print("Test set results:", "loss= {:.4f}".format(loss_test.data.item()),
"r2_test= {:.4f}".format(r2_test),
"l0_norm_att_test: {}".format(l0_norm_att_test))
# Train model
t_total = time.time()
loss_values = []
bad_counter = 0
best = args.epochs + 1
best_epoch = 0
for epoch in range(args.epochs):
loss_values.append(train(epoch))
torch.save(model.state_dict(), filedir + '/{}.pkl'.format(epoch))
if loss_values[-1] < best:
best = loss_values[-1]
best_epoch = epoch
bad_counter = 0
else:
bad_counter += 1
if bad_counter == args.patience:
break
files = glob.glob(filedir + '/*.pkl')
for file in files:
epoch_nb = int(file.split('/')[-1][:-4])
if epoch_nb < best_epoch:
os.remove(file)
loss_test = F.nll_loss(output[idx_test], labels[idx_test])
acc_test = accuracy(output[idx_test], labels[idx_test])
print("Test set results:", "loss= {:.4f}".format(loss_test.item()),
"accuracy= {:.4f}".format(acc_test.item()))
# Train model
t_total = time.time()
loss_values = []
bad_counter = 0
best = args.epochs + 1
best_epoch = 0
for epoch in range(args.epochs):
loss_values.append(train(epoch))
torch.save(model.state_dict(), '{}.pkl'.format(epoch))
if loss_values[-1] < best:
best = loss_values[-1]
best_epoch = epoch
bad_counter = 0
else:
bad_counter += 1
if bad_counter == args.patience:
break
files = glob.glob('*.pkl')
for file in files:
epoch_nb = int(file.split('.')[0])
if epoch_nb < best_epoch:
os.remove(file)
def train_pipeline(self, adj, features, labels, idx_train, idx_val,
idx_test, *args):
adj = normalize_adj(adj + sp.eye(adj.shape[0]))
if sp.issparse(adj):
adj = adj.todense()
if sp.issparse(features):
features = features.todense()
# With networkx, we no longer need to convert from one-hot encoding...
# labels = np.where(labels)[1]
adj = torch.FloatTensor(adj)
features = torch.FloatTensor(features)
labels = torch.LongTensor(labels)
idx_train = torch.LongTensor(idx_train)
idx_val = torch.LongTensor(idx_val)
idx_test = torch.LongTensor(idx_test)
random.seed(self.args.seed)
np.random.seed(self.args.seed)
torch.manual_seed(self.args.seed)
if self.args.cuda:
torch.cuda.manual_seed(self.args.seed)
# Model and optimizer
if self.args.sparse:
model = SpGAT(
nfeat=features.shape[1],
nhid=self.args.hidden,
nclass=int(labels.max()) + 1,
dropout=self.args.dropout,
nheads=self.args.nb_heads,
alpha=self.args.alpha,
)
else:
model = GAT(
nfeat=features.shape[1],
nhid=self.args.hidden,
nclass=int(labels.max()) + 1,
dropout=self.args.dropout,
nheads=self.args.nb_heads,
alpha=self.args.alpha,
)
optimizer = optim.Adam(model.parameters(),
lr=self.args.lr,
weight_decay=self.args.weight_decay)
if self.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)
# TODO: Test if these lines could be written below line 41.
self.adj = adj
self.features = features
self.labels = labels
self.idx_train = idx_train
self.idx_val = idx_val
self.idx_test = idx_test
def train(epoch):
t = time.time()
model.train()
optimizer.zero_grad()
output = model(features, adj)
loss_train = F.nll_loss(output[idx_train], labels[idx_train])
acc_train = accuracy(output[idx_train], labels[idx_train])
loss_train.backward()
optimizer.step()
if not self.args.fastmode:
