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))
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)
