def main(args):
data = load_data(args.normalize, args.symmetry)
log.info("preprocess finish")
log.info("Train Examples: %s" % len(data["train_index"]))
log.info("Val Examples: %s" % len(data["val_index"]))
log.info("Test Examples: %s" % len(data["test_index"]))
log.info("Num nodes %s" % data["graph"].num_nodes)
log.info("Num edges %s" % data["graph"].num_edges)
log.info("Average Degree %s" % np.mean(data["graph"].indegree()))
place = fluid.CUDAPlace(0) if args.use_cuda else fluid.CPUPlace()
train_program = fluid.Program()
startup_program = fluid.Program()
samples = []
if args.samples_1 > 0:
samples.append(args.samples_1)
if args.samples_2 > 0:
samples.append(args.samples_2)
with fluid.program_guard(train_program, startup_program):
feature, feature_init = paddle_helper.constant(
"feat",
dtype=data['feature'].dtype,
value=data['feature'],
hide_batch_size=False)
graph_wrapper = pgl.graph_wrapper.GraphWrapper(
"sub_graph",
fluid.CPUPlace(),
node_feat=data['graph'].node_feat_info())
model_loss, model_acc = build_graph_model(
graph_wrapper,
num_class=data["num_class"],
feature=feature,
hidden_size=args.hidden_size,
graphsage_type=args.graphsage_type,
k_hop=len(samples))
test_program = train_program.clone(for_test=True)
with fluid.program_guard(train_program, startup_program):
adam = fluid.optimizer.Adam(learning_rate=args.lr)
adam.minimize(model_loss)
exe = fluid.Executor(place)
exe.run(startup_program)
feature_init(place)
train_iter = reader.multiprocess_graph_reader(
data['graph'],
graph_wrapper,
samples=samples,
num_workers=args.sample_workers,
batch_size=args.batch_size,
with_parent_node_index=True,
node_index=data['train_index'],
node_label=data["train_label"])
val_iter = reader.multiprocess_graph_reader(
data['graph'],
graph_wrapper,
samples=samples,
num_workers=args.sample_workers,
batch_size=args.batch_size,
with_parent_node_index=True,
node_index=data['val_index'],
node_label=data["val_label"])
test_iter = reader.multiprocess_graph_reader(
data['graph'],
graph_wrapper,
samples=samples,
num_workers=args.sample_workers,
batch_size=args.batch_size,
with_parent_node_index=True,
node_index=data['test_index'],
node_label=data["test_label"])
for epoch in range(args.epoch):
run_epoch(train_iter,
program=train_program,
exe=exe,
prefix="train",
model_loss=model_loss,
model_acc=model_acc,
epoch=epoch)
run_epoch(val_iter,
program=test_program,
exe=exe,
prefix="val",
model_loss=model_loss,
model_acc=model_acc,
log_per_step=10000,
epoch=epoch)
run_epoch(test_iter,
program=test_program,
prefix="test",
exe=exe,
model_loss=model_loss,
model_acc=model_acc,
log_per_step=10000,
epoch=epoch)
def main(args):
"""main"""
data = load_data(args.normalize, args.symmetry)
log.info("preprocess finish")
log.info("Train Examples: %s" % len(data["train_index"]))
log.info("Val Examples: %s" % len(data["val_index"]))
log.info("Test Examples: %s" % len(data["test_index"]))
log.info("Num nodes %s" % data["graph"].num_nodes)
log.info("Num edges %s" % data["graph"].num_edges)
log.info("Average Degree %s" % np.mean(data["graph"].indegree()))
place = fluid.CUDAPlace(0) if args.use_cuda else fluid.CPUPlace()
train_program = fluid.Program()
startup_program = fluid.Program()
samples = []
if args.samples_1 > 0:
samples.append(args.samples_1)
if args.samples_2 > 0:
samples.append(args.samples_2)
with fluid.program_guard(train_program, startup_program):
graph_wrapper = pgl.graph_wrapper.GraphWrapper(
"sub_graph",
fluid.CPUPlace(),
node_feat=data['graph'].node_feat_info())
model_loss, model_acc = build_graph_model(
graph_wrapper,
num_class=data["num_class"],
hidden_size=args.hidden_size,
graphsage_type=args.graphsage_type,
k_hop=len(samples))
test_program = train_program.clone(for_test=True)
with fluid.program_guard(train_program, startup_program):
adam = fluid.optimizer.Adam(learning_rate=args.lr)
adam.minimize(model_loss)
exe = fluid.Executor(place)
exe.run(startup_program)
if args.num_trainer > 1:
build_strategy = fluid.BuildStrategy()
build_strategy.remove_unnecessary_lock = False
build_strategy.enable_sequential_execution = True
train_exe = fluid.ParallelExecutor(use_cuda=args.use_cuda,
main_program=train_program,
build_strategy=build_strategy,
loss_name=model_loss.name)
else:
train_exe = exe
if args.sample_workers > 1:
train_iter = reader.multiprocess_graph_reader(
data['graph'],
graph_wrapper,
samples=samples,
num_workers=args.sample_workers,
batch_size=args.batch_size,
