Function train_lstm

code/lstm.py:448–649

(
    dim_proj=128,  # word embeding dimension and LSTM number of hidden units.
    patience=10,  # Number of epoch to wait before early stop if no progress
    max_epochs=5000,  # The maximum number of epoch to run
    dispFreq=10,  # Display to stdout the training progress every N updates
    decay_c=0.,  # Weight decay for the classifier applied to the U weights.
    lrate=0.0001,  # Learning rate for sgd (not used for adadelta and rmsprop)
    n_words=10000,  # Vocabulary size
    optimizer=adadelta,  # sgd, adadelta and rmsprop available, sgd very hard to use, not recommanded (probably need momentum and decaying learning rate).
    encoder='lstm',  # TODO: can be removed must be lstm.
    saveto='lstm_model.npz',  # The best model will be saved there
    validFreq=370,  # Compute the validation error after this number of update.
    saveFreq=1110,  # Save the parameters after every saveFreq updates
    maxlen=100,  # Sequence longer then this get ignored
    batch_size=16,  # The batch size during training.
    valid_batch_size=64,  # The batch size used for validation/test set.
    dataset='imdb',

    # Parameter for extra option
    noise_std=0.,
    use_dropout=True,  # if False slightly faster, but worst test error
                       # This frequently need a bigger model.
    reload_model=None,  # Path to a saved model we want to start from.
    test_size=-1,  # If >0, we keep only this number of test example.
)

def train_lstm(
    dim_proj=128,  # word embeding dimension and LSTM number of hidden units.
    patience=10,  # Number of epoch to wait before early stop if no progress
    max_epochs=5000,  # The maximum number of epoch to run
    dispFreq=10,  # Display to stdout the training progress every N updates
    decay_c=0.,  # Weight decay for the classifier applied to the U weights.
    lrate=0.0001,  # Learning rate for sgd (not used for adadelta and rmsprop)
    n_words=10000,  # Vocabulary size
    optimizer=adadelta,  # sgd, adadelta and rmsprop available, sgd very hard to use, not recommanded (probably need momentum and decaying learning rate).
    encoder='lstm',  # TODO: can be removed must be lstm.
    saveto='lstm_model.npz',  # The best model will be saved there
    validFreq=370,  # Compute the validation error after this number of update.
    saveFreq=1110,  # Save the parameters after every saveFreq updates
    maxlen=100,  # Sequence longer then this get ignored
    batch_size=16,  # The batch size during training.
    valid_batch_size=64,  # The batch size used for validation/test set.
    dataset='imdb',

    # Parameter for extra option
    noise_std=0.,
    use_dropout=True,  # if False slightly faster, but worst test error
                       # This frequently need a bigger model.
    reload_model=None,  # Path to a saved model we want to start from.
    test_size=-1,  # If >0, we keep only this number of test example.
):

    # Model options
    model_options = locals().copy()
    print("model options", model_options)

    load_data, prepare_data = get_dataset(dataset)

    print('Loading data')
    train, valid, test = load_data(n_words=n_words, valid_portion=0.05,
                                   maxlen=maxlen)
    if test_size > 0:
        # The test set is sorted by size, but we want to keep random
        # size example.  So we must select a random selection of the
        # examples.
        idx = numpy.arange(len(test[0]))
        numpy.random.shuffle(idx)
        idx = idx[:test_size]
        test = ([test[0][n] for n in idx], [test[1][n] for n in idx])

    ydim = numpy.max(train[1]) + 1

    model_options['ydim'] = ydim

    print('Building model')
    # This create the initial parameters as numpy ndarrays.
    # Dict name (string) -> numpy ndarray
    params = init_params(model_options)

    if reload_model:
        load_params('lstm_model.npz', params)

    # This create Theano Shared Variable from the parameters.
    # Dict name (string) -> Theano Tensor Shared Variable