def main(opt):
data = get_dataset(opt)
g = data[0]
if opt['gpu'] < 0:
cuda = False
else:
cuda = True
g = g.int().to(opt['gpu'])
features = g.ndata['feat']
labels = g.ndata['label']
train_mask = g.ndata['train_mask']
val_mask = g.ndata['val_mask']
test_mask = g.ndata['test_mask']
num_feats = features.shape[1]
n_classes = data.num_labels
n_edges = data.graph.number_of_edges()
print("""----Data statistics------'
#Edges %d
#Classes %d
#Train samples %d
#Val samples %d
#Test samples %d""" %
(n_edges, n_classes, train_mask.int().sum().item(),
val_mask.int().sum().item(), test_mask.int().sum().item()))
# add self loop
g = dgl.remove_self_loop(g)
g = dgl.add_self_loop(g)
n_edges = g.number_of_edges()
# create model
heads = ([opt['num_heads']] * opt['num_layers']) + [opt['num_out_heads']]
if opt['model'] == 'GAT':
model = GAT(g, opt['num_layers'], num_feats, opt['num_hidden'],
n_classes, heads, F.elu, opt['in_drop'], opt['attn_drop'],
opt['negative_slope'], opt['residual'], opt)
elif opt['model'] == 'AGNN':
model = AGNN(g, opt['num_layers'], num_feats, opt['num_hidden'],
n_classes, opt['in_drop'], opt)
print(model)
if opt['early_stop']:
stopper = EarlyStopping(patience=100)
if cuda:
model.cuda()
# use optimizer
optimizer = get_optimizer(opt['optimizer'],
parameters=model.parameters(),
lr=opt['lr'],
weight_decay=opt['weight_decay'])
# initialize graph
dur = []
for epoch in range(opt['epochs']):
# model.train()
if epoch >= 3:
t0 = time.time()
# forward
# logits = model(features)
# loss = loss_fcn(logits[train_mask], labels[train_mask])
# optimizer.zero_grad()
# loss.backward()
# optimizer.step()
loss, logits = train(model, optimizer, features, train_mask, labels)
if epoch >= 3:
dur.append(time.time() - t0)
train_acc = accuracy(logits[train_mask], labels[train_mask])
if opt['fastmode']:
val_acc = accuracy(logits[val_mask], labels[val_mask])
else:
val_acc = evaluate(model, features, labels, val_mask)
if opt['early_stop']:
if stopper.step(val_acc, model):
break
print("Epoch {:05d} | Time(s) {:.4f} | Loss {:.4f} | TrainAcc {:.4f} |"
" ValAcc {:.4f} | ETputs(KTEPS) {:.2f}".format(
epoch, np.mean(dur), loss.item(), train_acc, val_acc,
n_edges / np.mean(dur) / 1000))
print()
if opt['early_stop']:
model.load_state_dict(torch.load('es_checkpoint.pt'))
acc = evaluate(model, features, labels, test_mask)
print("Test Accuracy {:.4f}".format(acc))
if args.cuda:
torch.cuda.manual_seed(args.seed)
#Load data
adj, features, labels, idx_train, idx_val, idx_test = load_data()
model = GAT(nfeat=features.shape[1],
nhid=args.hidden,
nclass=int(labels.max())+1,
dropout=args.dropout,
nheads=args.nb_heads,
alpha=args.alpha)
optimizer = optim.Adam(model.parameters(),
lr=args.lr,
weight_decay=args.weight_decay)
if args.cuda:
model.cuda()
features = features.cuda()
adj = adj.cuda()
labels = labels.cuda()
idx_train = idx_train.cuda()
idx_val = idx_val.cuda()
idx_test = idx_test.cuda()
features, adj, labels = Variable(features), Variable(adj), Variable(labels)
train_losses, train_accs, val_losses, val_accs = [], [], [], []
def train_ray(opt, checkpoint_dir=None, data_dir="../data"):
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
data = get_dataset(opt)
g = data[0]
if opt['gpu'] < 0:
cuda = False
else:
cuda = True
g = g.int().to(opt['gpu'])
features = g.ndata['feat']
labels = g.ndata['label']
train_mask = g.ndata['train_mask']
val_mask = g.ndata['val_mask']
test_mask = g.ndata['test_mask']
num_feats = features.shape[1]
n_classes = data.num_classes
n_edges = data.graph.number_of_edges()
print("""----Data statistics------'
#Edges %d
#Classes %d
#Train samples %d
#Val samples %d
#Test samples %d""" %
(n_edges, n_classes, train_mask.int().sum().item(),
val_mask.int().sum().item(), test_mask.int().sum().item()))
# add self loop
g = dgl.remove_self_loop(g)
g = dgl.add_self_loop(g)
n_edges = g.number_of_edges()
# create model
heads = ([opt['num_heads']] * opt['num_layers']) + [opt['num_out_heads']]
models = []
optimizers = []
datas = [g for i in range(opt['num_init'])]
for split in range(opt['num_init']):
if opt['model'] == 'GAT':
model = GAT(g, opt['num_layers'], num_feats, opt['num_hidden'],
n_classes, heads, F.elu, opt['in_drop'],
opt['attn_drop'], opt['negative_slope'],
opt['residual'], opt)
elif opt['model'] == 'AGNN':
model = AGNN(g, opt['num_layers'], num_feats, opt['num_hidden'],
n_classes, opt['in_drop'], opt)
train_this = train
model = model.to(device)
models.append(model)
if torch.cuda.device_count() > 1:
model = nn.DataParallel(model)
# model = model.to(device)
parameters = [p for p in model.parameters() if p.requires_grad]
optimizer = get_optimizer(opt['optimizer'],
parameters,
lr=opt['lr'],
weight_decay=opt['weight_decay'])
optimizers.append(optimizer)
