Python model.get_model() Examples

def train(weights_path, epochs, batch_size, initial_epoch,
          kl_start_epoch, kl_alpha_increase_per_epoch):
    """Trains a model."""
    print ('loading data...')
    # Loads or creates training data.
    input_shape, train, valid, train_targets, valid_targets = get_train_data()
    print ('getting model...')
    # Loads or creates model.
    model, checkpoint_path, kl_alpha = get_model(input_shape,
                                        scale_factor=len(train)/batch_size,
                                        weights_path=weights_path)

    # Sets callbacks.
    checkpointer = ModelCheckpoint(checkpoint_path, verbose=1,
                                   save_weights_only=True, save_best_only=True)

    scheduler = LearningRateScheduler(schedule)
    annealer = Callback() if kl_alpha is None else AnnealingCallback(kl_alpha, kl_start_epoch, kl_alpha_increase_per_epoch)

    print ('fitting model...')
    # Trains model.
    model.fit(train, train_targets, batch_size, epochs,
              initial_epoch=initial_epoch,
              callbacks=[checkpointer, scheduler, annealer],
              validation_data=(valid, valid_targets)) 

def test(weights_path, batch_size):
    """Tests a model."""

    try:
        # Loads or creates test data.
        input_shape, test, test_targets, \
            test_coords, orig_test_shape = get_test_data()
    except FileNotFoundError as e:
        print(e)
        print("Could not find test files in data_dir. "
              "Did you specify the correct orig_test_data_dir?")
        return

    # Loads or creates model.
    model, checkpoint_path, _ = get_model(input_shape,
                                       scale_factor=len(test)/batch_size,
                                       weights_path=weights_path)

    # Predicts on test data and saves results.
    predict(model, test, test_targets, test_coords,
            orig_test_shape, input_shape)
    plots() 

def __init__(self, model_folder, checkpoint_file):
        sys.path.append(model_folder)

        from model import get_model
        from dataset import load_data

        self.dataset = load_data('validation')

        self.sess = tf.InteractiveSession()
        self.model = get_model('policy')

        saver = tf.train.Saver()
        saver.restore(self.sess, checkpoint_file) 

def get_coin_decisions(df, backtest=True):

    model = get_model(df)

    df_list, backtests = get_dataset_df(df, backtest)

    total_decisions_df = pd.DataFrame()
    total_prices_df = pd.DataFrame()
    for coin, coin_df in backtests.items():
        X, y = get_dataset(coin_df)
        final_df = get_backtest_action(X, y, model)
        for col in ['date', 'price']:
            final_df[col] = coin_df[col]

        coin_decision_df = final_df[['date', 'final_decision']]
        coin_prices_df = final_df[['date', 'price']]
        coin_decision_df.columns = ['date', coin]
        coin_prices_df.columns = ['date', coin]

        if total_decisions_df.empty:
            total_decisions_df = coin_decision_df
        else:
            total_decisions_df = pd.merge(total_decisions_df, coin_decision_df)
        if total_prices_df.empty:
            total_prices_df = coin_prices_df
        else:
            total_prices_df = pd.merge(total_prices_df, coin_prices_df)

    df_list = []
    for df in [total_decisions_df, total_prices_df]:
        df.set_index('date', inplace=True)
        df_list.append(df.T.reset_index())

    return df_list 

def main():
    args = get_args()
    image_dir = args.image_dir
    weight_file = args.weight_file
    val_noise_model = get_noise_model(args.test_noise_model)
    model = get_model(args.model)
    model.load_weights(weight_file)

    if args.output_dir:
        output_dir = Path(args.output_dir)
        output_dir.mkdir(parents=True, exist_ok=True)

    image_paths = list(Path(image_dir).glob("*.*"))

    for image_path in image_paths:
        image = cv2.imread(str(image_path))
        h, w, _ = image.shape
        image = image[:(h // 16) * 16, :(w // 16) * 16]  # for stride (maximum 16)
        h, w, _ = image.shape

        out_image = np.zeros((h, w * 3, 3), dtype=np.uint8)
        noise_image = val_noise_model(image)
        pred = model.predict(np.expand_dims(noise_image, 0))
        denoised_image = get_image(pred[0])
        out_image[:, :w] = image
        out_image[:, w:w * 2] = noise_image
        out_image[:, w * 2:] = denoised_image

        if args.output_dir:
            cv2.imwrite(str(output_dir.joinpath(image_path.name))[:-4] + ".png", out_image)
        else:
            cv2.imshow("result", out_image)
            key = cv2.waitKey(-1)
            # "q": quit
            if key == 113:
                return 0 

def merge_models(args, model, ingr_vocab_size, instrs_vocab_size):
    load_args = pickle.load(open(os.path.join(args.save_dir, args.project_name,
                                              args.transfer_from, 'checkpoints/args.pkl'), 'rb'))

    model_ingrs = get_model(load_args, ingr_vocab_size, instrs_vocab_size)
    model_path = os.path.join(args.save_dir, args.project_name, args.transfer_from, 'checkpoints', 'modelbest.ckpt')

