# scheduler.step()
hidden_emb = mu.cpu().data.numpy()
# roc_curr, ap_curr = get_roc_score(hidden_emb, adj_bs)
# print('cur_loss_list: ')
# print(cur_loss_list)
# print(len(cur_loss_list))
# one epoch one mean loss
# total training samples num: len(adj_feat_list)
# sum up all the batch losses and average them to get current epoch mean loss
mean_loss = sum(cur_loss_list) / len(adj_feat_list)
print('Epoch '+ str(epoch)+' mean_loss: ')
print(mean_loss)
loss_record.append(mean_loss)
print('loss record by epoch: ')
print(loss_record)
fout = open(model_out+'loss_by_epochs.txt', 'w')
fout.writelines(["%s\n" % item for item in loss_record])
# draw_loss_curve(loss_record)
end_time = time.time()
print('time elapse is : ' + str(end_time-start_time))
model_file = 'model_'+str(batch_size)+'_'+str(epochs)+'_'+str(lr)+'.pkl'
print(model.cpu())
# of = open(model_file, 'w')
model_cpu = model.cpu()
torch.save(model_cpu.state_dict(), model_out + model_file)
### load model dict
# model = GCNModelVAE(batch_size, args.hidden1, args.hidden2, args.dropout)
# model.load_state_dict(torch.load(model_file))
# print(model)
mu=mu,
logvar=logvar,
n_nodes=n_nodes,
norm=norm,
pos_weight=pos_weight)
cpu_loss = loss.cpu()
cur_loss_list.append(cpu_loss.data.numpy().tolist())
loss.backward()
# cur_loss = loss.item()
optimizer.step()
hidden_emb = mu.cpu().data.numpy()
print(cur_loss_list)
print(len(cur_loss_list))
# one epoch one mean loss
# total training samples num: len(adj_feat_list)
# sum up all the batch losses and average them to get current epoch mean loss
mean_loss = sum(cur_loss_list) / len(adj_feat_list)
print('epoch ' + str(epoch) + 'the mean loss:', end=' ')
print(mean_loss)
loss_record.append(mean_loss)
fout = open('./loss_by_epochs.txt', 'w')
fout.writelines(["%s\n" % item for item in loss_record])
# draw_loss_curve(loss_record)
model_file = 'model_' + str(batch_size) + '_' + str(epochs) + '_' + str(
lr) + '.pkl'
print(model.cpu())
of = open(model_file, 'wb')
pickle.dump(model.cpu(), of)
def gae_for(args):
print("Using {} dataset".format(args.dataset_str))
#得到原始邻接矩阵和特征
adj, features = load_data(args.dataset_str)
n_nodes, feat_dim = features.shape
# Store original adjacency matrix (without diagonal entries) for later
adj_orig = adj
adj_orig = adj_orig - sp.dia_matrix(
(adj_orig.diagonal()[np.newaxis, :], [0]), shape=adj_orig.shape)
adj_orig.eliminate_zeros()
print(adj.shape)
adj_train, train_edges, val_edges, val_edges_false, test_edges, test_edges_false = mask_test_edges(
adj)
adj = adj_train
print('adj.shape:{}'.format(adj.shape))
print("np.sum(adj):{}".format(np.sum(adj)))
print("len(train_edges):{}".format(len(train_edges)))
print("len(test_edges):{}".format(len(test_edges)))
print("len(val_edges):{}".format(len(val_edges)))
# Some preprocessing
adj_norm = preprocess_graph(adj)
adj_label = adj_train + sp.eye(adj_train.shape[0])
# adj_label = sparse_to_tuple(adj_label)
adj_label = torch.FloatTensor(adj_label.toarray())
pos_weight = float(adj.shape[0] * adj.shape[0] - adj.sum()) / adj.sum()
# pos_weight=torch.from_numpy(pos_weight)
norm = adj.shape[0] * adj.shape[0] / float(
(adj.shape[0] * adj.shape[0] - adj.sum()) * 2)
model = GCNModelVAE(feat_dim, args.hidden1, args.hidden2, args.dropout)
if cuda:
model = model.cuda()
features = features.cuda()
adj_norm = adj_norm.cuda()
optimizer = optim.Adam(model.parameters(), lr=args.lr)
hidden_emb = None
for epoch in range(args.epochs):
t = time.time()
model.train()
optimizer.zero_grad()
#每次将整个图放入到模型中训练
recovered, mu, logvar = model(features, adj_norm)
loss = loss_function(preds=recovered,
labels=adj_label,
mu=mu,
logvar=logvar,
n_nodes=n_nodes,
norm=norm)
loss.backward()
cur_loss = loss.item()
optimizer.step()
hidden_emb = mu.cpu().data.numpy()
roc_curr, ap_curr = get_roc_score(hidden_emb, adj_orig, val_edges,
val_edges_false)
print("Epoch:", '%04d' % (epoch + 1), "train_loss=",
"{:.5f}".format(cur_loss), "val_ap=", "{:.5f}".format(ap_curr),
"time=", "{:.5f}".format(time.time() - t))
print("Optimization Finished!")
roc_score, ap_score = get_roc_score(hidden_emb, adj_orig, test_edges,
test_edges_false)
print('Test ROC score: ' + str(roc_score))
print('Test AP score: ' + str(ap_score))
model = model.cpu()
