args.use_deadline, False))
print("Before training, global model generates", sum(ret))
start = time.time()
"""Training Loop"""
rl_model.train()
# Make a baseline model
bl_model = Solver(args.num_procs,
args.embedding_size,
args.hidden_size,
args.num_tasks,
use_deadline=False,
use_cuda=True)
if args.use_cuda:
bl_model.cuda()
bl_model.load_state_dict(rl_model.state_dict())
bl_model.eval()
optimizer = optim.Adam(rl_model.parameters(), lr=args.lr)
scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
args.lr_decay_step,
gamma=0.9,
last_epoch=-1)
last_rl_model_sum = -1
updates = 0
noupdateinarow = 0
_max = -1
for epoch in range(args.num_epochs):
loss_ = 0
avg_hit = []
for batch_idx, (_, sample_batch) in enumerate(train_loader):
if use_cuda:
order[chosen[k]] = args.num_tasks - k - 1 # 중요할수록 숫자가 높다.
if use_cuda:
ret.append(test_module(batch[j].cpu().numpy(), args.num_procs, order, args.use_deadline, False))
else:
ret.append(test_module(batch[j].numpy(), args.num_procs, order, args.use_deadline, False))
print("Before training, global model generates", sum(ret))
start = time.time()
"""Training Loop"""
rl_model.train()
# Make a baseline model
bl_model = Solver(args.num_procs, args.embedding_size, args.hidden_size,
args.num_tasks, use_deadline=False, use_cuda=True, only_encoder=True)
if args.use_cuda:
bl_model.cuda()
bl_model.load_state_dict(rl_model.state_dict(), strict=False)
bl_model.eval()
optimizer = optim.Adam(rl_model.parameters(), lr=args.lr)
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, args.lr_decay_step, gamma=0.9, last_epoch=-1)
last_rl_model_sum = -1
updates = 0
noupdateinarow = 0
_max = -1
for epoch in range(args.num_epochs):
loss_ = 0
avg_hit = []
for batch_idx, (_, sample_batch) in enumerate(train_loader):
if use_cuda:
sample_batch = sample_batch.cuda()
num_samples = sample_batch.shape[0]
optimizer.zero_grad()
