How to use the pgl.layers function in pgl
To help you get started, we’ve selected a few pgl examples, based on popular ways it is used in public projects.
Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
PaddlePaddle / PGL / examples / static_gat / train.py View on Github 
test_index = dataset.test_index
test_label = np.expand_dims(dataset.y[test_index], -1)
test_index = np.expand_dims(test_index, -1)
place = fluid.CUDAPlace(0) if args.use_cuda else fluid.CPUPlace()
train_program = fluid.Program()
startup_program = fluid.Program()
test_program = fluid.Program()
hidden_size = 16
with fluid.program_guard(train_program, startup_program):
gw = pgl.graph_wrapper.StaticGraphWrapper(
name="graph", graph=dataset.graph, place=place)
output = pgl.layers.gat(gw,
gw.node_feat["words"],
hidden_size,
activation="elu",
name="gat_layer_1",
num_heads=8,
feat_drop=0.6,
attn_drop=0.6,
is_test=False)
output = pgl.layers.gat(gw,
output,
dataset.num_classes,
num_heads=1,
activation=None,
name="gat_layer_2",
feat_drop=0.6,
attn_drop=0.6,with fluid.program_guard(train_program, startup_program):
gw = pgl.graph_wrapper.GraphWrapper(
name="graph",
place=place,
node_feat=dataset.graph.node_feat_info())
output = pgl.layers.gat(gw,
gw.node_feat["words"],
hidden_size,
activation="elu",
name="gat_layer_1",
num_heads=8,
feat_drop=0.6,
attn_drop=0.6,
is_test=False)
output = pgl.layers.gat(gw,
output,
dataset.num_classes,
num_heads=1,
activation=None,
name="gat_layer_2",
feat_drop=0.6,
attn_drop=0.6,
is_test=False)
node_index = fluid.layers.data(
"node_index",
shape=[None, 1],
dtype="int64",
append_batch_size=False)
node_label = fluid.layers.data(
"node_label",
shape=[None, 1],hidden_size = 16
with fluid.program_guard(train_program, startup_program):
gw = pgl.graph_wrapper.StaticGraphWrapper(
name="graph", graph=dataset.graph, place=place)
output = pgl.layers.gat(gw,
gw.node_feat["words"],
hidden_size,
activation="elu",
name="gat_layer_1",
num_heads=8,
feat_drop=0.6,
attn_drop=0.6,
is_test=False)
output = pgl.layers.gat(gw,
output,
dataset.num_classes,
num_heads=1,
activation=None,
name="gat_layer_2",
feat_drop=0.6,
attn_drop=0.6,
is_test=False)
val_program = train_program.clone(for_test=True)
test_program = train_program.clone(for_test=True)
initializer = []
with fluid.program_guard(train_program, startup_program):
train_node_index, init = paddle_helper.constant(
"train_node_index", dtype="int64", value=train_index)def main(args):
dataset = load(args.dataset)
place = fluid.CUDAPlace(0) if args.use_cuda else fluid.CPUPlace()
train_program = fluid.Program()
startup_program = fluid.Program()
test_program = fluid.Program()
hidden_size = 8
with fluid.program_guard(train_program, startup_program):
gw = pgl.graph_wrapper.GraphWrapper(
name="graph",
place=place,
node_feat=dataset.graph.node_feat_info())
output = pgl.layers.gat(gw,
gw.node_feat["words"],
hidden_size,
activation="elu",
name="gat_layer_1",
num_heads=8,
feat_drop=0.6,
attn_drop=0.6,
is_test=False)
output = pgl.layers.gat(gw,
output,
dataset.num_classes,
num_heads=1,
activation=None,
name="gat_layer_2",
feat_drop=0.6,
attn_drop=0.6,with fluid.program_guard(train_program, startup_program):
gw = pgl.graph_wrapper.GraphWrapper(
name="graph",
place=place,
node_feat=dataset.graph.node_feat_info())
output = pgl.layers.gcn(gw,
gw.node_feat["words"],
hidden_size,
activation="relu",
norm=gw.node_feat['norm'],
name="gcn_layer_1")
output = fluid.layers.dropout(
output, 0.5, dropout_implementation='upscale_in_train')
output = pgl.layers.gcn(gw,
output,
