def fast_train_mp(self):
""" multi-cpu-core or mix cpu & multi-gpu """
self.init_device_emb()
self.emb_model.share_memory()
sum_up_params(self.emb_model)
start_all = time.time()
ps = []
for i in range(len(self.args.gpus)):
p = mp.Process(target=self.fast_train_sp,
args=(i, self.args.gpus[i]))
ps.append(p)
p.start()
for p in ps:
p.join()
print("Used time: %.2fs" % (time.time() - start_all))
if self.args.save_in_pt:
self.emb_model.save_embedding_pt(self.dataset,
self.args.output_emb_file)
else:
self.emb_model.save_embedding(self.dataset,
self.args.output_emb_file)
def fast_train(self):
""" fast train with dataloader with only gpu / only cpu"""
# the number of postive node pairs of a node sequence
num_pos = 2 * self.args.walk_length * self.args.window_size\
- self.args.window_size * (self.args.window_size + 1)
num_pos = int(num_pos)
self.init_device_emb()
if self.args.async_update:
self.emb_model.share_memory()
self.emb_model.create_async_update()
if self.args.count_params:
sum_up_params(self.emb_model)
sampler = self.dataset.create_sampler(0)
dataloader = DataLoader(
dataset=sampler.seeds,
batch_size=self.args.batch_size,
collate_fn=sampler.sample,
shuffle=False,
drop_last=False,
num_workers=self.args.num_sampler_threads,
)
num_batches = len(dataloader)
print("num batchs: %d\n" % num_batches)
start_all = time.time()
start = time.time()
with torch.no_grad():
max_i = num_batches
for i, walks in enumerate(dataloader):
if self.args.fast_neg:
self.emb_model.fast_learn(walks)
else:
# do negative sampling
bs = len(walks)
neg_nodes = torch.LongTensor(
np.random.choice(self.dataset.neg_table,
bs * num_pos * self.args.negative,
replace=True))
self.emb_model.fast_learn(walks, neg_nodes=neg_nodes)
if i > 0 and i % self.args.print_interval == 0:
if self.args.print_loss:
print("Batch %d training time: %.2fs loss: %.4f" \
% (i, time.time()-start, -sum(self.emb_model.loss)/self.args.print_interval))
self.emb_model.loss = []
else:
print("Batch %d, training time: %.2fs" %
(i, time.time() - start))
start = time.time()
if self.args.async_update:
self.emb_model.finish_async_update()
print("Training used time: %.2fs" % (time.time() - start_all))
if self.args.save_in_txt:
self.emb_model.save_embedding_txt(self.dataset,
self.args.output_emb_file)
elif self.args.save_in_pt:
self.emb_model.save_embedding_pt(self.dataset,
self.args.output_emb_file)
else:
self.emb_model.save_embedding(self.dataset,
self.args.output_emb_file)
def fast_train(self):
""" fast train with dataloader with only gpu / only cpu"""
self.init_device_emb()
if self.args.async_update:
self.emb_model.share_memory()
self.emb_model.create_async_update()
sum_up_params(self.emb_model)
sampler = self.dataset.create_sampler(0)
dataloader = DataLoader(
dataset=sampler.seeds,
batch_size=self.args.batch_size,
collate_fn=sampler.sample,
shuffle=False,
drop_last=False,
num_workers=self.args.num_sampler_threads,
)
num_batches = len(dataloader)
print("num batchs: %d\n" % num_batches)
start_all = time.time()
start = time.time()
with torch.no_grad():
for i, edges in enumerate(dataloader):
if self.args.fast_neg:
self.emb_model.fast_learn(edges)
else:
# do negative sampling
bs = edges.size()[0]
neg_nodes = torch.LongTensor(
np.random.choice(self.dataset.neg_table,
bs * self.args.negative,
replace=True))
self.emb_model.fast_learn(edges, neg_nodes=neg_nodes)
if i > 0 and i % self.args.print_interval == 0:
if self.args.print_loss:
if self.args.only_fst:
print("Batch %d time: %.2fs fst-loss: %.4f" \
% (i, time.time()-start, -sum(self.emb_model.loss_fst)/self.args.print_interval))
elif self.args.only_snd:
print("Batch %d time: %.2fs snd-loss: %.4f" \
% (i, time.time()-start, -sum(self.emb_model.loss_snd)/self.args.print_interval))
else:
print("Batch %d time: %.2fs fst-loss: %.4f snd-loss: %.4f" \
% (i, time.time()-start, \
-sum(self.emb_model.loss_fst)/self.args.print_interval, \
-sum(self.emb_model.loss_snd)/self.args.print_interval))
self.emb_model.loss_fst = []
self.emb_model.loss_snd = []
else:
print("Batch %d, training time: %.2fs" %
(i, time.time() - start))
start = time.time()
if self.args.async_update:
self.emb_model.finish_async_update()
print("Training used time: %.2fs" % (time.time() - start_all))
if self.args.save_in_pt:
self.emb_model.save_embedding_pt(self.dataset,
self.args.output_emb_file)
else:
self.emb_model.save_embedding(self.dataset,
self.args.output_emb_file)
def fast_train(self):
""" fast train with dataloader """
# the number of postive node pairs of a node sequence
num_pos = 2 * self.args.walk_length * self.args.window_size\
- self.args.window_size * (self.args.window_size + 1)
num_pos = int(num_pos)
self.init_device_emb()
if self.args.count_params:
sum_up_params(self.emb_model)
sampler = self.dataset.create_sampler(0)
dataloader = DataLoader(
dataset=sampler.seeds,
batch_size=self.args.batch_size,
collate_fn=sampler.sample,
shuffle=False,
drop_last=False,
num_workers=4,
)
num_batches = len(dataloader)
print("num batchs: %d" % num_batches)
start_all = time.time()
start = time.time()
with torch.no_grad():
max_i = self.args.iterations * num_batches
for iteration in range(self.args.iterations):
print("\nIteration: " + str(iteration + 1))
for i, walks in enumerate(dataloader):
# decay learning rate for SGD
lr = self.args.lr * (max_i - i) / max_i
if lr < 0.00001:
lr = 0.00001
if self.args.fast_neg:
self.emb_model.fast_learn(walks, lr)
else:
# do negative sampling
bs = len(walks)
neg_nodes = torch.LongTensor(
np.random.choice(self.dataset.neg_table,
bs * num_pos * self.args.negative,
replace=True))
self.emb_model.fast_learn(walks,
lr,
neg_nodes=neg_nodes)
if i > 0 and i % self.args.print_interval == 0:
if self.args.print_loss:
print("Batch %d training time: %.2fs loss: %.4f" \
% (i, time.time()-start, -sum(self.emb_model.loss)/self.args.print_interval))
self.emb_model.loss = []
else:
print("Batch %d, training time: %.2fs" %
(i, time.time() - start))
start = time.time()
print("Training used time: %.2fs" % (time.time() - start_all))
if self.args.save_in_txt:
self.emb_model.save_embedding_txt(self.dataset,
self.args.output_emb_file)
elif self.args.save_in_pt:
self.emb_model.save_embedding_pt(self.dataset,
self.args.output_emb_file)
else:
self.emb_model.save_embedding(self.dataset,
self.args.output_emb_file)