# Evaluate validation set performance separately,
# deactivates dropout during validation run.
model.eval()
output = model(features, adj)
loss_val = F.nll_loss(output[idx_val], labels[idx_val])
acc_val = accuracy(output[idx_val], labels[idx_val])
print(
"Epoch: {:04d}".format(epoch + 1),
"loss_train: {:.4f}".format(loss_train.data.item()),
"acc_train: {:.4f}".format(acc_train.data.item()),
"loss_val: {:.4f}".format(loss_val.data.item()),
"acc_val: {:.4f}".format(acc_val.data.item()),
"time: {:.4f}s".format(time.time() - t),
)
return loss_val.data.item()
# Train model
t_total = time.time()
loss_values = []
bad_counter = 0
best = self.args.epochs + 1
best_epoch = 0
for epoch in range(self.args.epochs):
loss_values.append(train(epoch))
torch.save(model.state_dict(), "{}.pkl".format(epoch))
if loss_values[-1] < best:
best = loss_values[-1]
best_epoch = epoch
bad_counter = 0
else:
bad_counter += 1
if bad_counter == self.args.patience:
break
files = glob.glob("*.pkl")
for file in files:
epoch_nb = int(file.split(".")[0])
if epoch_nb < best_epoch:
os.remove(file)
files = glob.glob("*.pkl")
for file in files:
epoch_nb = int(file.split(".")[0])
if epoch_nb > best_epoch:
os.remove(file)
print("Optimization Finished!")
print("Total time elapsed: {:.4f}s".format(time.time() - t_total))
# Restore best model
print("Loading {}th epoch".format(best_epoch))
model.load_state_dict(torch.load("{}.pkl".format(best_epoch)))
self.model = model
return model
def main():
args.data_dir = os.path.join(args.data_dir, args.dataset)
args.output_dir = os.path.join(args.output_dir, args.dataset)
if os.path.exists(args.output_dir) and os.listdir(args.output_dir):
print("Output directory ({}) already exists and is not empty.".format(
args.output_dir))
else:
os.makedirs(args.output_dir, exist_ok=True)
random.seed(args.seed)
np.random.seed(args.seed)
torch.manual_seed(args.seed)
if CUDA:
args.use_cuda = CUDA
torch.cuda.manual_seed_all(args.seed)
torch.backends.cudnn.deterministic = True
print("args = ", args)
ori_model = 'None'
ori_load = True
for idx in range(args.N):
data_idx = idx
# Load data
adj, features, labels, idx_train, idx_val, idx_test, test_sub_idx, ori_adj, ori_idx_train, ori_idx_valid = \
load_data(args, data_idx, base_path=args.data_dir, dataset=args.dataset)
file_name = "model_name_" + str(args.model_name) + "_lr_" + str(
args.lr) + "_epochs_" + str(args.epochs) + "_k_factors_" + str(
args.k_factors) + "_up_bound_" + str(
args.up_bound) + "_top_n_" + str(
args.top_n) + "_att_lr_" + str(
args.att_lr) + "_hidden_" + str(
args.hidden) + "_w1_" + str(args.w1)
if args.all_data:
model_path = os.path.join(args.output_dir, file_name)
else:
model_path = os.path.join(args.output_dir, str(data_idx),
file_name)
if not os.path.exists(model_path):
os.makedirs(model_path)
# Model and optimizer
if args.model_name == "SpGAT":
model = SpGAT(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_name == "SpGAT_2":
model = SpGAT_2(nfeat=features.shape[1],
nclass=int(labels.max()) + 1,
config=args)
elif args.model_name == "SpGAT2":
model = SpGAT_2(nfeat=features.shape[1],
nclass=int(labels.max()) + 1,
config=args)
else:
model = GAT(nfeat=features.shape[1],
nhid=args.hidden,
nclass=int(labels.max()) + 1,
dropout=args.dropout,
nheads=args.nb_heads,
alpha=args.alpha)
print("load path", args.load)
if args.load != 'None' and ori_load:
model = load_model(model, args.load)
print("model loaded")
ori_load = False
if ori_model != 'None':
model = copy.deepcopy(ori_model)
print("load model from", idx - 1)
print(model.state_dict().keys())
if CUDA:
model.cuda()
features = Variable(features.cuda())
adj = Variable(adj.cuda())
labels = Variable(labels.cuda())
idx_train = idx_train.cuda()
idx_val = idx_val.cuda()
idx_test = idx_test.cuda()
if "_" in args.model_name and not args.all_data and data_idx > 0 and ori_adj is not None:
ori_adj = Variable(ori_adj.cuda())
ori_idx_train = ori_idx_train.cuda()