    # Load the trained model parameters
    model_ingrs.load_state_dict(torch.load(model_path, map_location=map_loc))
    model.ingredient_decoder = model_ingrs.ingredient_decoder
    args.transf_layers_ingrs = load_args.transf_layers_ingrs
    args.n_att_ingrs = load_args.n_att_ingrs

    return args, model 

def main():
    args = get_args()
    image_dir = args.image_dir
    weight_file = args.weight_file
    val_noise_model = get_noise_model(args.test_noise_model)
    model = get_model(args.model)
    model.load_weights(weight_file)

    if args.output_dir:
        output_dir = Path(args.output_dir)
        output_dir.mkdir(parents=True, exist_ok=True)

    image_paths = list(Path(image_dir).glob("*.*"))

    for image_path in image_paths:
        image = cv2.imread(str(image_path))
        h, w, _ = image.shape
        #image = image[:(h // 16) * 16, :(w // 16) * 16]  # for stride (maximum 16)
        h, w, _ = image.shape

        out_image = np.zeros((h, w * 1, 3), dtype=np.uint8)
        noise_image = val_noise_model(image)
        pred = model.predict(np.expand_dims(noise_image, 0))
        denoised_image = get_image(pred[0])
        out_image[:, :w] = denoised_image

        if args.output_dir:
            cv2.imwrite(str(output_dir.joinpath(image_path.name))[:-4] + ".png", out_image)
        else:
            cv2.imshow("result", out_image)
            key = cv2.waitKey(-1)
            # "q": quit
            if key == 113:
                return 0 

def export_input_graph(model_folder):
    sys.path.append(model_folder)
    from model import get_model

    with tf.Session() as sess:
        model = get_model('policy')

        saver = tf.train.Saver()

        tf.train.write_graph(sess.graph_def, model_folder, 'input_graph.pb', as_text=True) 

def train(args):

    device = args.device
    load_path = args.load_path
    # load data
    train_data = load_data('train')
    val_data = load_data('validation')

    # load model
    with tf.device('/gpu:%d' % device):
        model = get_model('train')

    # trainer init
    optimizer = Config.optimizer
    train_step = optimizer.minimize(model.loss)

    # init session and server
    sess = tf.InteractiveSession()
    saver = tf.train.Saver()
    if load_path==None:
        sess.run(tf.initialize_all_variables())
    else:
        saver.restore(sess, load_path)
        print("Model restored from %s" % load_path)

    # accuracy
    pred = tf.reshape(model.pred, [-1, 9*10*16])
    label = tf.reshape(model.label, [-1, 9*10*16])
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(label,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    logging.basicConfig(filename='log.txt', level=logging.DEBUG)
    # train steps
    for i in range(Config.n_epoch):

        # training step
        batch_data, batch_label = train_data.next_batch(Config.minibatch_size)

        input_dict = {model.label:batch_label}
        for var, data in zip(model.inputs, batch_data):
            input_dict[var]=data

        #from IPython import embed;embed()
        sess.run(train_step, feed_dict=input_dict)

        # evalue step
        if (i+1)%Config.evalue_point == 0:
            batch_data, batch_label = val_data.next_batch(Config.minibatch_size)
            val_dict = {model.label:batch_label}
            for var, data in zip(model.inputs, batch_data):
                val_dict[var]=data
            score = accuracy.eval(feed_dict=val_dict)
            print("epoch %d, accuracy is %.2f" % (i,score))
            logging.info("epoch %d, accuracy is %.2f" % (i,score))

        # save step
        if (i+1)%Config.check_point == 0:
            save_path = saver.save(sess, "%s/epoch-%d" %(Config.save_path, i))
            print("Model saved in file: %s" % save_path)
            logging.info("Model saved in file: %s" % save_path) 

def train(args):

    device = args.device
    load_path = args.load_path
    # load data
    train_data = load_data('train')
    val_data = load_data('validation')

    # load model
    with tf.device('/gpu:%d' % device):
        model = get_model('train')

    # trainer init
    optimizer = Config.optimizer
    train_step = optimizer.minimize(model.loss)

    # init session and server
    sess = tf.InteractiveSession()
    saver = tf.train.Saver()
    if load_path==None:
        sess.run(tf.initialize_all_variables())
    else:
        saver.restore(sess, load_path)
        print("Model restored from %s" % load_path)

