GCN源代码注释的解释,源码,解读
1. utils.py
import numpy as np
import pickle as pkl
import networkx as nx
import scipy.sparse as sp
from scipy.sparse.linalg.eigen.arpack import eigsh
import sys
def parse_index_file(filename):
"""Parse index file."""
index = []
for line in open(filename):
index.append(int(line.strip()))
return index
def sample_mask(idx, l):
"""Create mask."""
mask = np.zeros(l)
mask[idx] = 1
return np.array(mask, dtype=np.bool)
def load_data(dataset_str):
"""
Loads input data from gcn/data directory
ind.dataset_str.x => the feature vectors of the training instances as scipy.sparse.csr.csr_matrix object;
ind.dataset_str.tx => the feature vectors of the test instances as scipy.sparse.csr.csr_matrix object;
ind.dataset_str.allx => the feature vectors of both labeled and unlabeled training instances
(a superset of ind.dataset_str.x) as scipy.sparse.csr.csr_matrix object;
ind.dataset_str.y => the one-hot labels of the labeled training instances as numpy.ndarray object;
ind.dataset_str.ty => the one-hot labels of the test instances as numpy.ndarray object;
ind.dataset_str.ally => the labels for instances in ind.dataset_str.allx as numpy.ndarray object;
ind.dataset_str.graph => a dict in the format {index: [index_of_neighbor_nodes]} as collections.defaultdict object;
ind.dataset_str.test.index => the indices of test instances in graph, for the inductive setting as list object. 归纳这些test结点
All objects above must be saved using python pickle module.
:param dataset_str: Dataset name
:return: All data input files loaded (as well the training/test data).
"""
names = ['x', 'y', 'tx', 'ty', 'allx', 'ally', 'graph']
objects = []
for i in range(len(names)):
with open("data/ind.{}.{}".format(dataset_str, names[i]), 'rb') as f:
if sys.version_info > (3, 0):
objects.append(pkl.load(f, encoding='latin1'))
else:
objects.append(pkl.load(f))
x, y, tx, ty, allx, ally, graph = tuple(objects)
test_idx_reorder = parse_index_file(
"data/ind.{}.test.index".format(dataset_str))
test_idx_range = np.sort(test_idx_reorder)
if dataset_str == 'citeseer':
# Fix citeseer dataset (there are some isolated nodes in the graph)
# Find isolated nodes, add them as zero-vecs into the right position
test_idx_range_full = range(
min(test_idx_reorder), max(test_idx_reorder)+1)
tx_extended = sp.lil_matrix((len(test_idx_range_full), x.shape[1]))
tx_extended[test_idx_range-min(test_idx_range), :] = tx
tx = tx_extended
ty_extended = np.zeros((len(test_idx_range_full), y.shape[1]))
ty_extended[test_idx_range-min(test_idx_range), :] = ty
ty = ty_extended
features = sp.vstack((allx, tx)).tolil()
""" example
it works for numpy
arr = np.array([2, 3, 4, 5, 6])
idx_reorder = [4, 3, 2, 1, 0] # the disorder indices of arr
# we are going to order the arr in a sort indices
idx_range = np.sort(idx_reorder)
arr[idx_reorder] = arr[idx_range]
print(arr)
>>> [6 5 4 3 2]
----- lil matrix ----
feature = sp.lil_matrix(np.array([[2], [3], [4], [5], [6]]))
>>> (0, 0) 2
(1, 0) 3
(2, 0) 4
(3, 0) 5
(4, 0) 6
idx_reorder = [4, 3, 2, 1, 0] # the disorder indices of feature
# we are going to order the feature in a sort indices
idx_range = np.sort(idx_reorder)
feature[idx_reorder, :] = feature[idx_range, :] # [4,3,2,1,0] => [0,1,2,3,4] 原本 4 位置的值被0替换掉
>>> (0, 0) 6
(1, 0) 5
(2, 0) 4
(3, 0) 3
(4, 0) 2
"""
features[test_idx_reorder, :] = features[test_idx_range,:]
# 把特征矩阵还原 和对应的邻接矩阵对应起来 因为之前是打乱的
adj = nx.adjacency_matrix(nx.from_dict_of_lists(graph))
labels = np.vstack((ally, ty))
labels[test_idx_reorder, :] = labels[test_idx_range, :]
idx_test = test_idx_range.tolist() # [1708,2707]
idx_train = range(len(y)) # [0,140)
idx_val = range(len(y), len(y)+500) #[140,640)
""" bool [True True True ... False False False]
train_mask = [0,140)为True 其余为False
val_mask = [140,640)为True 其余为False
test_mask = [1708, 2707]为True 其余为False
"""
train_mask = sample_mask(idx_train, labels.shape[0])
val_mask = sample_mask(idx_val, labels.shape[0])
test_mask = sample_mask(idx_test, labels.shape[0])
y_train = np.zeros(labels.shape)
y_val = np.zeros(labels.shape)
y_test = np.zeros(labels.shape)
""" 替换False的位置为0
a = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9], [10, 11, 12]])
mask = np.zeros(len(a))
idx = [1, 2]
mask[idx] = 1
mask = np.array(mask, dtype=np.bool)
a_ = np.zeros(a.shape)
a_[mask, :] = a[mask, :]
print(a_mask)
>>> [[0. 0. 0.]
