def _inference(self, x, dropout):
# Graph convolutional layers.
x = tf.expand_dims(x, 2) # N x M x F=1
for i in range(len(self.p)):
with tf.variable_scope('conv{}'.format(i+1)):
with tf.name_scope('filter'):
## filter表示切比雪夫的卷积过程
# self.L[i]表示当前level邻接矩阵的拉普拉斯矩阵
# self.F[i] 当前level卷积操作的输出维度
# self.K[i] 当前level卷积切比雪夫展开项数
x = self.filter(x, self.L[i], self.F[i], self.K[i])
with tf.name_scope('bias_relu'):
x = self.brelu(x)
with tf.name_scope('pooling'):
x = self.pool(x, self.p[i])
# Fully connected hidden layers.
N, M, F = x.get_shape()
x = tf.reshape(x, [int(N), int(M*F)]) # N x M
for i,M in enumerate(self.M[:-1]):
with tf.variable_scope('fc{}'.format(i+1)):
x = self.fc(x, M)
x = tf.nn.dropout(x, dropout)
# Logits linear layer, i.e. softmax without normalization.
with tf.variable_scope('logits'):
x = self.fc(x, self.M[-1], relu=False)
return x
切比雪夫过程
def chebyshev5(self, x, L, Fout, K):
N, M, Fin = x.get_shape()
N, M, Fin = int(N), int(M), int(Fin)
# Rescale Laplacian and store as a TF sparse tensor. Copy to not modify the shared L.
L = scipy.sparse.csr_matrix(L)
L = graph.rescale_L(L, lmax=2)
L = L.tocoo()
indices = np.column_stack((L.row, L.col))
L = tf.SparseTensor(indices, L.data, L.shape)
L = tf.sparse_reorder(L)
# Transform to Chebyshev basis
x0 = tf.transpose(x, perm=[1, 2, 0]) # M x Fin x N
x0 = tf.reshape(x0, [M, Fin*N]) # M x Fin*N
x = tf.expand_dims(x0, 0) # 1 x M x Fin*N
def concat(x, x_):
x_ = tf.expand_dims(x_, 0) # 1 x M x Fin*N
return tf.concat([x, x_], axis=0) # K x M x Fin*N
if K > 1:
x1 = tf.sparse_tensor_dense_matmul(L, x0)
x = concat(x, x1)
for k in range(2, K):
x2 = 2 * tf.sparse_tensor_dense_matmul(L, x1) - x0 # M x Fin*N
x = concat(x, x2)
x0, x1 = x1, x2
x = tf.reshape(x, [K, M, Fin, N]) # K x M x Fin x N
x = tf.transpose(x, perm=[3,1,2,0]) # N x M x Fin x K
x = tf.reshape(x, [N*M, Fin*K]) # N*M x Fin*K
# Filter: Fin*Fout filters of order K, i.e. one filterbank per feature pair.
W = self._weight_variable([Fin*K, Fout], regularization=False)
x = tf.matmul(x, W) # N*M x Fout
return tf.reshape(x, [N, M, Fout]) # N x M x Fout
pool过程:
def mpool1(self, x, p):
"""Max pooling of size p. Should be a power of 2."""
if p > 1:
x = tf.expand_dims(x, 3) # N x M x F x 1
x = tf.nn.max_pool(x, ksize=[1,p,1,1], strides=[1,p,1,1], padding='SAME')
#tf.maximum
return tf.squeeze(x, [3]) # N x M/p x F
else:
return x