if __name__ == "__main__":
config = Config()
train_file = "data_labeled"
if len(sys.argv) > 2:
train_file = sys.argv[1]
dataset = Dataset(config)
lines = dataset.read_lines(train_file)
triples = dataset.get_data(lines)
sentence_batches, action_batches = dataset.get_action_batches(
triples, config.batches_num)
model = Transformer(config, len(dataset.vocab))
if torch.cuda.is_available():
model.cuda()
model.train()
optimizer = optim.Adam(model.parameters(), lr=config.lr)
# 多分类交叉熵损失函数
NLLLoss = nn.NLLLoss()
# 模型加载优化函数和损失函数
model.add_optimizer(optimizer)
model.add_loss_op(NLLLoss)
train_losses = []
for i in range(config.max_epochs):
print("Epoch: {}".format(i))
train_loss = model.run_epoch(sentence_batches, action_batches, i)
train_losses.append(train_loss)
train_acc = evaluate_model(model, sentence_batches, action_batches)
print("Final Training Dataset Accuracy: {.4f}".format(train_acc))
repeat=False,
shuffle=True)
time_end = time.time()
print(time_end - time_start, 's complete the processed')
print("vocab size", len(TEXT.vocab))
model = Transformer(Config, len(TEXT.vocab))
print(model)
model.cuda()
model.train()
model.load_state_dict(torch.load('epoch_0_0.4479.pt'))
optimizer = optim.Adam(model.parameters(), lr=Config.lr)
loss = nn.CrossEntropyLoss()
model.add_optimizer(optimizer)
model.add_loss_op(loss)
train_losses = []
val_accuracies = []
# val_accuracy, F1_score = evaluate_model(model, dataset.val_iterator)
# print("\tVal Accuracy: {:.4f}".format(val_accuracy))
for i in range(Config.max_epochs):
print("\nEpoch: {}".format(i))
train_loss, val_accuracy = model.run_epoch(train_iter, valid_iter, i)
train_losses.append(train_loss)
val_accuracies.append(val_accuracy)
train_acc, train_F1 = evaluate_model(model, train_iter)
val_acc, val_F1 = evaluate_model(model, valid_iter)
print('Final Training Accuracy: {:.4f}'.format(train_acc))
