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:
sample_batch = sample_batch.cuda()
num_samples = sample_batch.shape[0]
_sample, num_proc, None,
use_deadline) # 여기서 OPA에 테스트 안넘겼는데 까고 들어가보면 DA어쩌구 테스트를 사용함.
with ProcessPoolExecutor(max_workers=4) as executor:
inputs = []
res_opa = np.zeros(len(test_dataset), dtype=int).tolist()
for i, sample in test_dataset:
#ret = heu.OPA(sample, args.num_procs, heu.test_DA_LC, use_deadline)
inputs.append((sample, args.num_procs, use_deadline))
for i, ret in tqdm(enumerate(executor.map(wrap, inputs))):
res_opa[i] = ret
opares = np.sum(res_opa)
print("[before training][OPA generates %d]" % opares)
model.train()
optimizer = optim.Adam(model.parameters(), lr=0.5 * args.lr)
loss_ = 0
avg_hit = []
updates = 0
prev_ = -1
require_pt = True
if require_pt:
for batch_idx, (_, sample_batch) in enumerate(train_data_loader):
guide = []
as_np = sample_batch.numpy()
for r in as_np:
guide.append(
np.argsort(
py_heu.get_DM_scores(r, args.num_procs, use_deadline)))
guide = torch.from_numpy(np.array(guide, dtype=np.int64))
if use_cuda:
