last_model = os.path.join(save_dir, f'saved_model_epoch_{epochs}.pt')
if os.path.exists(last_model):
model.load_state_dict(torch.load(last_model, map_location=device))
else:
for epoch in range(epochs):
train(
epoch,
model,
loader,
optimizer,
scheduler,
writer=writer,
verbose=verbose
)
torch.save(
model.state_dict(),
os.path.join(save_dir, f'saved_model_epoch_{epoch+1}.pt')
)
torch.save(
model.state_dict(),
os.path.join(save_dir, 'saved_model_epoch_last.pt')
)
logger.info('Done pretraining!')
# Downstream task
dataset = CSVDataset(DOWNSTREAM_TRAIN_FILE, LANG_FILE)
train_latent_data = []
train_target = []
model.encoder.update_batch_size(2)
for seqs, y in dataset:
encoder_seq, _, _ = packed_sequential_data_preparation(
z, _, _ = model(data.x, data.edge_index)
acc = model.test(z[data.train_mask], data.y[data.train_mask],
z[data.test_mask], data.y[data.test_mask], max_iter=150)
return acc
test_acc = []
best_acc = 0
for _ in range(5):
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = DeepGraphInfomax(
hidden_channels=512, encoder=Encoder(dataset.num_features, 512),
summary=lambda z, *args, **kwargs: torch.sigmoid(z.mean(dim=0)),
corruption=corruption).to(device)
data = dataset[0].to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
for epoch in range(1, 301):
loss = train()
# print('Epoch: {:03d}, Loss: {:.4f}'.format(epoch, loss))
acc = test()
test_acc.append(acc)
print('Accuracy: {:.4f}'.format(acc))
if best_acc < acc:
best_acc = acc
if not os.path.isdir('../checkpoint'):
os.makedirs('../checkpoint')
torch.save(model.state_dict(), os.path.join('../checkpoint', '{}.pth'.format(args.dataset)))
test_acc = np.array(test_acc)
print("Node classification for {}, acc mean {:.4f}, acc std {:.4f}".format(args.dataset,
np.mean(test_acc), np.std(test_acc, ddof=1)))
