shakespeare_disc(m, m_addn_feats) if round(m_output.item()) == 0.0: num_correct += 1 print ('Accuracy: {}'.format(num_correct/total_samples))
def main(): # init random seed init_random_seed(params.manual_seed) # Load dataset mnist_data_loader = get_usps(train=True, download=True) mnist_data_loader_eval = get_usps(train=False, download=True) usps_data_loader = get_usps(train=True, download=True) usps_data_loader_eval = get_usps(train=False, download=True) # Model init ADDA src_encoder = model_init(Encoder(), params.src_encoder_adda_rb_path) tgt_encoder = model_init(Encoder(), params.tgt_encoder_adda_rb_path) critic = model_init(Discriminator(), params.disc_adda_rb_path) clf = model_init(Classifier(), params.clf_adda_rb_path) # Train source model for adda print( "====== Robust training source encoder and classifier in MNIST domain ======" ) if not (src_encoder.pretrained and clf.pretrained and params.model_trained): src_encoder, clf = train_src_robust(src_encoder, clf, mnist_data_loader) # Eval source model print("====== Evaluating classifier for MNIST domain ======") eval_tgt(src_encoder, clf, mnist_data_loader_eval) # Train target encoder print("====== Robust training encoder for USPS domain ======") # Initialize target encoder's weights with those of the source encoder if not tgt_encoder.pretrained: tgt_encoder.load_state_dict(src_encoder.state_dict()) if not (tgt_encoder.pretrained and critic.pretrained and params.model_trained): tgt_encoder = train_tgt_adda(src_encoder, tgt_encoder, clf, critic, mnist_data_loader, usps_data_loader, usps_data_loader_eval, robust=True) # Eval target encoder on test set of target dataset print("====== Ealuating classifier for encoded USPS domain ======") print("-------- Source only --------") eval_tgt(src_encoder, clf, usps_data_loader_eval) print("-------- Domain adaption --------") eval_tgt(tgt_encoder, clf, usps_data_loader_eval)
def main(): opt = get_opt() print(opt) print("Start to train stage: %s" % (opt.stage)) # create dataset if opt.stage == "Shape": dataset = PolyDatasetShape(128) train_loader = DataLoader(dataset, batch_size=opt.b, shuffle=False, num_workers=opt.j, drop_last=True, pin_memory=True) elif opt.stage == "Stitch": dataset = PolyDatasetStitch(128) train_loader = DataLoader(dataset, batch_size=opt.b, shuffle=False, num_workers=opt.j, drop_last=True, pin_memory=True) elif opt.stage == "Refine": dataset = PolyDatasetRefine(128) train_loader = DataLoader(dataset, batch_size=opt.b, shuffle=False, num_workers=opt.j, drop_last=True, pin_memory=True) else: sys.exit("Please mention the Stage from [Shape, Stitch, Refine]") if not os.path.exists(opt.results): os.makedirs(opt.results) netG = GeneratorCoarse(opt.input_channel, 3) netD = Discriminator() # create model & train & save the final checkpoint netG.cuda() netD.cuda() netG.apply(weights_init_normal) netD.apply(weights_init_normal) train(opt, train_loader, netG, netD) print('Finished training %s!' % (opt.stage))
def main(): # init random seed init_random_seed(params.manual_seed) # Load dataset svhn_data_loader = get_svhn(split='train', download=True) svhn_data_loader_eval = get_svhn(split='test', download=True) mnist_data_loader = get_mnist(train=True, download=True) mnist_data_loader_eval = get_mnist(train=False, download=True) # Model init DANN tgt_encoder = model_init(Encoder(), params.tgt_encoder_dann_rb_path) critic = model_init( Discriminator(in_dims=params.d_in_dims, h_dims=params.d_h_dims, out_dims=params.d_out_dims), params.disc_dann_rb_path) clf = model_init(Classifier(), params.clf_dann_rb_path) # Train models print( "====== Training source encoder and classifier in SVHN and MNIST domains ======" ) if not (tgt_encoder.pretrained and clf.pretrained and critic.pretrained and params.model_trained): tgt_encoder, clf, critic = train_dann(tgt_encoder, clf, critic, svhn_data_loader, mnist_data_loader, mnist_data_loader_eval, robust=True) # Eval target encoder on test set of target dataset print( "====== Evaluating classifier for encoded SVHN and MNIST domains ======" ) print("-------- SVHN domain --------") eval_tgt_robust(tgt_encoder, clf, svhn_data_loader_eval) print("-------- MNIST adaption --------") eval_tgt_robust(tgt_encoder, clf, mnist_data_loader_eval)
torch.backends.cudnn.enabled = True torch.backends.cudnn.benchmark = True quant = True if 'GS8' in args.base_model_str else False subnet_model_path = os.path.join('subnet_structures', args.dataset, args.task, args.base_model_str, 'pth') ## Networks # G: dim_lst_path = os.path.join(subnet_model_path, 'epoch%d_netG.npy' % 199) netG = Generator(args.input_nc, args.output_nc, dim_lst=np.load(dim_lst_path), quant=quant).cuda() # D: netD = Discriminator(args.input_nc).cuda() ## results_dir: optimizer_str = 'adam_lr%s_wd%s' % (args.lr, args.wd) loss_str = 'beta%s_%s' % (args.beta, args.lc) results_dir = os.path.join('finetune_results', args.dataset, args.task, args.base_model_str, '%s_%s' % (optimizer_str, loss_str)) img_dir = os.path.join(results_dir, 'img') pth_dir = os.path.join(results_dir, 'pth') create_dir(img_dir), create_dir(pth_dir) # Optimizers optimizer_G = torch.optim.Adam(netG.parameters(), lr=args.lr, weight_decay=args.wd,
parser.add_argument("--lambda_gp", type=int, default=10, help="lambda for gradient penalty") opt = parser.parse_args() exp_folder = "{}_{}".format(opt.exp_folder, opt.target_set) os.makedirs("./exps/" + exp_folder, exist_ok=True) # Loss function adversarial_loss = torch.nn.BCEWithLogitsLoss() distance_loss = torch.nn.L1Loss() # Initialize generator and discriminator generator = Generator() discriminator = Discriminator() if torch.cuda.is_available(): device = torch.device('cuda:0') generator.to(device) discriminator.to(device) adversarial_loss.to(device) # Visualize a single batch def visualizeSingleBatch(fp_loader_test, opt, exp_folder, batches_done, batch_size=8): print('Loading saved model ... \n{}'.format( './checkpoints/{}_{}.pth'.format(exp_folder, batches_done)))
try: model.trans.load_state_dict(torch.load(sys.argv[2])) model.atmos.load_state_dict(torch.load(sys.argv[3])) ''' for param in model.trans.parameters(): param.requires_grad = False for param in model.atmos.parameters(): param.requires_grad = False ''' except Exception as e: try: model.load_state_dict(torch.load(sys.argv[2])) except Exception as e: print("No weights. Training from scratch.") if MODE == 'GAN': model_d = Discriminator().to(device) optimizer_d = torch.optim.Adam(model_d.parameters(), lr=learning_rate) try: model_d.load_state_dict(torch.load(sys.argv[3])) if opt['parallel']: model_d = nn.DataParallel(model_d) except Exception as e: print("No weights. Training from scratch discrim.") else: print('MODE INCORRECT : TRANS or ATMOS or FAST or DUAL or GAN') exit() # Wrap in Data Parallel for multi-GPU use if opt['parallel']: model = nn.DataParallel(model)