    # accuracy
    pred = tf.reshape(model.pred, [-1, 9*10*16])
    label = tf.reshape(model.label, [-1, 9*10*16])
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(label,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    logging.basicConfig(filename='log.txt', level=logging.DEBUG)
    # train steps
    for i in range(Config.n_epoch):

        # training step
        batch_data, batch_label = train_data.next_batch(Config.minibatch_size)

        input_dict = {model.label:batch_label}
        for var, data in zip(model.inputs, batch_data):
            input_dict[var]=data

        #from IPython import embed;embed()
        sess.run(train_step, feed_dict=input_dict)

        # evalue step
        if (i+1)%Config.evalue_point == 0:
            batch_data, batch_label = val_data.next_batch(Config.minibatch_size)
            val_dict = {model.label:batch_label}
            for var, data in zip(model.inputs, batch_data):
                val_dict[var]=data
            score = accuracy.eval(feed_dict=val_dict)
            print("epoch %d, accuracy is %.2f" % (i,score))
            logging.info("epoch %d, accuracy is %.2f" % (i,score))

        # save step
        if (i+1)%Config.check_point == 0:
            save_path = saver.save(sess, "%s/epoch-%d" %(Config.save_path, i))
            print("Model saved in file: %s" % save_path)
            logging.info("Model saved in file: %s" % save_path) 

def init_all(config, gpu_list, checkpoint, mode, *args, **params):
    result = {}

    logger.info("Begin to initialize dataset and formatter...")
    if mode == "train":
        init_formatter(config, ["train", "valid"], *args, **params)
        result["train_dataset"], result["valid_dataset"] = init_dataset(config, *args, **params)
    else:
        init_formatter(config, ["test"], *args, **params)
        result["test_dataset"] = init_test_dataset(config, *args, **params)

    logger.info("Begin to initialize models...")

    model = get_model(config.get("model", "model_name"))(config, gpu_list, *args, **params)
    optimizer = init_optimizer(model, config, *args, **params)
    trained_epoch = 0
    global_step = 0

    if len(gpu_list) > 0:
        model = model.cuda()

        try:
            model.init_multi_gpu(gpu_list, config, *args, **params)
        except Exception as e:
            logger.warning("No init_multi_gpu implemented in the model, use single gpu instead.")

    try:
        parameters = torch.load(checkpoint)
        model.load_state_dict(parameters["model"])

        if mode == "train":
            trained_epoch = parameters["trained_epoch"]
            if config.get("train", "optimizer") == parameters["optimizer_name"]:
                optimizer.load_state_dict(parameters["optimizer"])
            else:
                logger.warning("Optimizer changed, do not load parameters of optimizer.")

            if "global_step" in parameters:
                global_step = parameters["global_step"]
    except Exception as e:
        information = "Cannot load checkpoint file with error %s" % str(e)
        if mode == "test":
            logger.error(information)
            raise e
        else:
            logger.warning(information)

    result["model"] = model
    if mode == "train":
        result["optimizer"] = optimizer
        result["trained_epoch"] = trained_epoch
        result["output_function"] = init_output_function(config)
        result["global_step"] = global_step

    logger.info("Initialize done.")

    return result 

def main():
    args = get_args()
    image_dir = args.image_dir
    test_dir = args.test_dir
    image_size = args.image_size
    batch_size = args.batch_size
    nb_epochs = args.nb_epochs
    lr = args.lr
    steps = args.steps
    loss_type = args.loss
    output_path = Path(__file__).resolve().parent.joinpath(args.output_path)
    model = get_model(args.model)

    if args.weight is not None:
        model.load_weights(args.weight)

    opt = Adam(lr=lr)
    callbacks = []

    if loss_type == "l0":
        l0 = L0Loss()
        callbacks.append(UpdateAnnealingParameter(l0.gamma, nb_epochs, verbose=1))
        loss_type = l0()

    model.compile(optimizer=opt, loss=loss_type, metrics=[PSNR])
    source_noise_model = get_noise_model(args.source_noise_model)
    target_noise_model = get_noise_model(args.target_noise_model)
    val_noise_model = get_noise_model(args.val_noise_model)
    generator = NoisyImageGenerator(image_dir, source_noise_model, target_noise_model, batch_size=batch_size,
                                    image_size=image_size)
    val_generator = ValGenerator(test_dir, val_noise_model)
    output_path.mkdir(parents=True, exist_ok=True)
    callbacks.append(LearningRateScheduler(schedule=Schedule(nb_epochs, lr)))
    callbacks.append(ModelCheckpoint(str(output_path) + "/weights.{epoch:03d}-{val_loss:.3f}-{val_PSNR:.5f}.hdf5",
                                     monitor="val_PSNR",
                                     verbose=1,
                                     mode="max",
                                     save_best_only=True))

    hist = model.fit_generator(generator=generator,
                               steps_per_epoch=steps,
                               epochs=nb_epochs,
                               validation_data=val_generator,
                               verbose=1,
                               callbacks=callbacks)

    np.savez(str(output_path.joinpath("history.npz")), history=hist.history) 

def train(args):

    device = args.device
    load_path = args.load_path
    # load data
    train_data = load_data('train')
    val_data = load_data('validation')

