forked from PetarV-/GAT
-
Notifications
You must be signed in to change notification settings - Fork 0
/
execute_cora.py
174 lines (144 loc) · 6.54 KB
/
execute_cora.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
import time
import numpy as np
import tensorflow as tf
from models import GAT
from utils import process
checkpt_file = 'pre_trained/cora/mod_cora.ckpt'
dataset = 'cora'
# training params
batch_size = 1
nb_epochs = 100000
patience = 100
lr = 0.005 # learning rate
l2_coef = 0.0005 # weight decay
hid_units = [8] # numbers of hidden units per each attention head in each layer
n_heads = [8, 1] # additional entry for the output layer
residual = False
nonlinearity = tf.nn.elu
model = GAT
print('Dataset: ' + dataset)
print('----- Opt. hyperparams -----')
print('lr: ' + str(lr))
print('l2_coef: ' + str(l2_coef))
print('----- Archi. hyperparams -----')
print('nb. layers: ' + str(len(hid_units)))
print('nb. units per layer: ' + str(hid_units))
print('nb. attention heads: ' + str(n_heads))
print('residual: ' + str(residual))
print('nonlinearity: ' + str(nonlinearity))
print('model: ' + str(model))
adj, features, y_train, y_val, y_test, train_mask, val_mask, test_mask = process.load_data(dataset)
features, spars = process.preprocess_features(features)
nb_nodes = features.shape[0]
ft_size = features.shape[1]
nb_classes = y_train.shape[1]
adj = adj.todense()
features = features[np.newaxis]
adj = adj[np.newaxis]
y_train = y_train[np.newaxis]
y_val = y_val[np.newaxis]
y_test = y_test[np.newaxis]
train_mask = train_mask[np.newaxis]
val_mask = val_mask[np.newaxis]
test_mask = test_mask[np.newaxis]
biases = process.adj_to_bias(adj, [nb_nodes], nhood=1)
with tf.Graph().as_default():
with tf.name_scope('input'):
ftr_in = tf.placeholder(dtype=tf.float32, shape=(batch_size, nb_nodes, ft_size))
bias_in = tf.placeholder(dtype=tf.float32, shape=(batch_size, nb_nodes, nb_nodes))
lbl_in = tf.placeholder(dtype=tf.int32, shape=(batch_size, nb_nodes, nb_classes))
msk_in = tf.placeholder(dtype=tf.int32, shape=(batch_size, nb_nodes))
attn_drop = tf.placeholder(dtype=tf.float32, shape=())
ffd_drop = tf.placeholder(dtype=tf.float32, shape=())
is_train = tf.placeholder(dtype=tf.bool, shape=())
logits = model.inference(ftr_in, nb_classes, nb_nodes, is_train,
attn_drop, ffd_drop,
bias_mat=bias_in,
hid_units=hid_units, n_heads=n_heads,
residual=residual, activation=nonlinearity)
log_resh = tf.reshape(logits, [-1, nb_classes])
lab_resh = tf.reshape(lbl_in, [-1, nb_classes])
msk_resh = tf.reshape(msk_in, [-1])
loss = model.masked_softmax_cross_entropy(log_resh, lab_resh, msk_resh)
accuracy = model.masked_accuracy(log_resh, lab_resh, msk_resh)
train_op = model.training(loss, lr, l2_coef)
saver = tf.train.Saver()
init_op = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer())
vlss_mn = np.inf
vacc_mx = 0.0
curr_step = 0
with tf.Session() as sess:
sess.run(init_op)
train_loss_avg = 0
train_acc_avg = 0
val_loss_avg = 0
val_acc_avg = 0
for epoch in range(nb_epochs):
tr_step = 0
tr_size = features.shape[0]
while tr_step * batch_size < tr_size:
_, loss_value_tr, acc_tr = sess.run([train_op, loss, accuracy],
feed_dict={
ftr_in: features[tr_step*batch_size:(tr_step+1)*batch_size],
bias_in: biases[tr_step*batch_size:(tr_step+1)*batch_size],
lbl_in: y_train[tr_step*batch_size:(tr_step+1)*batch_size],
msk_in: train_mask[tr_step*batch_size:(tr_step+1)*batch_size],
is_train: True,
attn_drop: 0.6, ffd_drop: 0.6})
train_loss_avg += loss_value_tr
train_acc_avg += acc_tr
tr_step += 1
vl_step = 0
vl_size = features.shape[0]
while vl_step * batch_size < vl_size:
loss_value_vl, acc_vl = sess.run([loss, accuracy],
feed_dict={
ftr_in: features[vl_step*batch_size:(vl_step+1)*batch_size],
bias_in: biases[vl_step*batch_size:(vl_step+1)*batch_size],
lbl_in: y_val[vl_step*batch_size:(vl_step+1)*batch_size],
msk_in: val_mask[vl_step*batch_size:(vl_step+1)*batch_size],
is_train: False,
attn_drop: 0.0, ffd_drop: 0.0})
val_loss_avg += loss_value_vl
val_acc_avg += acc_vl
vl_step += 1
print('Training: loss = %.5f, acc = %.5f | Val: loss = %.5f, acc = %.5f' %
(train_loss_avg/tr_step, train_acc_avg/tr_step,
val_loss_avg/vl_step, val_acc_avg/vl_step))
if val_acc_avg/vl_step >= vacc_mx or val_loss_avg/vl_step <= vlss_mn:
if val_acc_avg/vl_step >= vacc_mx and val_loss_avg/vl_step <= vlss_mn:
vacc_early_model = val_acc_avg/vl_step
vlss_early_model = val_loss_avg/vl_step
saver.save(sess, checkpt_file)
vacc_mx = np.max((val_acc_avg/vl_step, vacc_mx))
vlss_mn = np.min((val_loss_avg/vl_step, vlss_mn))
curr_step = 0
else:
curr_step += 1
if curr_step == patience:
print('Early stop! Min loss: ', vlss_mn, ', Max accuracy: ', vacc_mx)
print('Early stop model validation loss: ', vlss_early_model, ', accuracy: ', vacc_early_model)
break
train_loss_avg = 0
train_acc_avg = 0
val_loss_avg = 0
val_acc_avg = 0
saver.restore(sess, checkpt_file)
ts_size = features.shape[0]
ts_step = 0
ts_loss = 0.0
ts_acc = 0.0
while ts_step * batch_size < ts_size:
loss_value_ts, acc_ts = sess.run([loss, accuracy],
feed_dict={
ftr_in: features[ts_step*batch_size:(ts_step+1)*batch_size],
bias_in: biases[ts_step*batch_size:(ts_step+1)*batch_size],
lbl_in: y_test[ts_step*batch_size:(ts_step+1)*batch_size],
msk_in: test_mask[ts_step*batch_size:(ts_step+1)*batch_size],
is_train: False,
attn_drop: 0.0, ffd_drop: 0.0})
ts_loss += loss_value_ts
ts_acc += acc_ts
ts_step += 1
print('Test loss:', ts_loss/ts_step, '; Test accuracy:', ts_acc/ts_step)
sess.close()