dmlc--dgl
Zihao Ye
9a0511c8e9
* upd * damn it * fuck * fuck pylint * fudge * remove some comments about MXNet * upd * upd * damn it * damn it * fuck * fuck * upd * upd * pylint bastard * upd * upd * upd * upd * upd * upd * upd * upd * upd
122 行
3.8 KiB
Python
122 行
3.8 KiB
Python
"""
|
|
This code was modified from the GCN implementation in DGL examples.
|
|
Simplifying Graph Convolutional Networks
|
|
Paper: https://arxiv.org/abs/1902.07153
|
|
Code: https://github.com/Tiiiger/SGC
|
|
SGC implementation in DGL.
|
|
"""
|
|
import argparse, time, math
|
|
import numpy as np
|
|
import mxnet as mx
|
|
from mxnet import nd, gluon
|
|
from mxnet.gluon import nn
|
|
from dgl import DGLGraph
|
|
from dgl.data import register_data_args, load_data
|
|
from dgl.nn.mxnet.conv import SGConv
|
|
|
|
|
|
def evaluate(model, g, features, labels, mask):
|
|
pred = model(g, features).argmax(axis=1)
|
|
accuracy = ((pred == labels) * mask).sum() / mask.sum().asscalar()
|
|
return accuracy.asscalar()
|
|
|
|
def main(args):
|
|
# load and preprocess dataset
|
|
data = load_data(args)
|
|
features = nd.array(data.features)
|
|
labels = nd.array(data.labels)
|
|
train_mask = nd.array(data.train_mask)
|
|
val_mask = nd.array(data.val_mask)
|
|
test_mask = nd.array(data.test_mask)
|
|
|
|
in_feats = features.shape[1]
|
|
n_classes = data.num_labels
|
|
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.sum().asscalar(),
|
|
val_mask.sum().asscalar(),
|
|
test_mask.sum().asscalar()))
|
|
|
|
if args.gpu < 0:
|
|
ctx = mx.cpu(0)
|
|
else:
|
|
ctx = mx.gpu(args.gpu)
|
|
|
|
features = features.as_in_context(ctx)
|
|
labels = labels.as_in_context(ctx)
|
|
train_mask = train_mask.as_in_context(ctx)
|
|
val_mask = val_mask.as_in_context(ctx)
|
|
test_mask = test_mask.as_in_context(ctx)
|
|
|
|
# graph preprocess and calculate normalization factor
|
|
g = DGLGraph(data.graph)
|
|
n_edges = g.number_of_edges()
|
|
# add self loop
|
|
g.add_edges(g.nodes(), g.nodes())
|
|
|
|
# create SGC model
|
|
model = SGConv(in_feats,
|
|
n_classes,
|
|
k=2,
|
|
cached=True,
|
|
bias=args.bias)
|
|
|
|
model.initialize(ctx=ctx)
|
|
n_train_samples = train_mask.sum().asscalar()
|
|
loss_fcn = gluon.loss.SoftmaxCELoss()
|
|
|
|
# use optimizer
|
|
print(model.collect_params())
|
|
trainer = gluon.Trainer(model.collect_params(), 'adam',
|
|
{'learning_rate': args.lr, 'wd': args.weight_decay})
|
|
|
|
# initialize graph
|
|
dur = []
|
|
for epoch in range(args.n_epochs):
|
|
if epoch >= 3:
|
|
t0 = time.time()
|
|
# forward
|
|
with mx.autograd.record():
|
|
pred = model(g, features)
|
|
loss = loss_fcn(pred, labels, mx.nd.expand_dims(train_mask, 1))
|
|
loss = loss.sum() / n_train_samples
|
|
|
|
loss.backward()
|
|
trainer.step(batch_size=1)
|
|
|
|
if epoch >= 3:
|
|
loss.asscalar()
|
|
dur.append(time.time() - t0)
|
|
acc = evaluate(model, g, features, labels, val_mask)
|
|
print("Epoch {:05d} | Time(s) {:.4f} | Loss {:.4f} | Accuracy {:.4f} | "
|
|
"ETputs(KTEPS) {:.2f}". format(
|
|
epoch, np.mean(dur), loss.asscalar(), acc, n_edges / np.mean(dur) / 1000))
|
|
|
|
# test set accuracy
|
|
acc = evaluate(model, g, features, labels, test_mask)
|
|
print("Test accuracy {:.2%}".format(acc))
|
|
|
|
|
|
if __name__ == '__main__':
|
|
parser = argparse.ArgumentParser(description='SGC')
|
|
register_data_args(parser)
|
|
parser.add_argument("--gpu", type=int, default=-1,
|
|
help="gpu")
|
|
parser.add_argument("--lr", type=float, default=0.2,
|
|
help="learning rate")
|
|
parser.add_argument("--bias", action='store_true', default=False,
|
|
help="flag to use bias")
|
|
parser.add_argument("--n-epochs", type=int, default=100,
|
|
help="number of training epochs")
|
|
parser.add_argument("--weight-decay", type=float, default=5e-6,
|
|
help="Weight for L2 loss")
|
|
args = parser.parse_args()
|
|
print(args)
|
|
|
|
main(args) |