    # load model
    with tf.device('/gpu:%d' % device):
        model = get_model('train')

    # trainer init
    optimizer = Config.optimizer
    train_step = optimizer.minimize(model.loss)

    # init session and server
    sess = tf.InteractiveSession()
    saver = tf.train.Saver()
    if load_path==None:
        sess.run(tf.initialize_all_variables())
    else:
        saver.restore(sess, load_path)
        print("Model restored from %s" % load_path)

    # accuracy
    pred = tf.reshape(model.pred, [-1, 9*10*16])
    label = tf.reshape(model.label, [-1, 9*10*16])
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(label,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    logging.basicConfig(filename='log.txt', level=logging.DEBUG)
    # train steps
    for i in range(Config.n_epoch):

        # training step
        batch_data, batch_label = train_data.next_batch(Config.minibatch_size)

        input_dict = {model.label:batch_label}
        for var, data in zip(model.inputs, batch_data):
            input_dict[var]=data

        #from IPython import embed;embed()
        sess.run(train_step, feed_dict=input_dict)

        # evalue step
        if (i+1)%Config.evalue_point == 0:
            batch_data, batch_label = val_data.next_batch(Config.minibatch_size)
            val_dict = {model.label:batch_label}
            for var, data in zip(model.inputs, batch_data):
                val_dict[var]=data
            score = accuracy.eval(feed_dict=val_dict)
            print("epoch %d, accuracy is %.2f" % (i,score))
            logging.info("epoch %d, accuracy is %.2f" % (i,score))

        # save step
        if (i+1)%Config.check_point == 0:
            save_path = saver.save(sess, "%s/epoch-%d" %(Config.save_path, i))
            print("Model saved in file: %s" % save_path)
            logging.info("Model saved in file: %s" % save_path) 

def train(args):

    device = args.device
    load_path = args.load_path
    # load data
    train_data = load_data('train')
    val_data = load_data('validation')

    # load model
    with tf.device('/gpu:%d' % device):
        model = get_model('train')

    # trainer init
    optimizer = Config.optimizer
    train_step = optimizer.minimize(model.loss)

    # init session and server
    sess = tf.InteractiveSession()
    saver = tf.train.Saver()
    if load_path==None:
        sess.run(tf.initialize_all_variables())
    else:
        saver.restore(sess, load_path)
        print("Model restored from %s" % load_path)

    # accuracy
    pred = tf.reshape(model.pred, [-1, 9*10*16])
    label = tf.reshape(model.label, [-1, 9*10*16])
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(label,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    logging.basicConfig(filename='log.txt', level=logging.DEBUG)
    # train steps
    for i in range(Config.n_epoch):

        # training step
        batch_data, batch_label = train_data.next_batch(Config.minibatch_size)

        input_dict = {model.label:batch_label}
        for var, data in zip(model.inputs, batch_data):
            input_dict[var]=data

        #from IPython import embed;embed()
        sess.run(train_step, feed_dict=input_dict)

        # evalue step
        if (i+1)%Config.evalue_point == 0:
            batch_data, batch_label = val_data.next_batch(Config.minibatch_size)
            val_dict = {model.label:batch_label}
            for var, data in zip(model.inputs, batch_data):
                val_dict[var]=data
            score = accuracy.eval(feed_dict=val_dict)
            print("epoch %d, accuracy is %.2f" % (i,score))
            logging.info("epoch %d, accuracy is %.2f" % (i,score))

        # save step
        if (i+1)%Config.check_point == 0:
            save_path = saver.save(sess, "%s/epoch-%d" %(Config.save_path, i))
            print("Model saved in file: %s" % save_path)
            logging.info("Model saved in file: %s" % save_path) 

def train(args):

    device = args.device
    load_path = args.load_path
    # load data
    train_data = load_data('train')
    val_data = load_data('validation')

