def run():
# load source dataset
src_data_loader = get_data_loader(params.src_dataset)
src_data_loader_eval = get_data_loader(params.src_dataset, train=False)
# load models
src_encoder = init_model(net=LeNetEncoder(),
restore=params.src_encoder_restore)
src_classifier = init_model(net=LeNetClassifier(),
restore=params.src_classifier_restore)
# pre-train source model
print("=== Training classifier for source domain ===")
print(">>> Source Encoder <<<")
im, _ = next(iter(src_data_loader))
summary(src_encoder, input_size=im[0].size())
print(">>> Source Classifier <<<")
print(src_classifier)
if not (src_encoder.restored and src_classifier.restored and
params.src_model_trained):
src_encoder, src_classifier = train_src(
src_encoder, src_classifier, src_data_loader)
# eval source model
print("=== Evaluating classifier for source domain ===")
eval_src(src_encoder, src_classifier, src_data_loader_eval)
def office():
init_random_seed(params.manual_seed)
# load dataset
src_data_loader = get_data_loader(params.src_dataset)
src_data_loader_eval = get_data_loader(params.src_dataset, train=False)
tgt_data_loader = get_data_loader(params.tgt_dataset)
tgt_data_loader_eval = get_data_loader(params.tgt_dataset, train=False)
# load models
src_encoder = init_model(net=LeNetEncoder(),
restore=params.src_encoder_restore)
src_classifier = init_model(net=LeNetClassifier(),
restore=params.src_classifier_restore)
tgt_encoder = init_model(net=LeNetEncoder(),
restore=params.tgt_encoder_restore)
critic = init_model(Discriminator(input_dims=params.d_input_dims,
hidden_dims=params.d_hidden_dims,
output_dims=params.d_output_dims),
restore=params.d_model_restore)
if not (src_encoder.restored and src_classifier.restored and
params.src_model_trained):
src_encoder, src_classifier = train_src(
src_encoder, src_classifier, src_data_loader)
# eval source model
# print("=== Evaluating classifier for source domain ===")
# eval_src(src_encoder, src_classifier, src_data_loader_eval)
# train target encoder by GAN
# init weights of target encoder with those of source encoder
if not tgt_encoder.restored:
tgt_encoder.load_state_dict(src_encoder.state_dict())
if not (tgt_encoder.restored and critic.restored and
params.tgt_model_trained):
tgt_encoder = train_tgt(src_encoder, tgt_encoder, critic,
src_data_loader, tgt_data_loader)
# eval target encoder on test set of target dataset
print(">>> domain adaption <<<")
acc = eval_tgt(tgt_encoder, src_classifier, tgt_data_loader_eval)
return acc
def run():
# load dataset
tgt_data_loader_eval = get_data_loader(params.tgt_dataset, train=False)
# Load models
src_encoder = init_model(net=LeNetEncoder(),
restore=params.src_encoder_restore)
src_classifier = init_model(net=LeNetClassifier(),
restore=params.src_classifier_restore)
tgt_encoder = init_model(net=LeNetEncoder(),
restore=params.tgt_encoder_restore)
# Evalute target encoder on test set of target dataset
print("=== Evaluating classifier for encoded target domain ===")
print(">>> source only <<<")
eval_tgt(src_encoder, src_classifier, tgt_data_loader_eval)
print(">>> domain adaption <<<")
eval_tgt(tgt_encoder, src_classifier, tgt_data_loader_eval)
def experiments(exp):
#print(exp, case, affine, num_epochs)
# init random seed
#params.d_learning_rate = lr_d
#params.c_learning_rate = lr_c
init_random_seed(params.manual_seed)
# load dataset
src_dataset, tgt_dataset = exp.split('_')
src_data_loader = get_data_loader(src_dataset)
src_data_loader_eval = get_data_loader(src_dataset, train=False)
tgt_data_loader = get_data_loader(tgt_dataset)
tgt_data_loader_eval = get_data_loader(tgt_dataset, train=False)
# load models
src_encoder = init_model(net=LeNetEncoder(),
restore=params.src_encoder_restore,
exp=exp)
src_classifier = init_model(net=LeNetClassifier(),
restore=params.src_classifier_restore,
exp=exp)
tgt_encoder = init_model(net=LeNetEncoder(),
restore=params.tgt_encoder_restore,
exp=exp)
critic = init_model(Discriminator(input_dims=params.d_input_dims,
hidden_dims=params.d_hidden_dims,
output_dims=params.d_output_dims),
exp=exp,
restore=params.d_model_restore)
# train source model
print("=== Training classifier for source domain ===")
print(">>> Source Encoder <<<")
print(src_encoder)
print(">>> Source Classifier <<<")
print(src_classifier)
if not (src_encoder.restored and src_classifier.restored
and params.src_model_trained):
src_encoder, src_classifier = train_src(exp, src_encoder,