dataset.num_classes,
activation=None,
norm=gw.node_feat['norm'],
name="gcn_layer_2")
node_index = fluid.layers.data(
"node_index",
shape=[None, 1],
dtype="int64",
append_batch_size=False)
node_label = fluid.layers.data(
"node_label",
shape=[None, 1],
dtype="int64",
append_batch_size=False)val_index = np.expand_dims(val_index, -1)
test_index = dataset.test_index
test_label = np.expand_dims(dataset.y[test_index], -1)
test_index = np.expand_dims(test_index, -1)
place = fluid.CUDAPlace(0) if args.use_cuda else fluid.CPUPlace()
train_program = fluid.Program()
startup_program = fluid.Program()
test_program = fluid.Program()
hidden_size = 16
with fluid.program_guard(train_program, startup_program):
gw = pgl.graph_wrapper.StaticGraphWrapper(
name="graph", graph=dataset.graph, place=place)
output = pgl.layers.gcn(gw,
gw.node_feat["words"],
hidden_size,
activation="relu",
norm=gw.node_feat['norm'],
name="gcn_layer_1")
output = fluid.layers.dropout(
output, 0.5, dropout_implementation='upscale_in_train')
output = pgl.layers.gcn(gw,
output,
dataset.num_classes,
activation=None,
norm=gw.node_feat['norm'],
name="gcn_layer_2")
val_program = train_program.clone(for_test=True)
test_program = train_program.clone(for_test=True)norm[indegree > 0] = np.power(indegree[indegree > 0], -0.5)
dataset.graph.node_feat["norm"] = np.expand_dims(norm, -1)
place = fluid.CUDAPlace(0) if args.use_cuda else fluid.CPUPlace()
train_program = fluid.Program()
startup_program = fluid.Program()
test_program = fluid.Program()
hidden_size = 16
with fluid.program_guard(train_program, startup_program):
gw = pgl.graph_wrapper.GraphWrapper(
name="graph",
place=place,
node_feat=dataset.graph.node_feat_info())
output = pgl.layers.gcn(gw,
gw.node_feat["words"],
hidden_size,
activation="relu",
norm=gw.node_feat['norm'],
name="gcn_layer_1")
output = fluid.layers.dropout(
output, 0.5, dropout_implementation='upscale_in_train')
output = pgl.layers.gcn(gw,
output,
dataset.num_classes,
activation=None,
norm=gw.node_feat['norm'],
name="gcn_layer_2")
node_index = fluid.layers.data(
"node_index",
shape=[None, 1],startup_program = fluid.Program()
test_program = fluid.Program()
hidden_size = 16
with fluid.program_guard(train_program, startup_program):
gw = pgl.graph_wrapper.StaticGraphWrapper(
name="graph", graph=dataset.graph, place=place)
output = pgl.layers.gcn(gw,
gw.node_feat["words"],
hidden_size,
activation="relu",
norm=gw.node_feat['norm'],
name="gcn_layer_1")
output = fluid.layers.dropout(
output, 0.5, dropout_implementation='upscale_in_train')
output = pgl.layers.gcn(gw,
output,
dataset.num_classes,
activation=None,
norm=gw.node_feat['norm'],
name="gcn_layer_2")
val_program = train_program.clone(for_test=True)
test_program = train_program.clone(for_test=True)
initializer = []
with fluid.program_guard(train_program, startup_program):
train_node_index, init = paddle_helper.constant(
"train_node_index", dtype="int64", value=train_index)
initializer.append(init)
train_node_label, init = paddle_helper.constant(
Popular pgl functions
- pgl.data_loader
- pgl.data_loader.CitationDataset
- pgl.data_loader.CoraDataset
- pgl.graph.Graph
- pgl.graph_kernel
- pgl.graph_kernel.node2vec_sample
- pgl.graph_wrapper
- pgl.graph_wrapper.GraphWrapper
- pgl.graph_wrapper.StaticGraphWrapper
- pgl.layers
- pgl.redis_graph.RedisGraph
- pgl.utils.logger.log
- pgl.utils.logger.log.info
- pgl.utils.logger.log.warning
- pgl.utils.mp_reader.multiprocess_reader
- pgl.utils.op.read_rows
- pgl.utils.paddle_helper
- pgl.utils.paddle_helper.constant