    # load model
    with tf.device('/gpu:%d' % device):
        model = get_model('train')

    # trainer init
    optimizer = Config.optimizer
    train_step = optimizer.minimize(model.loss)

    # init session and server
    sess = tf.InteractiveSession()
    saver = tf.train.Saver()
    if load_path==None:
        sess.run(tf.initialize_all_variables())
    else:
        saver.restore(sess, load_path)
        print("Model restored from %s" % load_path)

    # accuracy
    pred = tf.reshape(model.pred, [-1, 9*10*16])
    label = tf.reshape(model.label, [-1, 9*10*16])
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(label,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    logging.basicConfig(filename='log.txt', level=logging.DEBUG)
    # train steps
    for i in range(Config.n_epoch):

        # training step
        batch_data, batch_label = train_data.next_batch(Config.minibatch_size)

        input_dict = {model.label:batch_label}
        for var, data in zip(model.inputs, batch_data):
            input_dict[var]=data

        #from IPython import embed;embed()
        sess.run(train_step, feed_dict=input_dict)

        # evalue step
        if (i+1)%Config.evalue_point == 0:
            batch_data, batch_label = val_data.next_batch(Config.minibatch_size)
            val_dict = {model.label:batch_label}
            for var, data in zip(model.inputs, batch_data):
                val_dict[var]=data
            score = accuracy.eval(feed_dict=val_dict)
            print("epoch %d, accuracy is %.2f" % (i,score))
            logging.info("epoch %d, accuracy is %.2f" % (i,score))

        # save step
        if (i+1)%Config.check_point == 0:
            save_path = saver.save(sess, "%s/epoch-%d" %(Config.save_path, i))
            print("Model saved in file: %s" % save_path)
            logging.info("Model saved in file: %s" % save_path) 

def main():
    args = get_args()
    image_dir = args.image_dir
    test_dir = args.test_dir
    image_size = args.image_size
    batch_size = args.batch_size
    nb_epochs = args.nb_epochs
    lr = args.lr
    steps = args.steps
    loss_type = args.loss
    output_path = Path(__file__).resolve().parent.joinpath(args.output_path)
    model = get_model(args.model)

    if args.weight is not None:
        model.load_weights(args.weight)

    opt = Adam(lr=lr)
    callbacks = []

    if loss_type == "l0":
        l0 = L0Loss()
        callbacks.append(UpdateAnnealingParameter(l0.gamma, nb_epochs, verbose=1))
        loss_type = l0()

    model.compile(optimizer=opt, loss=loss_type, metrics=[PSNR])
    source_noise_model = get_noise_model(args.source_noise_model)
    target_noise_model = get_noise_model(args.target_noise_model)
    val_noise_model = get_noise_model(args.val_noise_model)
    generator = NoisyImageGenerator(image_dir, source_noise_model, target_noise_model, batch_size=batch_size,
                                    image_size=image_size)
    val_generator = ValGenerator(test_dir, val_noise_model)
    output_path.mkdir(parents=True, exist_ok=True)
    callbacks.append(LearningRateScheduler(schedule=Schedule(nb_epochs, lr)))
    callbacks.append(ModelCheckpoint(str(output_path) + "/weights.{epoch:03d}-{val_loss:.3f}-{val_PSNR:.5f}.hdf5",
                                     monitor="val_PSNR",
                                     verbose=1,
                                     mode="max",
                                     save_best_only=True))

    hist = model.fit_generator(generator=generator,
                               steps_per_epoch=steps,
                               epochs=nb_epochs,
                               validation_data=val_generator,
                               verbose=1,
                               callbacks=callbacks)

    np.savez(str(output_path.joinpath("history.npz")), history=hist.history) 

def train(args):

    device = args.device
    load_path = args.load_path
    # load data
    train_data = load_data('train')
    val_data = load_data('validation')

    # load model
    with tf.device('/gpu:%d' % device):
        model = get_model('train')

    # trainer init
    optimizer = Config.optimizer
    train_step = optimizer.minimize(model.loss)

    # init session and server
    sess = tf.InteractiveSession()
    saver = tf.train.Saver()
    if load_path==None:
        sess.run(tf.initialize_all_variables())
    else:
        saver.restore(sess, load_path)
        print("Model restored from %s" % load_path)

    # accuracy
    pred = tf.reshape(model.pred, [-1, 9*10*16])
    label = tf.reshape(model.label, [-1, 9*10*16])
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(label,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    logging.basicConfig(filename='log.txt', level=logging.DEBUG)
    # train steps
    for i in range(Config.n_epoch):

        # training step
        batch_data, batch_label = train_data.next_batch(Config.minibatch_size)

        input_dict = {model.label:batch_label}
        for var, data in zip(model.inputs, batch_data):
            input_dict[var]=data

