Example #1
0
def create_trainer(args, converter):
    """
    Creates or loads a neural network according to the specified args.
    """

    logger = logging.getLogger("Logger")

    if args.load:
        logger.info("Loading provided network...")
        trainer = SentimentTrainer.load(args.load)
        # change learning rate
        trainer.learning_rate = args.learning_rate
    else:
        logger.info('Creating new network...')
        # sum the number of features in all extractors' tables
        input_size = converter.size() * (args.window * 2 + 1)
        nn = Network(input_size, args.hidden, 2)
        options = {
            'learning_rate': args.learning_rate,
            'eps': args.eps,
            'ro': args.ro,
            'verbose': args.verbose,
            'left_context': args.window,
            'right_context': args.window,
            'ngram_size': args.ngrams,
            'alpha': args.alpha
        }
        trainer = SentimentTrainer(nn, converter, options)

    trainer.saver = saver(args.model, args.vectors)

    logger.info("... with the following parameters:")
    logger.info(trainer.nn.description())

    return trainer
Example #2
0
def create_trainer(args, converter):
    """
    Creates or loads a neural network according to the specified args.
    """

    logger = logging.getLogger("Logger")

    if args.load:
        logger.info("Loading provided network...")
        trainer = SentimentTrainer.load(args.load)
        # change learning rate
        trainer.learning_rate = args.learning_rate
    else:
        logger.info('Creating new network...')
        # sum the number of features in all extractors' tables 
        input_size = converter.size() * (args.window * 2 + 1)
        nn = Network(input_size, args.hidden, 2)
        options = {
            'learning_rate': args.learning_rate,
            'eps': args.eps,
            'ro': args.ro,
            'verbose': args.verbose,
            'left_context': args.window,
            'right_context': args.window,
            'ngram_size': args.ngrams,
            'alpha': args.alpha
        }
        trainer = SentimentTrainer(nn, converter, options)

    trainer.saver = saver(args.model, args.vectors)

    logger.info("... with the following parameters:")
    logger.info(trainer.nn.description())
    
    return trainer
Example #3
0
def create_trainer(args, converter):
    """
    Creates or loads a neural network according to the specified args.
    """

    logger = logging.getLogger("Logger")

    if args.load:
        logger.info("Loading provided network...")
        trainer = SentimentTrainer.load(args.load)
        trainer.learning_rate = args.learning_rate
    else:
        logger.info('Creating new network...')
        trainer = SentimentTrainer(converter, args.learning_rate,
                                   args.window/2, args.window/2,
                                   args.hidden, args.ngrams, args.alpha)

    trainer.saver = saver(args.output, args.vectors)

    logger.info("... with the following parameters:")
    logger.info(trainer.nn.description())
    
    return trainer
Example #4
0
def create_trainer(args, converter):
    """
    Creates or loads a neural network according to the specified args.
    """

    logger = logging.getLogger("Logger")

    if args.load:
        logger.info("Loading provided network...")
        trainer = SentimentTrainer.load(args.load)
        trainer.learning_rate = args.learning_rate
    else:
        logger.info('Creating new network...')
        trainer = SentimentTrainer(converter, args.learning_rate,
                                   args.window / 2, args.window / 2,
                                   args.hidden, args.ngrams, args.alpha)

    trainer.saver = saver(args.output, args.vectors)

    logger.info("... with the following parameters:")
    logger.info(trainer.nn.description())

    return trainer