iter_number = (int)(INPUT_SIZE / BATCH_SIZE) + 1 image_root = utils.download_images() train_ds = utils.load_data(image_root) train_ds = utils.prepare_train_ds(train_ds, BATCH_SIZE, BUFFER_SIZE, image_size=128) # Guild generator and discriminator model. generator_net = Generator(dtype=flags.FLAGS.dtype) generator_optimizer = tf.train.AdamOptimizer( learning_rate=flags.FLAGS.learning_rate_generator, beta1=flags.FLAGS.beta1, beta2=flags.FLAGS.beta2) discriminator_net = Discriminator(alpha=flags.FLAGS.alpha, dtype=flags.FLAGS.dtype) discriminator_optimizer = tf.train.AdamOptimizer( learning_rate=flags.FLAGS.learning_rate_discriminator, beta1=flags.FLAGS.beta1, beta2=flags.FLAGS.beta2) # Print the network structure to show that the model is well built. generator_net.build(input_shape=(None, 128)) discriminator_net.build(input_shape=(None, 128, 128, 3)) generator_net.summary() discriminator_net.summary() # Save model parameters and tensorboard information the adversarial network basepath = "./mnist/" + str(flags.FLAGS.model_id) logdir = os.path.join(basepath, "logs")
opt = parser.parse_args() print(opt) random.seed(opt.seed) torch.manual_seed(opt.seed) if torch.cuda.is_available(): torch.cuda.manual_seed(opt.seed) # Networks if opt.upsample == 'ori': netG_A2B = Generator_ori(opt.input_nc, opt.output_nc) netG_B2A = Generator_ori(opt.output_nc, opt.input_nc) else: netG_A2B = Generator(opt.input_nc, opt.output_nc) netG_B2A = Generator(opt.output_nc, opt.input_nc) netD_A = Discriminator(opt.input_nc) netD_B = Discriminator(opt.output_nc) netG_A2B.cuda() netG_B2A.cuda() netD_A.cuda() netD_B.cuda() netG_A2B.apply(weights_init_normal) netG_B2A.apply(weights_init_normal) netD_A.apply(weights_init_normal) netD_B.apply(weights_init_normal) torch.save(netG_A2B.state_dict(), "initial_weights/netG_A2B_seed_{}.pth.tar".format(opt.seed)) torch.save(netG_B2A.state_dict(),
print(args) os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu torch.backends.cudnn.enabled = True torch.backends.cudnn.benchmark = True quant = True if 'GS8' in args.base_model_str else False subnet_model_path = os.path.join('subnet_structures', args.dataset, args.task, args.base_model_str, 'pth') ## Networks # G: dim_lst_path = os.path.join(subnet_model_path, 'epoch%d_netG.npy' % 199) netG = Generator(args.input_nc, args.output_nc, dim_lst=np.load(dim_lst_path), quant=quant).cuda() # D: netD = Discriminator(args.input_nc).cuda() ## results_dir: optimizer_str = 'adam_lr%s_wd%s' % (args.lr, args.wd) loss_str = 'beta%s_%s' % (args.beta, args.lc) results_dir = os.path.join('finetune_results', args.dataset, args.task, args.base_model_str, '%s_%s' % (optimizer_str, loss_str)) img_dir = os.path.join(results_dir, 'img') pth_dir = os.path.join(results_dir, 'pth') create_dir(img_dir), create_dir(pth_dir) # Optimizers optimizer_G = torch.optim.Adam(netG.parameters(), lr=args.lr, weight_decay=args.wd, betas=(0.5, 0.999)) # lr=1e-3 optimizer_D = torch.optim.Adam(netD.parameters(), lr=args.lr, weight_decay=args.wd, betas=(0.5, 0.999)) # lr=1e-3 # LR schedulers:
return syn_feature, syn_label, syn_att """"pre-train a classifier on seen classes""" trc = utils.train_cla(data.train_feature, data.train_label, CLA, device=opts.device, ) trc.run(50, data.test_seen_feature, data.test_seen_label, save_path='./cla_model') # load best classifier pre_cla = torch.load("./cla_model/model.pt") for p in pre_cla.parameters(): # set requires_grad to False p.requires_grad = False if(opts.GD == 1): netG = Generator(opts).to(opts.device) netD = Discriminator(opts).to(opts.device) else: netG = Generator1(opts).to(opts.device) netD = Discriminator1(opts).to(opts.device) # seen reconstructor netRS = Reconstructor(opts).to(opts.device) # unseen reconstructor netRU = Reconstructor(opts).to(opts.device) if opts.optimizer == "ADAM": optimzerF = optim.Adam else: optimzerF = optim.RMSprop #train setup