ori_idx_valid = ori_idx_valid.cuda()
loader = Corpus(features, adj, labels, idx_train, idx_val, idx_test,
ori_adj, ori_idx_train, ori_idx_valid)
for name, param in model.named_parameters():
if param.requires_grad == False:
print("False", name)
param.requires_grad = True
best_epoch = 0
if args.evaluate == 0:
best_epoch = train(model, model_path, loader, data_idx)
ori_model = copy.deepcopy(model)
evaluate(model,
model_path,
loader,
data_idx,
best_epoch=best_epoch,
test_sub_idx=test_sub_idx)
evaluate(model,
model_path,
loader,
data_idx,
best_epoch=best_epoch,
test_sub_idx=test_sub_idx,
best_or_final='final')
args.load = os.path.join(model_path, 'trained_final.pth')
# Train model
t_total = time.time()
loss_values = []
bad_counter = 0
best = args.epochs + 1
best_epoch = 0
if not os.path.exists(f'./saved_models/{args.dataset}/'):
os.mkdir(f'./saved_models/{args.dataset}/')
for epoch in range(args.epochs):
loss_values.append(train(epoch))
if loss_values[-1] < best:
torch.save(model.state_dict(),
f'./saved_models/{args.dataset}/best.pkl')
best = loss_values[-1]
best_epoch = epoch
bad_counter = 0
else:
bad_counter += 1
if bad_counter == args.patience:
break
# files = glob.glob(f'./saved_models/{args.dataset}/*.pkl')
# for file in files:
# epoch_nb = int(file.split('.')[0])
# if epoch_nb < best_epoch:
# os.remove(file)
def train_pipeline(self, *args, custom_function=True, function=None):
random.seed(self.args.seed)
np.random.seed(self.args.seed)
torch.manual_seed(self.args.seed)
if self.args.cuda:
torch.cuda.manual_seed(self.args.seed)
# Load data
adj, features, labels, idx_train, idx_val, idx_test = new_load_data(
*args, custom_function=custom_function, function=function)
# Model and optimizer
if self.args.sparse:
model = SpGAT(nfeat=features.shape[1],
nhid=self.args.hidden,
nclass=int(labels.max()) + 1,
dropout=self.args.dropout,
nheads=self.args.nb_heads,
alpha=self.args.alpha)
else:
model = GAT(nfeat=features.shape[1],
nhid=self.args.hidden,
nclass=int(labels.max()) + 1,
dropout=self.args.dropout,
nheads=self.args.nb_heads,
alpha=self.args.alpha)
optimizer = optim.Adam(model.parameters(),
lr=self.args.lr,
weight_decay=self.args.weight_decay)
if self.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)
# TODO: Test if these lines could be written below line 41.
self.adj = adj
self.features = features
self.labels = labels
self.idx_train = idx_train
self.idx_val = idx_val
self.idx_test = idx_test
def train(epoch):
t = time.time()
model.train()
optimizer.zero_grad()
output = model(features, adj)
loss_train = F.nll_loss(output[idx_train], labels[idx_train])
acc_train = accuracy(output[idx_train], labels[idx_train])
loss_train.backward()
optimizer.step()
if not self.args.fastmode:
# Evaluate validation set performance separately,
# deactivates dropout during validation run.
model.eval()
output = model(features, adj)
loss_val = F.nll_loss(output[idx_val], labels[idx_val])
acc_val = accuracy(output[idx_val], labels[idx_val])
print('Epoch: {:04d}'.format(epoch + 1),
'loss_train: {:.4f}'.format(loss_train.data.item()),
'acc_train: {:.4f}'.format(acc_train.data.item()),
'loss_val: {:.4f}'.format(loss_val.data.item()),
'acc_val: {:.4f}'.format(acc_val.data.item()),
'time: {:.4f}s'.format(time.time() - t))
return loss_val.data.item()
# Train model
t_total = time.time()
loss_values = []
bad_counter = 0
best = self.args.epochs + 1
best_epoch = 0
for epoch in range(self.args.epochs):
loss_values.append(train(epoch))
torch.save(model.state_dict(), '{}.pkl'.format(epoch))
if loss_values[-1] < best:
best = loss_values[-1]
best_epoch = epoch
bad_counter = 0
else:
bad_counter += 1
if bad_counter == self.args.patience:
break
files = glob.glob('*.pkl')
for file in files:
epoch_nb = int(file.split('.')[0])
if epoch_nb < best_epoch:
os.remove(file)
files = glob.glob('*.pkl')
for file in files:
epoch_nb = int(file.split('.')[0])
if epoch_nb > best_epoch:
os.remove(file)
print("Optimization Finished!")