node_index=data['train_index'],
node_label=data["train_label"])
else:
train_iter = reader.graph_reader(data['graph'],
graph_wrapper,
samples=samples,
batch_size=args.batch_size,
node_index=data['train_index'],
node_label=data["train_label"])
if args.sample_workers > 1:
val_iter = reader.multiprocess_graph_reader(
data['graph'],
graph_wrapper,
samples=samples,
num_workers=args.sample_workers,
batch_size=args.batch_size,
node_index=data['val_index'],
node_label=data["val_label"])
else:
val_iter = reader.graph_reader(data['graph'],
graph_wrapper,
samples=samples,
batch_size=args.batch_size,
node_index=data['val_index'],
node_label=data["val_label"])
if args.sample_workers > 1:
test_iter = reader.multiprocess_graph_reader(
data['graph'],
graph_wrapper,
samples=samples,
num_workers=args.sample_workers,
batch_size=args.batch_size,
node_index=data['test_index'],
node_label=data["test_label"])
else:
test_iter = reader.graph_reader(data['graph'],
graph_wrapper,
samples=samples,
batch_size=args.batch_size,
node_index=data['test_index'],
node_label=data["test_label"])
for epoch in range(args.epoch):
run_epoch(train_iter,
program=train_program,
exe=train_exe,
prefix="train",
model_loss=model_loss,
model_acc=model_acc,
num_trainer=args.num_trainer,
epoch=epoch)
run_epoch(val_iter,
program=test_program,
exe=exe,
prefix="val",
model_loss=model_loss,
model_acc=model_acc,
log_per_step=10000,
epoch=epoch)
run_epoch(test_iter,
program=test_program,
prefix="test",
exe=exe,
model_loss=model_loss,
model_acc=model_acc,
log_per_step=10000,
epoch=epoch)
with fluid.program_guard(train_program, startup_program):
lr = args.lr
adam = fluid.optimizer.Adam(
learning_rate=lr,
regularization=fluid.regularizer.L2DecayRegularizer(
regularization_coeff=args.rc))
adam.minimize(loss)
exe = fluid.Executor(place)
exe.run(startup_program)
train_iter = reader.multiprocess_graph_reader(
g,
gw,
samples=samples,
num_workers=sample_workers,
batch_size=batch_size,
with_parent_node_index=True,
node_index=train_idx,
node_label=np.array(label[train_idx], dtype='float32'))
val_iter = reader.multiprocess_graph_reader(
g,
gw,
samples=samples,
num_workers=sample_workers,
batch_size=batch_size,
with_parent_node_index=True,
node_index=valid_idx,
node_label=np.array(label[valid_idx], dtype='float32'))
def main(args):
data = load_data()
log.info("preprocess finish")
log.info("Train Examples: %s" % len(data["train_index"]))
log.info("Val Examples: %s" % len(data["val_index"]))
log.info("Test Examples: %s" % len(data["test_index"]))
place = fluid.CUDAPlace(0) if args.use_cuda else fluid.CPUPlace()
train_program = fluid.Program()
startup_program = fluid.Program()
samples = []
if args.samples_1 > 0:
samples.append(args.samples_1)
if args.samples_2 > 0:
samples.append(args.samples_2)
with fluid.program_guard(train_program, startup_program):
graph_wrapper = pgl.graph_wrapper.GraphWrapper(
"sub_graph", fluid.CPUPlace(), node_feat=[('feats', [None, 602], np.dtype('float32'))])
model_loss, model_acc = build_graph_model(
graph_wrapper,
num_class=data["num_class"],
hidden_size=args.hidden_size,
graphsage_type=args.graphsage_type,
k_hop=len(samples))
test_program = train_program.clone(for_test=True)
with fluid.program_guard(train_program, startup_program):
adam = fluid.optimizer.Adam(learning_rate=args.lr)
adam.minimize(model_loss)
exe = fluid.Executor(place)
exe.run(startup_program)
train_iter = reader.multiprocess_graph_reader(
graph_wrapper,
samples=samples,
num_workers=args.sample_workers,
batch_size=args.batch_size,
node_index=data['train_index'],
node_label=data["train_label"])
val_iter = reader.multiprocess_graph_reader(
graph_wrapper,
samples=samples,
num_workers=args.sample_workers,
batch_size=args.batch_size,
node_index=data['val_index'],
node_label=data["val_label"])
test_iter = reader.multiprocess_graph_reader(
graph_wrapper,
samples=samples,
num_workers=args.sample_workers,
batch_size=args.batch_size,
node_index=data['test_index'],
node_label=data["test_label"])
for epoch in range(args.epoch):
run_epoch(
train_iter,
program=train_program,
exe=exe,
prefix="train",
model_loss=model_loss,
model_acc=model_acc,
log_per_step=1,
epoch=epoch)
run_epoch(
val_iter,
program=test_program,
exe=exe,
prefix="val",
model_loss=model_loss,
model_acc=model_acc,
log_per_step=10000,
epoch=epoch)
run_epoch(
test_iter,
program=test_program,
prefix="test",
exe=exe,
model_loss=model_loss,
model_acc=model_acc,
log_per_step=10000,
epoch=epoch)