loss_str = 'alpha%s_beta%s_%s' % (args.alpha, args.beta, args.lc) results_dir = os.path.join( 'distill_results', args.dataset, args.task, '%s_%s_%s_%s' % (method_str, loss_str, opt_str, W_optimizer_str)) img_dir = os.path.join(results_dir, 'img') pth_dir = os.path.join(results_dir, 'pth') create_dir(img_dir), create_dir(pth_dir) ## Networks # G: netG = Generator(args.input_nc, args.output_nc, quant=args.quant, alpha=args.alpha).cuda() # D: netD = Discriminator(args.input_nc).cuda() # FLOPs for G: netG.cpu() count_ops = measure_model(netG, 256, 256) print("#parameters: %s" % model_param_num(netG)) f = open(os.path.join(results_dir, 'model_size.txt'), 'a+') f.write('count_ops: {:.6f}M'.format(count_ops / 1024. / 1024.)) f.write("#parameters: %s" % model_param_num(netG)) f.close() netG.cuda() # Optimizers: optimizer_G = torch.optim.Adam(netG.parameters(), lr=args.lrw, weight_decay=args.wd,
opt = parser.parse_args() cuda = True if torch.cuda.is_available() else False lambda_gp = 10 multi_gpu = False exp_folder = "{}_{}".format(opt.exp_folder, opt.target_set) os.makedirs("./exps/" + exp_folder, exist_ok=True) # Loss function adversarial_loss = torch.nn.BCEWithLogitsLoss() distance_loss = torch.nn.L1Loss() # Initialize generator and discriminator generator = Generator() discriminator = Discriminator() if cuda: generator.cuda() discriminator.cuda() adversarial_loss.cuda() # Visualize a single batch def visualizeSingleBatch(fp_loader_test, opt, exp_folder, batches_done, batch_size=8): print('Loading saved model ... \n{}'.format( './checkpoints/{}_{}.pth'.format(exp_folder, batches_done))) generatorTest = Generator()
gamma_optimizer_str = 'sgd_mom%s_lrgamma%s' % (args.momentum, args.lrgamma) W_optimizer_str = 'adam_lrw%s_wd%s' % (args.lrw, args.wd) opt_str = 'e%d-b%d' % (args.epochs, args.batch_size) loss_str = 'rho%s_beta%s_%s' % (args.rho, args.beta, args.lc) results_dir = os.path.join( 'results', args.dataset, args.task, '%s_%s_%s_%s_%s' % (method_str, loss_str, opt_str, gamma_optimizer_str, W_optimizer_str)) img_dir = os.path.join(results_dir, 'img') pth_dir = os.path.join(results_dir, 'pth') create_dir(img_dir), create_dir(pth_dir) ## Networks # G: netG = Generator(args.input_nc, args.output_nc, quant=args.quant).cuda() # D: netD = Discriminator(args.input_nc).cuda() # param list: parameters_G, parameters_D, parameters_gamma = [], [], [] for name, para in netG.named_parameters(): if 'weight' in name and para.ndimension() == 1: parameters_gamma.append(para) else: parameters_G.append(para) for name, para in netD.named_parameters(): # print(name, para.size(), para.ndimension()) parameters_D.append(para) print('parameters_gamma:', len(parameters_gamma)) # Optimizers: optimizer_gamma = torch.optim.SGD(parameters_gamma,
def train(model_config, train_config): mode = 'train' dataset = ShakespeareModern(train_shakespeare_path, test_shakespeare_path, train_modern_path, test_modern_path, mode=mode) dataloader = DataLoader(dataset, batch_size=train_config['batch_size'], shuffle=False) print(dataset.domain_A_max_len) shakespeare_disc = Discriminator(model_config['embedding_size'], model_config['hidden_dim'], len(dataset.vocab), batch_size=train_config['batch_size']).cuda() shakespeare_disc.train() if train_config['continue_train']: shakespeare_disc.load_state_dict(torch.load(train_config['model_path'])) criterion = nn.BCELoss().cuda() optimizer = torch.optim.Adam(shakespeare_disc.parameters(), lr=train_config['base_lr'], weight_decay=1e-5) real_label = torch.ones((train_config['batch_size'], 1)).cuda() fake_label = torch.zeros((train_config['batch_size'], 1)).cuda() for epoch in range(train_config['num_epochs']): for idx, (s, s_addn_feats, m, m_addn_feats) in tqdm(enumerate(dataloader)): s = s.transpose(0, 1) m = m.transpose(0, 1) s = Variable(s).cuda() s_output = shakespeare_disc(s, s_addn_feats) s_loss = criterion(s_output, real_label) s_loss = 100 * s_loss optimizer.zero_grad() s_loss.backward() optimizer.step() shakespeare_disc.hidden = shakespeare_disc.init_hidden() m = Variable(m).cuda() m_output = shakespeare_disc(m, m_addn_feats) m_loss = criterion(m_output, fake_label) m_loss = 100 * m_loss optimizer.zero_grad() m_loss.backward() optimizer.step() shakespeare_disc.hidden = shakespeare_disc.init_hidden() if idx % 100 == 0: print('\tepoch [{}/{}], iter: {}, s_loss: {:.4f}, m_loss: {:.4f}, preds: s: {}, {}, m: {}, {}' .format(epoch+1, train_config['num_epochs'], idx, s_loss.item(), m_loss.item(), s_output.item(), round(s_output.item()), m_output.item(), round(m_output.item()))) print('\tepoch [{}/{}]'.format(epoch+1, train_config['num_epochs'])) torch.save(shakespeare_disc.state_dict(), './shakespeare_disc.pth')
def main(): parser = argparse.ArgumentParser( description='Train Cartoon avatar Gan models') parser.add_argument('--crop_size', default=64, type=int, help='Training images crop size') parser.add_argument('--num_epochs', default=50, type=int, help='Train epoch number') parser.add_argument('--data_root', default='data/cartoon', help='Root directory for dataset') parser.add_argument('--worker', default=2, type=int, help='Number of workers for dataloader') parser.add_argument('--batch_size', default=16, type=int, help='Batch size during training') parser.add_argument('--channels', default=3, type=int, help='Number of channels in the training images') parser.add_argument('--nz', default=100, type=int, help='Size of generator input') parser.add_argument('--ngf', default=64, type=int, help='Size of feature maps in generator') parser.add_argument('--ndf', default=64, type=int, help='Size of feature maps in descriminator') parser.add_argument('--lr', default=0.0002, type=float, help='Learning rate for optimizer') parser.add_argument('--beta1', default=0.5, type=float, help='Beta1 hyperparam for Adam optimizers') parser.add_argument('--beta2', default=0.999, type=float, help='Beta2 hyperparam for Adam optimizers') parser.add_argument('--ngpu', default=1, type=int, help='Number of GPUs , use 0 for CPU mode') parser.add_argument( '--latent_vector_num', default=8, type=int, help= 'latent vectors that we will use to visualize , 8 means that it will visualize 8 images during training' ) opt = parser.parse_args() dataroot = opt.data_root workers = opt.worker batch_size = opt.batch_size image_size = opt.crop_size nc = opt.channels nz = opt.nz ngf = opt.ngf ndf = opt.ndf num_epochs = opt.num_epochs lr = opt.lr beta1 = opt.beta1 beta2 = opt.beta2 ngpu = opt.ngpu latent_vector_num = opt.latent_vector_num # Create the dataset dataset = dset.ImageFolder(root=dataroot, transform=transforms.Compose([ transforms.Resize(image_size), transforms.CenterCrop(image_size), transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)), ])) # Create the dataloader dataloader = torch.utils.data.DataLoader(dataset, batch_size=batch_size, shuffle=True, num_workers=workers) # Decide which device we want to run on device = torch.device("cuda:0" if ( torch.cuda.is_available() and ngpu > 0) else "cpu") # Create the generator netG = Generator(ngpu, nz, ngf, nc).to(device) # Create the Discriminator netD = Discriminator(ngpu, nc, ndf).to(device) # Handle multi-gpu if desired if (device.type == 'cuda') and (ngpu > 1): netG = nn.DataParallel(netG, list(range(ngpu))) netD = nn.DataParallel(netD, list(range(ngpu))) # Apply the weights_init function to randomly initialize all weights # to mean=0, stdev=0.2. netG.apply(weights_init) netD.apply(weights_init) # Setup Adam optimizers for both G and D optimizerD = optim.Adam(netD.parameters(), lr=lr, betas=(beta1, 0.999)) optimizerG = optim.Adam(netG.parameters(), lr=lr, betas=(beta1, 0.999)) # Print models print(netG) print(netD) # Initialize