src_classifier,
src_data_loader,
src_data_loader_eval)
# eval source model
print("=== Evaluating classifier for source domain ===")
evaluation(src_encoder, src_classifier, src_data_loader_eval)
# train target encoder by GAN
print("=== Training encoder for target domain ===")
print(">>> Target Encoder <<<")
print(tgt_encoder)
print(">>> Critic <<<")
print(critic)
# init weights of target encoder with those of source encoder
if not tgt_encoder.restored:
tgt_encoder.load_state_dict(src_encoder.state_dict())
if not (tgt_encoder.restored and critic.restored
and params.tgt_model_trained):
tgt_encoder = train_tgt(exp, src_encoder, tgt_encoder, critic,
src_classifier, src_data_loader,
tgt_data_loader, tgt_data_loader_eval)
# eval target encoder on test set of target dataset
print("=== Evaluating classifier for encoded target domain ===")
print(">>> source only <<<")
evaluation(src_encoder, src_classifier, tgt_data_loader_eval)
print(">>> domain adaption <<<")
evaluation(tgt_encoder, src_classifier, tgt_data_loader_eval)
from utils import get_data_loader, init_model, init_random_seed
if __name__ == '__main__':
# init random seed
init_random_seed(params.manual_seed)
# load dataset
src_data_loader = get_data_loader(params.src_dataset)
src_data_loader_eval = get_data_loader(params.src_dataset, train=False)
tgt_data_loader = get_data_loader(params.tgt_dataset)
tgt_data_loader_eval = get_data_loader(params.tgt_dataset, train=False)
# load models
src_encoder = init_model(net=LeNetEncoder(),
restore=params.src_encoder_restore)
src_classifier = init_model(net=LeNetClassifier(),
restore=params.src_classifier_restore)
tgt_encoder = init_model(net=LeNetEncoder(),
restore=params.tgt_encoder_restore)
critic = init_model(Discriminator(input_dims=params.d_input_dims,
hidden_dims=params.d_hidden_dims,
output_dims=params.d_output_dims),
restore=params.d_model_restore)
# train source model
print("=== Training classifier for source domain ===")
print(">>> Source Encoder <<<")
print(src_encoder)
print(">>> Source Classifier <<<")
print(src_classifier)
# load dataset SM
# src_data_loader = get_data_loader(cfg.src_dataset)
# src_data_loader_eval = get_data_loader(cfg.src_dataset, train=False)
# tgt_data_loader = get_data_loader(cfg.tgt_dataset)
# tgt_data_loader_eval = get_data_loader(cfg.tgt_dataset, train=False)
# load dataset UM MU
src_data_loader = get_data_loader(cfg.src_dataset, sample=True)
src_data_loader_eval = get_data_loader(cfg.src_dataset, train=False)
tgt_data_loader = get_data_loader(cfg.tgt_dataset, sample=True)
tgt_data_loader_eval = tgt_data_loader
# load models
src_encoder = init_model(net=LeNetEncoder(cfg.inputc),
restore=cfg.src_encoder_restore)
src_classifier = init_model(net=LeNetClassifier(ncls=cfg.ncls),
restore=cfg.src_classifier_restore)
tgt_classifier = init_model(net=LeNetClassifier(ncls=cfg.ncls),
restore=cfg.src_classifier_restore)
tgt_encoder = init_model(net=LeNetEncoder(cfg.inputc),
restore=cfg.tgt_encoder_restore)
critic = init_model(Discriminator_feat(input_dims=cfg.d_input_dims,
hidden_dims=cfg.d_hidden_dims,
output_dims=cfg.d_output_dims),
restore=cfg.d_model_restore)
generator = init_model(net=LeNetGenerator(input_dims=cfg.g_input_dims,
outputc=cfg.inputc),
restore=cfg.src_generator_restore)
# generator = init_model(net=LeNetGenerator(input_dims=cfg.g_input_dims, outputc = cfg.inputc),
# restore=None)
discriminator = init_model(net=Discriminator_img(nc=cfg.inputc),
val_src_dataloader = DataLoader(val_src_dataset, batch_size=batch_size, shuffle=False)
val_tgt_dataloader = DataLoader(val_tgt_dataset, batch_size=batch_size, shuffle=False)
src_label = 0
tgt_label = 1
print(len(src_dataset), len(tgt_dataset), len(val_src_dataset), len(val_tgt_dataset))
# In[4]:
# init models
src_encoder = LeNetEncoder()
tgt_encoder = LeNetEncoder()
src_classifier = LeNetClassifier()
discriminator = Discriminator()
# init weights
src_encoder.apply(init_weights)
tgt_encoder.apply(init_weights)
src_classifier.apply(init_weights)
discriminator.apply(init_weights)
# to device
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
src_encoder.to(device)
tgt_encoder.to(device)
src_classifier.to(device)
discriminator.to(device)
dataloader_target_test = torch.utils.data.DataLoader(
dataset=data_test.DATA(opt),
batch_size=opt.batch_size,
shuffle=False,
num_workers=opt.n_cpu
)
# ------------
# Load Model
# ------------
print("---> preparing models...")
