def norm_adj(adj_to_norm):
return normalize_nonsym_adj(adj_to_norm)
},
}
if not os.path.exists(SUMMARIESDIR):
os.makedirs(SUMMARIESDIR)
train_support = get_degree_supports(adj_train, DEGREE, adj_self_con=ADJ_SELF_CONNECTIONS)
val_support = get_degree_supports(adj_val, DEGREE, adj_self_con=ADJ_SELF_CONNECTIONS)
test_support = get_degree_supports(adj_test, DEGREE, adj_self_con=ADJ_SELF_CONNECTIONS)
if DATASET != 'amazon':
q_support = get_degree_supports(adj_q, DEGREE, adj_self_con=ADJ_SELF_CONNECTIONS)
if DATASET == 'polyvore':
res_q_support = get_degree_supports(res_adj_q, DEGREE, adj_self_con=ADJ_SELF_CONNECTIONS)
for i in range(1, len(train_support)):
train_support[i] = normalize_nonsym_adj(train_support[i])
val_support[i] = normalize_nonsym_adj(val_support[i])
test_support[i] = normalize_nonsym_adj(test_support[i])
if DATASET != 'amazon':
q_support[i] = normalize_nonsym_adj(q_support[i])
if DATASET == 'polyvore':
res_q_support[i] = normalize_nonsym_adj(res_q_support[i])
num_support = len(train_support)
placeholders = {
'row_indices': tf.placeholder(tf.int32, shape=(None,)),
'col_indices': tf.placeholder(tf.int32, shape=(None,)),
'dropout': tf.placeholder_with_default(0., shape=()),
'weight_decay': tf.placeholder_with_default(0., shape=()),
'is_train': tf.placeholder_with_default(True, shape=()),
'support': [tf.sparse_placeholder(tf.float32, shape=(None, None)) for sup in range(num_support)],