BCELoss function criterion = nn.BCELoss() # Create batch of latent vectors that we will use to visualize fixed_noise = torch.randn(latent_vector_num, nz, 1, 1, device=device) #real and fake labels during training real_label = 1 fake_label = 0 # Lists to keep track of progress img_list = [] G_losses = [] D_losses = [] iters = 0 print("Starting Training ...") for epoch in range(num_epochs): for i, data in enumerate(dataloader, 0): ############################ # (1) Update D network: maximize log(D(x)) + log(1 - D(G(z))) ########################### ## Train with all-real batch netD.zero_grad() # Format batch real_cpu = data[0].to(device) b_size = real_cpu.size(0) label = torch.full((b_size, ), real_label, device=device) # Forward pass real batch through D output = netD(real_cpu).view(-1) # Calculate loss on all-real batch errD_real = criterion(output, label) # Calculate gradients for D in backward pass errD_real.backward() D_x = output.mean().item() ## Train with all-fake batch # Generate batch of latent vectors noise = torch.randn(b_size, nz, 1, 1, device=device) # Generate fake image batch with G fake = netG(noise) label.fill_(fake_label) # Classify all fake batch with D output = netD(fake.detach()).view(-1) # Calculate D's loss on the all-fake batch errD_fake = criterion(output, label) # Calculate the gradients for this batch errD_fake.backward() D_G_z1 = output.mean().item() # Add the gradients from the all-real and all-fake batches errD = errD_real + errD_fake # Update D optimizerD.step() ############################ # (2) Update G network: maximize log(D(G(z))) ########################### netG.zero_grad() label.fill_(real_label) # fake labels are real for generator cost # Since we just updated D, perform another forward pass of all-fake batch through D output = netD(fake).view(-1) # Calculate G's loss based on this output errG = criterion(output, label) # Calculate gradients for G errG.backward() D_G_z2 = output.mean().item() # Update G optimizerG.step() # Output training stats if i % 50 == 0: # Save model data torch.save(netG.state_dict(), 'pretrained_model/netG_epoch_%d.pth' % (iters)) torch.save(netD.state_dict(), 'pretrained_model/netD_epoch_%d.pth' % (iters)) # Print training stats print( '[%d/%d][%d/%d]\tLoss_D: %.4f\tLoss_G: %.4f\tD(x): %.4f\tD(G(z)): %.4f / %.4f' % (epoch, num_epochs, i, len(dataloader), errD.item(), errG.item(), D_x, D_G_z1, D_G_z2)) # Save Losses for plotting later G_losses.append(errG.item()) D_losses.append(errD.item()) # Check how the generator is doing by saving G's output on fixed_noise if (iters % 650 == 0) or ((epoch == num_epochs - 1) and (i == len(dataloader) - 1)): with torch.no_grad(): fake = netG(fixed_noise).detach().cpu() img_list.append( vutils.make_grid(fake, padding=2, normalize=True)) iters += 1 # Display and Save samples GIF fig = plt.figure(figsize=(8, 8)) plt.axis("off") ims = [[plt.imshow(np.transpose(i, (1, 2, 0)), animated=True)] for i in img_list] ani = animation.ArtistAnimation(fig, ims, interval=1000, repeat_delay=1000, blit=True) ani.save('output/samples.gif', writer='imagemagick', fps=100)
def main(): # init random seed init_random_seed(params.manual_seed) # Load dataset mnist_data_loader = get_mnist(train=True, download=True) mnist_data_loader_eval = get_mnist(train=False, download=True) usps_data_loader = get_usps(train=True, download=True) usps_data_loader_eval = get_usps(train=False, download=True) # Model init DANN tgt_encoder = model_init(Encoder(), params.tgt_encoder_dann_rb_path) critic = model_init(Discriminator(), params.disc_dann_rb_path) clf = model_init(Classifier(), params.clf_dann_rb_path) # Train models print( "====== Robust Training