target_encoder = LeNetEncoder()
source_classifier = LeNetClassifier()
# Select models that were trained on the correct dataset
if opt.target == "mnistm":
target_encoder_name = "ADDA-target-encoder-SVHN_MNISTM.pt"
source_classifier_name = "ADDA-source-classifier-SVHN_MNISTM.pt"
target_encoder_pth = os.path.join(opt.save_dir, target_encoder_name)
source_classifier_pth = os.path.join(opt.save_dir, source_classifier_name)
elif opt.target == "svhn":
target_encoder_name = "ADDA-target-encoder-MNISTM_SVHN.pt"
source_classifier_name = "ADDA-source-classifier-MNISTM_SVHN.pt"
target_encoder_pth = os.path.join(opt.save_dir, target_encoder_name)
source_classifier_pth = os.path.join(opt.save_dir, source_classifier_name)
else:
source_train_loader, source_test_loader = utils.load_data("MNIST")
target_train_loader, target_test_loader = utils.load_data("USPS")
batch_size = 256
# In[3]:
images, labels = next(iter(target_test_loader))
images.size()
# In[4]:
DEVICE = 'cuda:1'
#Load Models
src_encoder = LeNetEncoder().to(DEVICE)
src_classifier = LeNetClassifier().to(DEVICE)
tgt_encoder = LeNetEncoder().to(DEVICE)
discriminator = Discriminator(input_dims=500, hidden_dims=500,
output_dims=2).to(DEVICE)
# In[5]:
#Print models for source
print(src_encoder)
print(src_classifier)
# In[6]:
try:
src_encoder.load_state_dict(torch.load('src_encoder.pth'))
def main(args):
# read from args
test_path = args.test_path
d_target = args.d_target
output_predict_path = args.output_predict_path
########## Arguments ##########
batch_size = 128
# svhn, usps, mnistm
if d_target == "mnistm":
d_source = "usps"
elif d_target == "svhn":
d_source = "mnistm"
else:
d_source = "svhn"
output_src_classifier_path = "./hw3-4/models/src_classifier_{}_{}.pth".format(
d_source, d_target)
output_tgt_encoder_path = "./hw3-4//models/tgt_encoder_{}_{}.pth".format(
d_source, d_target)
#############################
dataset = ReproduceDataset(test_path)
dataloader = DataLoader(dataset, batch_size=batch_size, shuffle=False)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
# init models
tgt_encoder = LeNetEncoder()
src_classifier = LeNetClassifier()
# to device
tgt_encoder.to(device)
src_classifier.to(device)
# init weights
tgt_encoder.load_state_dict(torch.load(
output_tgt_encoder_path, map_location=device))
src_classifier.load_state_dict(torch.load(
output_src_classifier_path, map_location=device))
tgt_encoder.eval()
src_classifier.eval()
all_pred = []
for idx, targets in enumerate(dataloader):
target_images = targets.to(device)
target_bs = target_images.shape[0]
with torch.no_grad():
preds = src_classifier(tgt_encoder(target_images))
# calculate label acc
_, pred_labels = torch.max(preds, 1)
all_pred.append(pred_labels)
# save to predict
pred = torch.cat(all_pred).cpu().numpy()
image_names = ['{:05}.png'.format(i) for i in range(len(pred))]
pd.DataFrame({
'image_name': image_names,
'label': pred
}).to_csv(output_predict_path, index=False)
