def semantics(ss_path, cluster_type, cluster_path, **kwargs):
if ss_path:
ss = ss_model(ss_path)
cluster = define_last_model(cluster_type, cluster_path, 'classifier',
**kwargs)
return Semantics(ss, cluster)
else:
return define_last_model(cluster_type, cluster_path, 'classifier',
**kwargs)
def execute(args):
data_root_src = args.data_root_src
domain = args.domain
nz = 16
save_path = args.save_path
state_dict_path = get_last_model('nets_ema', save_path)
device = 'cuda'
domain = int(domain)
# Load model
state_dict = torch.load(state_dict_path, map_location='cpu')
generator = Generator(bottleneck_size=64, bottleneck_blocks=4, img_size=args.img_size, max_conv_dim=args.max_conv_dim).to(device)
generator.load_state_dict(state_dict['generator'])
mapping = MappingNetwork(nc=10)
mapping.load_state_dict(state_dict['mapping_network'])
mapping.to(device)
sem = semantics(None, 'vmt_cluster', args.da_path, shape=[3, 32], nc=10).cuda()
sem.eval()
classifier = define_last_model('classifier', args.classifier_path, 'classifier', shape=3, nc=10).to(device)
classifier.eval()
dataset = getattr(images, args.dataset_src)
src_dataset = dataset(data_root_src, 1, 32)[2]
accuracy = evaluate(src_dataset, nz, domain, sem, mapping, generator, classifier, device)
print(accuracy)
save_result(save_path, args.identifier, state_dict_path, accuracy)
def execute(args):
state_dict_path = args.state_dict_path
data_root_src = args.data_root_src
domain = args.domain
nz = 16
device = 'cuda'
domain = int(domain)
# Load model
state_dict = torch.load(state_dict_path, map_location='cpu')
generator = Generator(bottleneck_size=args.bottleneck_size,
bottleneck_blocks=4,
img_size=args.img_size,
max_conv_dim=args.max_conv_dim).to(device)
generator.load_state_dict(state_dict['generator'])
mapping = MappingNetwork()
mapping.load_state_dict(state_dict['mapping_network'])
mapping.to(device)
classifier = define_last_model('classifier',
args.classifier_path,
'classifier',
shape=3,
nc=10).to(device)
classifier.eval()
dataset = getattr(images, args.dataset_src)
src_dataset = dataset(data_root_src, 1, 64)[2]
accuracy = evaluate(src_dataset, nz, domain, mapping, generator,
classifier, device)
print(accuracy)