source encoder and classifier in MNIST and USPS domains ======" ) if not (tgt_encoder.pretrained and clf.pretrained and critic.pretrained and params.model_trained): tgt_encoder, clf, critic = train_dann(tgt_encoder, clf, critic, mnist_data_loader, usps_data_loader, usps_data_loader_eval, robust=False) # Eval target encoder on test set of target dataset print( "====== Evaluating classifier for encoded MNIST and USPS domains ======" ) print("-------- MNIST domain --------") eval_tgt_robust(tgt_encoder, clf, critic, mnist_data_loader_eval) print("-------- USPS adaption --------") eval_tgt_robust(tgt_encoder, clf, critic, usps_data_loader_eval) print("====== Pseudo labeling on USPS domain ======") pseudo_label(tgt_encoder, clf, "usps_train_pseudo", usps_data_loader) # Init a new model tgt_encoder = model_init(Encoder(), params.tgt_encoder_path) clf = model_init(Classifier(), params.clf_path) # Load pseudo labeled dataset usps_pseudo_loader = get_usps(train=True, download=True, get_pseudo=True) print("====== Standard training on USPS domain with pseudo labels ======") if not (tgt_encoder.pretrained and clf.pretrained): train_src_adda(tgt_encoder, clf, usps_pseudo_loader, mode='ADV') print("====== Evaluating on USPS domain with real labels ======") eval_tgt(tgt_encoder, clf, usps_data_loader_eval) tgt_encoder = model_init(Encoder(), params.tgt_encoder_rb_path) clf = model_init(Classifier(), params.clf_rb_path) print("====== Robust training on USPS domain with pseudo labels ======") if not (tgt_encoder.pretrained and clf.pretrained): train_src_robust(tgt_encoder, clf, usps_pseudo_loader, mode='ADV') print("====== Evaluating on USPS domain with real labels ======") eval_tgt(tgt_encoder, clf, usps_data_loader_eval)
torch.backends.cudnn.enabled = True torch.backends.cudnn.benchmark = True quant = True if 'GS8' in args.base_model_str else False subnet_model_path = os.path.join('subnet_structures_ticket', args.dataset, args.task, args.base_model_str, 'pth') ## Networks # G: dim_lst_path = os.path.join(subnet_model_path, 'epoch%d_netG.npy' % 199) netG = Generator(args.input_nc, args.output_nc, dim_lst=np.load(dim_lst_path), quant=quant).cuda() # D: netD = Discriminator(args.input_nc).cuda() ## results_dir: optimizer_str = 'adam_lr%s_wd%s' % (args.lr, args.wd) loss_str = '' results_dir = os.path.join('cp_finetune_results', args.dataset, args.task, args.base_model_str, '%s_%s' % (optimizer_str, loss_str)) img_dir = os.path.join(results_dir, 'img') pth_dir = os.path.join(results_dir, 'pth') create_dir(img_dir), create_dir(pth_dir) # Optimizers optimizer_G = torch.optim.Adam(netG.parameters(), lr=args.lr, weight_decay=args.wd,
else: source_str, target_str = 'B', 'A' foreign_dir = '/home/haotao/PyTorch-CycleGAN/' print(args) os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu torch.backends.cudnn.enabled = True torch.backends.cudnn.benchmark = True ## Networks # G: dim_lst_path = os.path.join(subnet_model_path, 'epoch%d_netG.npy' % 199) netG = Generator(args.input_nc, args.output_nc, dim_lst=np.load(dim_lst_path), quant=quant).cuda() # D: netD = Discriminator(args.input_nc).cuda() # load sub G extracted from latest.pth g_path = os.path.join(args.base_model_str, 'epoch%d_netG.pth' % 199) netG.load_state_dict(torch.load(g_path)) print('load G from %s' % g_path) # load full D directly from latest.pth d_path = os.path.join('cp_results', args.dataset, args.task, args.base_model_str, 'pth', 'latest.pth') netD.load_state_dict(torch.load(d_path)['netD']) print('load D from %s' % d_path) start_epoch = 0 best_FID = 1e9 loss_G_lst, loss_G_perceptual_lst, loss_G_GAN_lst, loss_D_lst = [], [], [], [] # Dataset loader: img shape=(256,256)