print("Total time elapsed: {:.4f}s".format(time.time() - t_total))
# Restore best model
print('Loading {}th epoch'.format(best_epoch))
model.load_state_dict(torch.load('{}.pkl'.format(best_epoch)))
self.model = model
return model
def __init__(self,graph,sparse = False,epochs = 200,learning_rate = 0.005,
weight_decay = 5e-4,hidden = 8,nb_heads = 8,drop_out = 0.6,
alpha = 0.2 ,patience = 100,train = 1500,val = 2000,test = 3100):
self.graph = graph
self.sparse = sparse
self.epochs = epochs
self.learning_rate = learning_rate
self.weight_decay = weight_decay
self.hidden = hidden
self.nb_heads = nb_heads
self.drop_out = drop_out
self.alpha = alpha
self.patience = patience
self.train = train
self.val = val
self.test = test
idx_train,idx_val , idx_test = self.load_data()
random.seed(random_seed)
np.random.seed(random_seed)
torch.manual_seed(random_seed)
if self.sparse:
model = SpGAT(nfeat=self.features.shape[1],
nhid=self.hidden,
nclass=int(self.labels.max()) + 1,
dropout=self.drop_out,
nheads=self.nb_heads,
alpha=self.alpha)
else:
model = GAT(nfeat=self.features.shape[1],
nhid=self.hidden,
nclass=int(self.labels.max()) + 1,
dropout=self.drop_out,
nheads=self.nb_heads,
alpha=self.alpha)
optimizer = optim.Adam(model.parameters(),
lr=self.learning_rate,
weight_decay=self.weight_decay)
#利用GPU
# device = torch.device("cuda:0")
# torch.cuda.empty_cache()
# model.to(device)
# self.features = self.features.to(device)
# self.adj = self.adj.to(device)
# self.labels = self.labels.to(device)
# idx_train = idx_train.to(device)
# idx_val = idx_val.to(device)
# idx_test = idx_test.to(device)
features, adj, labels = Variable(self.features), Variable(self.adj), Variable(self.labels)
t_total = time.time()
loss_values = []
bad_counter = 0
best = self.epochs + 1
best_epoch = 0
for epoch in range(self.epochs):
t = time.time()
model.train()
optimizer.zero_grad()
output = model(features, adj)
loss_train = F.nll_loss(output[idx_train], labels[idx_train])
acc_train = accuracy(output[idx_train], labels[idx_train])
loss_train.backward()
optimizer.step()
model.eval()
output = model(features, adj)
loss_val = F.nll_loss(output[idx_val], labels[idx_val])
acc_val = accuracy(output[idx_val], labels[idx_val])
print('Epoch: {:04d}'.format(epoch + 1),
'loss_train: {:.4f}'.format(loss_train.data),
'acc_train: {:.4f}'.format(acc_train.data),
'loss_val: {:.4f}'.format(loss_val.data),
'acc_val: {:.4f}'.format(acc_val.data),
'time: {:.4f}s'.format(time.time() - t))
loss_values.append(loss_val.data)
torch.save(model.state_dict(), '{}.pkl'.format(epoch))
if loss_values[-1] < best:
best = loss_values[-1]
best_epoch = epoch
bad_counter = 0
else:
bad_counter += 1
if bad_counter == self.patience:
break
files = glob.glob('*.pkl')
for file in files:
epoch_nb = int(file.split('.')[0])
if epoch_nb < best_epoch:
os.remove(file)
print("Optimization Finished!")
print("Total time elapsed: {:.4f}s".format(time.time() - t_total))
print('Loading {}th epoch'.format(best_epoch))
model.load_state_dict(torch.load('{}.pkl'.format(best_epoch)))
model.eval()
output = model(features, adj)
loss_test = F.nll_loss(output[idx_test], labels[idx_test])
acc_test = accuracy(output[idx_test], labels[idx_test])
print("Test set results:",
"loss= {:.4f}".format(loss_test.data),
"accuracy= {:.4f}".format(acc_test.data))