if __name__ == '__main__':
args = parser.arg_parse()
''' setup GPU '''
if torch.cuda.is_available():
torch.cuda.set_device(args.gpu)
'''Distinguish different training patterns'''
if "mnistm" == args.target_data:
dataset = data_c.Mnist(args, mode='test')
source = 'svhn'
target = 'mnistm'
elif "svhn" == args.target_data:
dataset = data_c.Svhn(args, mode='test')
source = 'mnistm'
target = 'svhn'
''' prepare data_loader '''
print('===> prepare data loader ...')
test_loader = torch.utils.data.DataLoader(dataset,
batch_size=args.test_batch,
num_workers=args.workers,
shuffle=False)
''' prepare mode '''
model = models.Dann(args)
#model = models.DannSource(args)
if torch.cuda.is_available():
model.cuda()
import models
import data_c
import numpy as np
from sklearn.manifold import TSNE
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
if __name__ == '__main__':
args = parser.arg_parse()
''' setup GPU '''
if torch.cuda.is_available():
torch.cuda.set_device(args.gpu)
'''Distinguish different training patterns'''
if "mnistm" == args.target_data:
source_data = data_c.Svhn(args, mode='train', visualization=True)
target_data = data_c.Mnist(args, mode='train', visualization=True)
source = 'svhn'
target = 'mnistm'
elif "svhn" == args.target_data:
source_data = data_c.Mnist(args, mode='train', visualization=True)
target_data = data_c.Svhn(args, mode='train', visualization=True)
source = 'mnistm'
target = 'svhn'
''' prepare data_loader '''
print('===> prepare data loader ...')
source_loader = torch.utils.data.DataLoader(source_data,
batch_size=args.test_batch,
num_workers=args.workers,
shuffle=False)
gts = np.concatenate(gts)
preds = np.concatenate(preds)
return accuracy_score(gts, preds)
if __name__ == '__main__':
args = parser.arg_parse()
source_data = 'svhn'
target_data = 'mnistm'
mnistm_dataset = data_c.Mnist(args, mode='train')
svhn_dataset = data_c.Svhn(args, mode='train')
''' load dataset and prepare data loader '''
print('===> prepare dataloader ...')
mnistm_loader = torch.utils.data.DataLoader(mnistm_dataset,
batch_size=args.train_batch,
num_workers=args.workers,
shuffle=True)
svhn_loader = torch.utils.data.DataLoader(svhn_dataset,
batch_size=args.train_batch,
num_workers=args.workers,
shuffle=True)
'''define source and target'''
if source_data == 'mnistm':
source = mnistm_loader
target = svhn_loader