        #from IPython import embed;embed()
        sess.run(train_step, feed_dict=input_dict)

        # evalue step
        if (i+1)%Config.evalue_point == 0:
            batch_data, batch_label = val_data.next_batch(Config.minibatch_size)
            val_dict = {model.label:batch_label}
            for var, data in zip(model.inputs, batch_data):
                val_dict[var]=data
            score = accuracy.eval(feed_dict=val_dict)
            print("epoch %d, accuracy is %.2f" % (i,score))
            logging.info("epoch %d, accuracy is %.2f" % (i,score))

        # save step
        if (i+1)%Config.check_point == 0:
            save_path = saver.save(sess, "%s/epoch-%d" %(Config.save_path, i))
            print("Model saved in file: %s" % save_path)
            logging.info("Model saved in file: %s" % save_path) 

def train(args):

    device = args.device
    load_path = args.load_path
    # load data
    train_data = load_data('train')
    val_data = load_data('validation')

    # load model
    with tf.device('/gpu:%d' % device):
        model = get_model('train')

    # trainer init
    optimizer = Config.optimizer
    train_step = optimizer.minimize(model.loss)

    # init session and server
    sess = tf.InteractiveSession()
    saver = tf.train.Saver()
    if load_path==None:
        sess.run(tf.initialize_all_variables())
    else:
        saver.restore(sess, load_path)
        print("Model restored from %s" % load_path)

    # accuracy
    pred = tf.reshape(model.pred, [-1, 9*10*16])
    label = tf.reshape(model.label, [-1, 9*10*16])
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(label,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    logging.basicConfig(filename='log.txt', level=logging.DEBUG)
    # train steps
    for i in range(Config.n_epoch):

        # training step
        batch_data, batch_label = train_data.next_batch(Config.minibatch_size)

        input_dict = {model.label:batch_label}
        for var, data in zip(model.inputs, batch_data):
            input_dict[var]=data

        #from IPython import embed;embed()
        sess.run(train_step, feed_dict=input_dict)

        # evalue step
        if (i+1)%Config.evalue_point == 0:
            batch_data, batch_label = val_data.next_batch(Config.minibatch_size)
            val_dict = {model.label:batch_label}
            for var, data in zip(model.inputs, batch_data):
                val_dict[var]=data
            score = accuracy.eval(feed_dict=val_dict)
            print("epoch %d, accuracy is %.2f" % (i,score))
            logging.info("epoch %d, accuracy is %.2f" % (i,score))

        # save step
        if (i+1)%Config.check_point == 0:
            save_path = saver.save(sess, "%s/epoch-%d" %(Config.save_path, i))
            print("Model saved in file: %s" % save_path)
            logging.info("Model saved in file: %s" % save_path) 

def train(args):

    device = args.device
    load_path = args.load_path
    # load data
    train_data = load_data('train')
    val_data = load_data('validation')

    # load model
    with tf.device('/gpu:%d' % device):
        model = get_model('policy')

    # trainer init
    optimizer = Config.optimizer
    train_step = optimizer.minimize(model.loss)

    # init session and server
    sess = tf.InteractiveSession()
    saver = tf.train.Saver()
    if load_path==None:
        sess.run(tf.initialize_all_variables())
    else:
        saver.restore(sess, load_path)
        print("Model restored from %s" % load_path)

    # accuracy
    pred = tf.reshape(model.pred, [-1, 9*10*16])
    label = tf.reshape(model.label, [-1, 9*10*16])
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(label,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    logging.basicConfig(filename='log.txt', level=logging.DEBUG)
    # train steps
    for i in range(Config.n_epoch):

        # training step
        batch_data, batch_label = train_data.next_batch(Config.minibatch_size)

        input_dict = {model.label:batch_label}
        for var, data in zip(model.inputs, batch_data):
            input_dict[var]=data

        #from IPython import embed;embed()
        sess.run(train_step, feed_dict=input_dict)

        # evalue step
        if (i+1)%Config.evalue_point == 0:
            batch_data, batch_label = val_data.next_batch(Config.minibatch_size)
            val_dict = {model.label:batch_label}
            for var, data in zip(model.inputs, batch_data):
                val_dict[var]=data
            score = accuracy.eval(feed_dict=val_dict)
            print("epoch %d, accuracy is %.2f" % (i,score))
            logging.info("epoch %d, accuracy is %.2f" % (i,score))

        # save step
        if (i+1)%Config.check_point == 0:
            save_path = saver.save(sess, "%s/epoch-%d" %(Config.save_path, i))
            print("Model saved in file: %s" % save_path)
            logging.info("Model saved in file: %s" % save_path) 

def train(args):

    device = args.device
    load_path = args.load_path
    # load data
    train_data = load_data('train')
    val_data = load_data('validation')

