Created by: snowsteper

如题 训练日志如下： Test in epoch 0, Loss: 4.757947, Acc: 0.354800 Test in epoch 0, Loss: 4.865430, Acc: 0.354230 Test in epoch 0, Loss: 4.937966, Acc: 0.356729 Test in epoch 1, Loss: 5.124760, Acc: 0.356336 Test in epoch 1, Loss: 5.165730, Acc: 0.355902 Test in epoch 1, Loss: 5.279254, Acc: 0.354999 Test in epoch 2, Loss: 5.431847, Acc: 0.354028 Test in epoch 2, Loss: 5.450323, Acc: 0.352916 Test in epoch 2, Loss: 5.486628, Acc: 0.355298 Test in epoch 3, Loss: 5.596898, Acc: 0.354946 Test in epoch 3, Loss: 5.595257, Acc: 0.352510 Test in epoch 3, Loss: 5.728043, Acc: 0.356146 Test in epoch 4, Loss: 5.937518, Acc: 0.347627 Test in epoch 4, Loss: 5.786941, Acc: 0.353117 Test in epoch 4, Loss: 5.885833, Acc: 0.354856 Test in epoch 5, Loss: 5.934639, Acc: 0.355649 Test in epoch 5, Loss: 5.919194, Acc: 0.353639 Test in epoch 5, Loss: 6.017453, Acc: 0.355212 Test in epoch 6, Loss: 6.062719, Acc: 0.355775 Test in epoch 6, Loss: 6.049249, Acc: 0.352780 Test in epoch 6, Loss: 6.193391, Acc: 0.354625 Test in epoch 7, Loss: 6.236372, Acc: 0.355126 Test in epoch 7, Loss: 6.229053, Acc: 0.351142 Test in epoch 7, Loss: 6.237000, Acc: 0.356059 Test in epoch 8, Loss: 6.331445, Acc: 0.354839 Test in epoch 8, Loss: 6.329272, Acc: 0.351808 Test in epoch 8, Loss: 6.363647, Acc: 0.355070 Test in epoch 9, Loss: 6.449283, Acc: 0.354044 Test in epoch 9, Loss: 6.400001, Acc: 0.351498 Test in epoch 9, Loss: 6.482876, Acc: 0.354735

模型用cnn + softmax + cross_entropy loss 训练程序如下： ``` # Network class_num = len(label_dict) + 1 char_dict_num = len(char_dict) + 1 word_dict_num = len(word_dict) + 1 logger.info("char dict dim:\t%s, word dict dim:\t%s, class dim:\t%s", char_dict_num, word_dict_num, class_num) pred, loss, label = network(char_dict_dim=char_dict_num, word_dict_dim=word_dict_num, class_dim=class_num, is_indep_char=is_indep_char) pred.persistable = True loss.persistable = True label.persistable = True

# Program
main_program = fluid.default_main_program()
start_program = fluid.default_startup_program()
test_program = main_program.clone(for_test=True)

# Optimizer
optimizer = fluid.optimizer.AdamOptimizer(
    learning_rate=0.01,
    beta1=0.9,
    beta2=0.999,
    epsilon=1e-8)
optimizer.minimize(loss)
fluid.memory_optimize(main_program)

# Executor
exe = fluid.Executor(place)
exe.run(start_program)

# setting for cpu training
# exec_strategy = fluid.ExecutionStrategy()
# exec_strategy.num_threads = 1 # cpu thread num

parallel_executor = fluid.ParallelExecutor(
    use_cuda=use_gpu, loss_name=loss.name,
    main_program=main_program)

# test_exe = fluid.Executor(place)
test_executor = fluid.ParallelExecutor(
    use_cuda=use_gpu,
    share_vars_from=parallel_executor,
    main_program=test_program)

# Feeder
feed_order = ["char_data", "basic_data", "phrase_data", "label"]
feed_var_list = [ main_program.global_block().var(var_name) for var_name in feed_order ]
feeder = fluid.DataFeeder(place=place, feed_list=feed_var_list)

def run_test(num_epoch):
    test_batch = paddle.batch(test_data_reader, 256, drop_last=False)
    # test_batch = paddle.batch(test_data_reader, batch_num, drop_last=False)
    comp = fluid.metrics.CompositeMetric()
    acc = Accuracy_TopN(topN=1)
    comp.add_metric(acc)
    comp.reset()
    tot_loss = .0
    tot_iter = 0
    for index, data in enumerate(test_batch()):
        preds, batch_avg_loss, labels = test_executor.run(fetch_list=[pred.name, loss.name, label.name], feed=feeder.feed(data))
        # preds, batch_avg_loss, labels = test_exe.run(program=test_program, fetch_list=[pred, loss, label], feed=feeder.feed(data))
        comp.update(preds=preds, labels=labels)
        tot_loss += np.mean(batch_avg_loss)
        tot_iter = index + 1
    np_acc = comp.eval()
    test_avg_loss = tot_loss / tot_iter
    logger.info("Test in epoch %3d, Loss:\t%.6f, Acc:\t%.6f", num_epoch, test_avg_loss, np_acc[0])

# Train Model
logger.info("Training...total pass:\t%s", pass_num)
for epoch in xrange(pass_num):
    for index, data in enumerate(batch_data()):
        avg_loss = parallel_executor.run(
            [loss.name], feed=feeder.feed(data)
        )
        # avg_loss = exe.run(
        #     program=main_program,
        #     fetch_list=[loss.name], feed=feeder.feed(data)
        # )
        if index % 1000 == 0:
            logger.info("Train epoch %3d, batch %6d, loss %f", epoch, index, np.mean(avg_loss[0]))
        if index % 12000 == 0 and index > 0:
            run_test(epoch)

    run_test(epoch)

    feeded_var_names = ["char_data", "basic_data", "phrase_data"]
    target_vars = [pred]
    model_name = model_name_prefix + "_pass_%04d" % epoch
    model_path = os.path.join(model_dir, model_name)
    logger.info("Saving model, path:\t%s", model_path)
    fluid.io.save_inference_model(dirname=model_path,
                                  model_filename=model_name,
                                  feeded_var_names=feeded_var_names,
                                  target_vars=target_vars,
                                  executor=exe,
                                  main_program=test_program)