trlog['train_loss'] = []
trlog['val_loss'] = []
trlog['train_acc'] = []
trlog['val_acc'] = []
trlog['max_acc'] = 0.0
timer = Timer()
for epoch in range(1, args.max_epoch + 1):
lr_scheduler_cnn.step()
lr_scheduler_atten.step()
lr_scheduler_gen.step()
lr_scheduler_global1.step()
lr_scheduler_global2.step()
model_cnn.train()
model_reg.train()
model_gen.train()
tl1 = Averager()
tl2 = Averager()
ta1 = Averager()
ta2 = Averager()
for i, batch in enumerate(train_loader, 1):
data, lab = [_.cuda() for _ in batch]
p = args.shot * args.train_way
data_shot = data[:p]
data_query = data[p:]
data_shot = data_shot[:, :3, :]
torch.save(model.state_dict(), osp.join(save_path, name + '.pth'))
trlog = {}
trlog['args'] = vars(args)
trlog['train_loss'] = []
trlog['val_loss'] = []
trlog['train_acc'] = []
trlog['val_acc'] = []
trlog['max_acc'] = 0.0
timer = Timer()
for epoch in range(1, max_epoch + 1):
lr_scheduler.step()
model.train()
tl = Averager()
ta = Averager()
for i, batch in enumerate(train_loader, 1):
data, _ = [_ for _ in batch]
p = shot * train_way
data_shot, data_query = data[:p], data[p:]
proto = model(data_shot)
proto = proto.reshape(shot, train_way, -1).mean(dim=0)
label = torch.arange(train_way).repeat(2)
label = label.type(torch.LongTensor)
def main(args):
device = torch.device(args.device)
ensure_path(args.save_path)
data = Data(args.dataset, args.n_batches, args.train_way, args.test_way, args.shot, args.query)
train_loader = data.train_loader
val_loader = data.valid_loader
model = Convnet(x_dim=2).to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=20, gamma=0.5)
def save_model(name):
torch.save(model.state_dict(), osp.join(args.save_path, name + '.pth'))
trlog = dict(
args=vars(args),
train_loss=[],
val_loss=[],
train_acc=[],
val_acc=[],
max_acc=0.0,
)
timer = Timer()
for epoch in range(1, args.max_epoch + 1):
lr_scheduler.step()
model.train()
tl = Averager()
ta = Averager()
for i, batch in enumerate(train_loader, 1):
data, _ = [_.to(device) for _ in batch]
data = data.reshape(-1, 2, 105, 105)
p = args.shot * args.train_way
embedded = model(data)
embedded_shot, embedded_query = embedded[:p], embedded[p:]
proto = embedded_shot.reshape(args.shot, args.train_way, -1).mean(dim=0)
label = torch.arange(args.train_way).repeat(args.query).to(device)
logits = euclidean_metric(embedded_query, proto)
loss = F.cross_entropy(logits, label)
acc = count_acc(logits, label)
print('epoch {}, train {}/{}, loss={:.4f} acc={:.4f}'
.format(epoch, i, len(train_loader), loss.item(), acc))
tl.add(loss.item())
ta.add(acc)
optimizer.zero_grad()
loss.backward()
optimizer.step()
tl = tl.item()
ta = ta.item()
model.eval()
vl = Averager()
va = Averager()
for i, batch in enumerate(val_loader, 1):
data, _ = [_.cuda() for _ in batch]
data = data.reshape(-1, 2, 105, 105)
p = args.shot * args.test_way
data_shot, data_query = data[:p], data[p:]
proto = model(data_shot)
proto = proto.reshape(args.shot, args.test_way, -1).mean(dim=0)
label = torch.arange(args.test_way).repeat(args.query).to(device)
logits = euclidean_metric(model(data_query), proto)
loss = F.cross_entropy(logits, label)
acc = count_acc(logits, label)
vl.add(loss.item())
va.add(acc)
vl = vl.item()
va = va.item()
print('epoch {}, val, loss={:.4f} acc={:.4f}'.format(epoch, vl, va))
if va > trlog['max_acc']:
trlog['max_acc'] = va
save_model('max-acc')
trlog['train_loss'].append(tl)
trlog['train_acc'].append(ta)
trlog['val_loss'].append(vl)
trlog['val_acc'].append(va)
torch.save(trlog, osp.join(args.save_path, 'trlog'))
save_model('epoch-last')
if epoch % args.save_epoch == 0:
save_model('epoch-{}'.format(epoch))
print('ETA:{}/{}'.format(timer.measure(), timer.measure(epoch / args.max_epoch)))