'--log-interval',
type=int,
default=10,
metavar='N',
help='how many batches to wait before logging training status')
args = parser.parse_args()
args.cuda = not args.no_cuda and torch.cuda.is_available()
torch.manual_seed(args.seed)
if args.cuda:
torch.cuda.manual_seed(args.seed)
kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
trainset = FashionAI('./',
attribute=args.attribute,
split=0.8,
ci=args.ci,
data_type='train',
reset=False)
testset = FashionAI('./',
attribute=args.attribute,
split=0.8,
ci=args.ci,
data_type='test',
reset=trainset.reset)
train_loader = DataLoader(trainset,
batch_size=args.batch_size,
shuffle=True,
**kwargs)
test_loader = DataLoader(testset,
batch_size=args.test_batch_size,
shuffle=True,
parser.add_argument(
'--log-interval',
type=int,
default=10,
metavar='N',
help='how many batches to wait before logging training status')
args = parser.parse_args()
args.cuda = not args.no_cuda and torch.cuda.is_available()
torch.manual_seed(args.seed)
if args.cuda:
torch.cuda.manual_seed(args.seed)
kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
evalset = FashionAI('./',
attribute=args.attribute,
data_type='eval',
reset=False)
eval_loader = torch.utils.data.DataLoader(evalset,
batch_size=args.batch_size,
shuffle=True,
**kwargs)
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(3, 10, kernel_size=5)
self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
self.conv2_drop = nn.Dropout2d()
self.fc1 = nn.Linear(180, 50)
self.fc2 = nn.Linear(50, 8)