[4. 5. 6.]
[7. 8. 9.]
[0. 0. 0.]]
"""
y_train[train_mask, :] = labels[train_mask, :]
y_val[val_mask, :] = labels[val_mask, :]
y_test[test_mask, :] = labels[test_mask, :]
return adj, features, y_train, y_val, y_test, train_mask, val_mask, test_mask
def sparse_to_tuple(sparse_mx):
"""Convert sparse matrix to tuple representation.
将稀疏矩阵转换为元组形式(行列坐标,值,shape)"""
def to_tuple(mx):
if not sp.isspmatrix_coo(mx): # 判断mx是否为coo_matrix
mx = mx.tocoo() # 返回稀疏矩阵coo_matrix形式
coords = np.vstack((mx.row, mx.col)).transpose() # 矩阵mx的行和列索引
values = mx.data # 矩阵mx的值
shape = mx.shape # 矩阵mx的形状
""" example:
a = [[1,0,2],
[0,0,3],
[5,0,0]]
mx = coo_matrix(a)
>>> (0, 0) 1
(0, 2) 2
(1, 2) 3
(2, 0) 5
mx.row => [0,0,1,2]
mx.col => [0,2,2,0]
np.vstack((mx.row,mx.col)).transpose()
>>> [[0 0]
[0 2]
[1 2]
[2 0]]
mx.data
>>> [1 2 3 5]
mx.shape
>>> (3, 3)
:return: tuple
>>> (array([[0, 0], [0, 2], [1, 2], [2, 0]], dtype=int32),
array([1, 2, 3, 5]), (3, 3))
"""
return coords, values, shape
if isinstance(sparse_mx, list): # 判断sparse_mx是否为list类型
for i in range(len(sparse_mx)):
sparse_mx[i] = to_tuple(sparse_mx[i])
else:
sparse_mx = to_tuple(sparse_mx)
return sparse_mx
# preprocess_features和normalize_adj的写法一样 都是用度矩阵来归一化
def preprocess_features(features):
"""Row-normalize feature matrix and convert to tuple representation"""
rowsum = np.array(features.sum(1)) # 对每一行求和 axis=1是按列 axis=0是行
""" example
a = np.array([[1, 2, 4], [4, 6, 3]])
np.sum(a, axis=1)
>>> [7, 13]
"""
r_inv = np.power(rowsum, -1).flatten()
r_inv[np.isinf(r_inv)] = 0.
r_mat_inv = sp.diags(r_inv) # 稀疏对角矩阵
# 这里的归一化类似于GCN里面的归一化 用矩阵的度来归一化 相当于就是除以这一行的和 妙！
features = r_mat_inv.dot(features)
return sparse_to_tuple(features)
def normalize_adj(adj):
"""Symmetrically normalize adjacency matrix.
对称归一化,对应论文中的公式."""
adj = sp.coo_matrix(adj)
rowsum = np.array(adj.sum(1))
d_inv_sqrt = np.power(rowsum, -0.5).flatten()
d_inv_sqrt[np.isinf(d_inv_sqrt)] = 0.
d_mat_inv_sqrt = sp.diags(d_inv_sqrt)
return adj.dot(d_mat_inv_sqrt).transpose().dot(d_mat_inv_sqrt).tocoo()
def preprocess_adj(adj):
"""Preprocessing of adjacency matrix for simple GCN model and conversion to tuple representation."""
adj_normalized = normalize_adj(adj + sp.eye(adj.shape[0]))
return sparse_to_tuple(adj_normalized)
def construct_feed_dict(features, support, labels, labels_mask, placeholders):
"""Construct feed dictionary."""
""" example
dic=dict()
dic={'Name':'Liugx','age':20}
>>> {'Name': 'Liugx', 'age': 20}
dic.update({'sex':'man'}) 添加指定字典到dic中
>>> {'Name': 'Liugx', 'age': 20, 'sex': 'man'}
"""
feed_dict = dict()
feed_dict.update({placeholders['labels']: labels})
feed_dict.update({placeholders['labels_mask']: labels_mask})
feed_dict.update({placeholders['features']: features})
feed_dict.update({placeholders['support'][i]: support[i]
for i in range(len(support))})
feed_dict.update({placeholders['num_features_nonzero']: features[1].shape})
return feed_dict
def chebyshev_polynomials(adj, k):
"""Calculate Chebyshev polynomials up to order k. Return a list of sparse matrices (tuple representation)."""