    # load model
    with tf.device('/gpu:%d' % device):
        model = get_model('train')

    # trainer init
    optimizer = Config.optimizer
    train_step = optimizer.minimize(model.loss)

    # init session and server
    sess = tf.InteractiveSession()
    saver = tf.train.Saver()
    if load_path==None:
        sess.run(tf.initialize_all_variables())
    else:
        saver.restore(sess, load_path)
        print("Model restored from %s" % load_path)

    # accuracy
    pred = tf.reshape(model.pred, [-1, 9*10*16])
    label = tf.reshape(model.label, [-1, 9*10*16])
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(label,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    logging.basicConfig(filename='log.txt', level=logging.DEBUG)
    # train steps
    for i in range(Config.n_epoch):

        # training step
        batch_data, batch_label = train_data.next_batch(Config.minibatch_size)

        input_dict = {model.label:batch_label}
        for var, data in zip(model.inputs, batch_data):
            input_dict[var]=data

        #from IPython import embed;embed()
        sess.run(train_step, feed_dict=input_dict)

        # evalue step
        if (i+1)%Config.evalue_point == 0:
            batch_data, batch_label = val_data.next_batch(Config.minibatch_size)
            val_dict = {model.label:batch_label}
            for var, data in zip(model.inputs, batch_data):
                val_dict[var]=data
            score = accuracy.eval(feed_dict=val_dict)
            print("epoch %d, accuracy is %.2f" % (i,score))
            logging.info("epoch %d, accuracy is %.2f" % (i,score))

        # save step
        if (i+1)%Config.check_point == 0:
            save_path = saver.save(sess, "%s/epoch-%d" %(Config.save_path, i))
            print("Model saved in file: %s" % save_path)
            logging.info("Model saved in file: %s" % save_path) 

def train(args):

    device = args.device
    load_path = args.load_path
    # load data
    train_data = load_data('train')
    val_data = load_data('validation')

    # load model
    with tf.device('/gpu:%d' % device):
        model = get_model('train')

    # trainer init
    optimizer = Config.optimizer
    train_step = optimizer.minimize(model.loss)

    # init session and server
    sess = tf.InteractiveSession()
    saver = tf.train.Saver()
    if load_path==None:
        sess.run(tf.initialize_all_variables())
    else:
        saver.restore(sess, load_path)
        print("Model restored from %s" % load_path)

    # accuracy
    pred = tf.reshape(model.pred, [-1, 9*10*16])
    label = tf.reshape(model.label, [-1, 9*10*16])
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(label,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    logging.basicConfig(filename='log.txt', level=logging.DEBUG)
    # train steps
    for i in range(Config.n_epoch):

        # training step
        batch_data, batch_label = train_data.next_batch(Config.minibatch_size)

        input_dict = {model.label:batch_label}
        for var, data in zip(model.inputs, batch_data):
            input_dict[var]=data

        #from IPython import embed;embed()
        sess.run(train_step, feed_dict=input_dict)

        # evalue step
        if (i+1)%Config.evalue_point == 0:
            batch_data, batch_label = val_data.next_batch(Config.minibatch_size)
            val_dict = {model.label:batch_label}
            for var, data in zip(model.inputs, batch_data):
                val_dict[var]=data
            score = accuracy.eval(feed_dict=val_dict)
            print("epoch %d, accuracy is %.2f" % (i,score))
            logging.info("epoch %d, accuracy is %.2f" % (i,score))

        # save step
        if (i+1)%Config.check_point == 0:
            save_path = saver.save(sess, "%s/epoch-%d" %(Config.save_path, i))
            print("Model saved in file: %s" % save_path)
            logging.info("Model saved in file: %s" % save_path) 

def train(args):

    device = args.device
    load_path = args.load_path
    # load data
    train_data = load_data('train')
    val_data = load_data('validation')

    # load model
    with tf.device('/gpu:%d' % device):
        model = get_model('train')

    # trainer init
    optimizer = Config.optimizer
    train_step = optimizer.minimize(model.loss)

    # init session and server
    sess = tf.InteractiveSession()
    saver = tf.train.Saver()
    if load_path==None:
        sess.run(tf.initialize_all_variables())
    else:
        saver.restore(sess, load_path)
        print("Model restored from %s" % load_path)

    # accuracy
    pred = tf.reshape(model.pred, [-1, 9*10*16])
    label = tf.reshape(model.label, [-1, 9*10*16])
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(label,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    logging.basicConfig(filename='log.txt', level=logging.DEBUG)
    # train steps
    for i in range(Config.n_epoch):