# The `checkpoint_dir` parameter gets passed by Ray Tune when a checkpoint
# should be restored.
if checkpoint_dir:
checkpoint = os.path.join(checkpoint_dir, "checkpoint")
model_state, optimizer_state = torch.load(checkpoint)
model.load_state_dict(model_state)
optimizer.load_state_dict(optimizer_state)
for epoch in range(1, opt['epochs']):
loss = np.mean([
train_this(model, optimizer, features, train_mask,
labels)[0].item()
for model, optimizer in zip(models, optimizers)
])
train_accs, val_accs, tmp_test_accs = average_test(models, datas)
with tune.checkpoint_dir(step=epoch) as checkpoint_dir:
best = np.argmax(val_accs)
path = os.path.join(checkpoint_dir, "checkpoint")
torch.save(
(models[best].state_dict(), optimizers[best].state_dict()),
path)
tune.report(loss=loss,
accuracy=np.mean(val_accs),
test_acc=np.mean(tmp_test_accs),
train_acc=np.mean(train_accs))
sampler=ImbalancedDatasetSampler(
train_db, callback_get_weight=WeightBinary(pos_ratio)))
return trainloader
# Model and optimizer
model = GAT(nfeat=args.nfeat,
nhid=args.hidden,
nout=128,
nlmphid=64,
nclass=args.nclass,
dropout=args.dropout,
nheads=args.nb_heads,
alpha=args.alpha)
optimizer = torch.optim.SGD(model.parameters(),
lr=args.lr,
weight_decay=args.weight_decay)
criterion = torch.nn.CrossEntropyLoss()
def run(epoch, dataloader, phase='train'):
loss_train = []
labels = []
outputs = []
preds = []
pos_correct = 0.0
neg_correct = 0.0
pos = 0.0
neg = 0.0
def train_ray_int(opt, checkpoint_dir=None, data_dir="../data"):
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
data = get_dataset(opt)
g = data[0]
if opt['gpu'] < 0:
cuda = False
else:
cuda = True
g = g.int().to(opt['gpu'])
# if opt["num_splits"] > 0:
# dataset.data = set_train_val_test_split(
# 23 * np.random.randint(0, opt["num_splits"]), # random prime 23 to make the splits 'more' random. Could remove
# dataset.data,
# num_development=5000 if opt["dataset"] == "CoauthorCS" else 1500)
features = g.ndata['feat']
labels = g.ndata['label']
train_mask = g.ndata['train_mask']
val_mask = g.ndata['val_mask']
test_mask = g.ndata['test_mask']
num_feats = features.shape[1]
n_classes = data.num_classes
n_edges = data.graph.number_of_edges()
print("""----Data statistics------'
#Edges %d
#Classes %d
#Train samples %d
#Val samples %d
#Test samples %d""" %
(n_edges, n_classes, train_mask.int().sum().item(),
val_mask.int().sum().item(), test_mask.int().sum().item()))
# add self loop
g = dgl.remove_self_loop(g)
g = dgl.add_self_loop(g)
n_edges = g.number_of_edges()
# create model
heads = ([opt['num_heads']] * opt['num_layers']) + [opt['num_out_heads']]
if opt['model'] == 'GAT':
model = GAT(g, opt['num_layers'], num_feats, opt['num_hidden'],
n_classes, heads, F.elu, opt['in_drop'], opt['attn_drop'],
opt['negative_slope'], opt['residual'], opt)
elif opt['model'] == 'AGNN':
model = AGNN(g, opt['num_layers'], num_feats, opt['num_hidden'],
n_classes, opt['in_drop'], opt)
model = model.to(device)
if torch.cuda.device_count() > 1:
model = nn.DataParallel(model)
parameters = [p for p in model.parameters() if p.requires_grad]
optimizer = get_optimizer(opt["optimizer"],
parameters,
lr=opt["lr"],
weight_decay=opt["weight_decay"])
if checkpoint_dir:
checkpoint = os.path.join(checkpoint_dir, "checkpoint")
model_state, optimizer_state = torch.load(checkpoint)
model.load_state_dict(model_state)
optimizer.load_state_dict(optimizer_state)
train_this = train
this_test = test_OGB if opt['dataset'] == 'ogbn-arxiv' else test
best_time = best_epoch = train_acc = val_acc = test_acc = 0
for epoch in range(1, opt["epoch"]):
# loss = train(model, optimizer, data)
loss = train_this(model, optimizer, features, train_mask,
labels)[0].item()