print("Calculating Chebyshev polynomials up to order {}...".format(k))
adj_normalized = normalize_adj(adj)
laplacian = sp.eye(adj.shape[0]) - adj_normalized
largest_eigval, _ = eigsh(laplacian, 1, which='LM')
scaled_laplacian = (
2. / largest_eigval[0]) * laplacian - sp.eye(adj.shape[0])
t_k = list()
t_k.append(sp.eye(adj.shape[0]))
t_k.append(scaled_laplacian)
def chebyshev_recurrence(t_k_minus_one, t_k_minus_two, scaled_lap):
s_lap = sp.csr_matrix(scaled_lap, copy=True)
return 2 * s_lap.dot(t_k_minus_one) - t_k_minus_two
for i in range(2, k+1):
t_k.append(chebyshev_recurrence(t_k[-1], t_k[-2], scaled_laplacian))
return sparse_to_tuple(t_k)
2. models.py
基类Model实现build()方法，该方法进行前向传播，具体的传播方法靠layer定义，每个模型具体的layers在子类的_build()方法中定义。
from gcn.layers import *
from gcn.metrics import *
flags = tf.app.flags
FLAGS = flags.FLAGS
class Model(object):
def __init__(self, **kwargs):
allowed_kwargs = {'name', 'logging'}
for kwarg in kwargs.keys():
assert kwarg in allowed_kwargs, 'Invalid keyword argument: ' + kwarg
name = kwargs.get('name')
if not name:
name = self.__class__.__name__.lower()
self.name = name
logging = kwargs.get('logging', False)
self.logging = logging
self.vars = {}
self.placeholders = {}
self.layers = []
self.activations = []
self.inputs = None
self.outputs = None
self.loss = 0
self.accuracy = 0
self.optimizer = None
self.opt_op = None
def _build(self):
raise NotImplementedError
def build(self):
""" Wrapper for _build() """
with tf.variable_scope(self.name):
self._build()
# Build sequential layer model
self.activations.append(self.inputs) # 初始化第一个元素为inputs features
for layer in self.layers:
hidden = layer(self.activations[-1]) # 这个hidden即为对应最后一个input的输出
self.activations.append(hidden)
self.outputs = self.activations[-1]
# Store model variables for easy access
variables = tf.get_collection(
tf.GraphKeys.GLOBAL_VARIABLES, scope=self.name)
self.vars = {var.name: var for var in variables}
# Build metrics
self._loss()
self._accuracy()
self.opt_op = self.optimizer.minimize(self.loss)
def predict(self):
pass # 不做任何事情 用做占位语句 给后面的子类用的
def _loss(self):
raise NotImplementedError # 子类一定要实现这个方法 否则就会报错
def _accuracy(self):
raise NotImplementedError # 子类一定要实现这个方法 否则就会报错
def save(self, sess=None):
if not sess:
raise AttributeError("TensorFlow session not provided.")
saver = tf.train.Saver(self.vars)
save_path = saver.save(sess, "tmp/%s.ckpt" % self.name)
print("Model saved in file: %s" % save_path)
def load(self, sess=None):
if not sess:
raise AttributeError("TensorFlow session not provided.")
saver = tf.train.Saver(self.vars)
save_path = "tmp/%s.ckpt" % self.name
saver.restore(sess, save_path)
print("Model restored from file: %s" % save_path)
class MLP(Model):
def __init__(self, placeholders, input_dim, **kwargs):
super(MLP, self).__init__(**kwargs)
self.inputs = placeholders['features']
self.input_dim = input_dim
# self.input_dim = self.inputs.get_shape().as_list()[1] # To be supported in future Tensorflow versions
self.output_dim = placeholders['labels'].get_shape().as_list()[1]
self.placeholders = placeholders
self.optimizer = tf.train.AdamOptimizer(
learning_rate=FLAGS.learning_rate)
self.build()
def _loss(self):
# Weight decay loss
for var in self.layers[0].vars.values():
self.loss += FLAGS.weight_decay * tf.nn.l2_loss(var)
# Cross entropy error
self.loss += masked_softmax_cross_entropy(self.outputs, self.placeholders['labels'],
self.placeholders['labels_mask'])
def _accuracy(self):
self.accuracy = masked_accuracy(self.outputs, self.placeholders['labels'],
self.placeholders['labels_mask'])
def _build(self):
self.layers.append(Dense(input_dim=self.input_dim,
output_dim=FLAGS.hidden1,
placeholders=self.placeholders,
act=tf.nn.relu,
dropout=True,
sparse_inputs=True,
logging=self.logging))
self.layers.append(Dense(input_dim=FLAGS.hidden1,
output_dim=self.output_dim,
placeholders=self.placeholders,
act=lambda x: x,
dropout=True,
logging=self.logging))
def predict(self):
return tf.nn.softmax(self.outputs)
class GCN(Model):
def __init__(self, placeholders, input_dim, **kwargs):
super(GCN, self).__init__(**kwargs)
self.inputs = placeholders['features']
self.input_dim = input_dim
# self.input_dim = self.inputs.get_shape().as_list()[1] # To be supported in future Tensorflow versions
self.output_dim = placeholders['labels'].get_shape().as_list()[1]
self.placeholders = placeholders
self.optimizer = tf.train.AdamOptimizer(
learning_rate=FLAGS.learning_rate)
self.build()
def _loss(self):
# Weight decay loss
# l2损失加到总损失里面
for var in self.layers[0]文章来源互联网，尊重作者原创，如有侵权，请联系管理员删除。