        # training step
        batch_data, batch_label = train_data.next_batch(Config.minibatch_size)

        input_dict = {model.label:batch_label}
        for var, data in zip(model.inputs, batch_data):
            input_dict[var]=data

        #from IPython import embed;embed()
        sess.run(train_step, feed_dict=input_dict)

        # evalue step
        if (i+1)%Config.evalue_point == 0:
            batch_data, batch_label = val_data.next_batch(Config.minibatch_size)
            val_dict = {model.label:batch_label}
            for var, data in zip(model.inputs, batch_data):
                val_dict[var]=data
            score = accuracy.eval(feed_dict=val_dict)
            print("epoch %d, accuracy is %.2f" % (i,score))
            logging.info("epoch %d, accuracy is %.2f" % (i,score))

        # save step
        if (i+1)%Config.check_point == 0:
            save_path = saver.save(sess, "%s/epoch-%d" %(Config.save_path, i))
            print("Model saved in file: %s" % save_path)
            logging.info("Model saved in file: %s" % save_path) 

def train(args):

    device = args.device
    load_path = args.load_path
    # load data
    train_data = load_data('train')
    val_data = load_data('validation')

    # load model
    with tf.device('/gpu:%d' % device):
        model = get_model('train')

    # trainer init
    optimizer = Config.optimizer
    train_step = optimizer.minimize(model.loss)

    # init session and server
    sess = tf.InteractiveSession()
    saver = tf.train.Saver()
    if load_path==None:
        sess.run(tf.initialize_all_variables())
    else:
        saver.restore(sess, load_path)
        print("Model restored from %s" % load_path)

    # accuracy
    pred = tf.reshape(model.pred, [-1, 9*10*16])
    label = tf.reshape(model.label, [-1, 9*10*16])
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(label,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    # train steps
    for i in range(Config.n_epoch):

        # training step
        batch_data, batch_label = train_data.next_batch(Config.minibatch_size)

        input_dict = {model.label:batch_label}
        for var, data in zip(model.inputs, batch_data):
            input_dict[var]=data

        #from IPython import embed;embed()
        sess.run(train_step, feed_dict=input_dict)

        # evalue step
        if (i+1)%Config.evalue_point == 0:
            batch_data, batch_label = val_data.next_batch(Config.minibatch_size)
            val_dict = {model.label:batch_label}
            for var, data in zip(model.inputs, batch_data):
                val_dict[var]=data
            score = accuracy.eval(feed_dict=val_dict)
            print("epoch %d, accuracy is %.2f" % (i,score))

        # save step
        if (i+1)%Config.check_point == 0:
            save_path = saver.save(sess, "%s/epoch-%d" %(Config.save_path, i))
            print("Model saved in file: %s" % save_path) 

def train(args):

    device = args.device
    load_path = args.load_path
    # load data
    train_data = load_data('train')
    val_data = load_data('validation')

    # load model
    with tf.device('/gpu:%d' % device):
        model = get_model('train')

    # trainer init
    optimizer = Config.optimizer
    train_step = optimizer.minimize(model.loss)

    # init session and server
    sess = tf.InteractiveSession()
    saver = tf.train.Saver()
    if load_path==None:
        sess.run(tf.initialize_all_variables())
    else:
        saver.restore(sess, load_path)
        print("Model restored from %s" % load_path)

    # accuracy
    pred = tf.reshape(model.pred, [-1, 9*10*16])
    label = tf.reshape(model.label, [-1, 9*10*16])
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(label,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    logging.basicConfig(filename='log.txt', level=logging.DEBUG)
    # train steps
    for i in range(Config.n_epoch):

        # training step
        batch_data, batch_label = train_data.next_batch(Config.minibatch_size)

        input_dict = {model.label:batch_label}
        for var, data in zip(model.inputs, batch_data):
            input_dict[var]=data

        #from IPython import embed;embed()
        sess.run(train_step, feed_dict=input_dict)

        # evalue step
        if (i+1)%Config.evalue_point == 0:
            batch_data, batch_label = val_data.next_batch(Config.minibatch_size)
            val_dict = {model.label:batch_label}
            for var, data in zip(model.inputs, batch_data):
                val_dict[var]=data
            score = accuracy.eval(feed_dict=val_dict)
            print("epoch %d, accuracy is %.2f" % (i,score))
            logging.info("epoch %d, accuracy is %.2f" % (i,score))

        # save step
        if (i+1)%Config.check_point == 0:
            save_path = saver.save(sess, "%s/epoch-%d" %(Config.save_path, i))
            print("Model saved in file: %s" % save_path)
            logging.info("Model saved in file: %s" % save_path)