if opt["no_early"]:
tmp_train_acc, tmp_val_acc, tmp_test_acc = this_test(model, g)
best_time = opt['time']
else:
tmp_train_acc, tmp_val_acc, tmp_test_acc = this_test(model, g)
if tmp_val_acc > val_acc:
best_epoch = epoch
train_acc = tmp_train_acc
val_acc = tmp_val_acc
test_acc = tmp_test_acc
with tune.checkpoint_dir(step=epoch) as checkpoint_dir:
path = os.path.join(checkpoint_dir, "checkpoint")
torch.save((model.state_dict(), optimizer.state_dict()), path)
tune.report(loss=loss,
accuracy=val_acc,
test_acc=test_acc,
train_acc=train_acc,
best_time=best_time,
best_epoch=best_epoch)
if args.model == 'GAT':
model = GAT(nfeat=features.shape[1],
nhid=args.hidden,
nclass=int(labels.max()) + 1,
dropout=args.dropout,
nheads=args.nb_heads,
alpha=args.alpha)
elif args.model == 'GCN':
model = GCN(nfeat=features.shape[1],
nhid=args.hidden,
nclass=int(labels.max()) + 1,
dropout=args.dropout)
else:
raise ValueError("Model {} not registered".format(args.model))
optimizer = optim.Adadelta(model.parameters(),
lr=args.lr,
weight_decay=args.weight_decay)
features, adj, labels = Variable(features), Variable(adj), Variable(labels)
if args.cuda:
model.cuda()
features = features.cuda()
adj = adj.cuda()
labels = labels.cuda()
idx_train = idx_train.cuda()
idx_val = idx_val.cuda()
idx_test = idx_test.cuda()
random.seed(args.seed)
np.random.seed(args.seed)
torch.manual_seed(args.seed)
if args.cuda:
torch.cuda.manual_seed(args.seed)
# Load data
# adj, features, labels, idx_train, idx_val, idx_test = load_data()
adj, features, labels, idx_train, idx_val, idx_test = load_data_gat(path='data/', dataset_str=args.dataset)
# print(adj.sum(dim=0))
print(int(labels.max()) + 1)
# Model and optimizer
model = GAT(nfeat=features.shape[1], nhid=args.hidden, nclass=int(labels.max()) + 1, dropout=args.dropout, nheads=args.nb_heads, alpha=args.alpha)
optimizer = optim.Adam(model.parameters(), lr=args.lr, weight_decay=args.weight_decay)
if args.cuda:
model.cuda()
features = features.cuda()
adj = adj.cuda()
labels = labels.cuda()
idx_train = idx_train.cuda()
idx_val = idx_val.cuda()
idx_test = idx_test.cuda()
features, adj, labels = Variable(features), Variable(adj), Variable(labels)
# Train model
t_total = time.time()
loss_values = []
args = parser.parse_args()
args.cuda = not args.no_cuda and torch.cuda.is_available()
random.seed(args.seed)
np.random.seed(args.seed)
torch.manual_seed(args.seed)
if args.cuda:
torch.cuda.manual_seed(args.seed)
# Load data
adj, features, labels, idx_train, idx_val, idx_test = load_data()
# Model and optimizer
model = GAT(nfeat=features.shape[1], nhid=args.hidden, nclass=int(labels.max()) + 1, dropout=args.dropout, nheads=args.nb_heads, alpha=args.alpha)
optimizer = optim.Adam(model.parameters(), lr=args.lr, weight_decay=args.weight_decay)
if args.cuda:
model.cuda()
features = features.cuda()
adj = adj.cuda()
labels = labels.cuda()
idx_train = idx_train.cuda()
idx_val = idx_val.cuda()
idx_test = idx_test.cuda()
features, adj, labels = Variable(features), Variable(adj), Variable(labels)
def train(epoch):
t = time.time()
torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
print('loading data')
x, y, adj = load_data()
y_train = y[:60000]
x_train = x[:60000]
y_test = y[60000:]
x_test = x[60000:]
adj = torch.Tensor(adj)
print('loading on cuda')
model = GAT(nfeat=1, nhid=5, nclass=1, dropout=0.8, nheads=2, alpha=0.2)
optimizer = optim.Adam(model.parameters(), lr=0.005, weight_decay=5e-4)
model.cuda()
adj = adj.cuda()
def train(epoch):
# LR = [1.00e-02, 8.89e-03, 7.78e-03, 6.67e-03, 5.56e-03, 4.45e-03, 3.34e-03, 2.23e-03, 1.12e-03, 1.00e-05]
print('Epoch: ' + str(epoch))
n_iter = 500
batch_size = int(60000 / n_iter)
t = time.time()
