if __name__ == "__main__":
Log.AppLogger.configure(mkdir=True)
App.add_command(
'decode', decode, {
'gpu':
arg('--gpu',
'-g',
type=int,
default=-1,
help='GPU ID (negative value indicates CPU)'),
'model_file':
arg('--modelfile',
type=str,
required=True,
help='Trained model archive file'),
'save_to':
arg('--out',
type=str,
default=None,
help='Save results to the specified directory'),
'target_file':
arg('--targetfile',
type=str,
required=True,
help='Decoding target data file'),
})
App.run()
model,
loss_func=chainer.functions.softmax_cross_entropy,
accuracy_func=chainer.functions.accuracy)
trainer.configure(
hooks={
training.EPOCH_TRAIN_BEGIN: lambda _: set_chainer_train(True),
training.EPOCH_VALIDATE_BEGIN: lambda _: set_chainer_train(False)
},
converter=lambda x: chainer.dataset.convert.to_device(device, x))
trainer.add_listener(
training.listeners.ProgressBar(lambda n: tqdm(total=n)), priority=200)
trainer.fit((train_x, train_y), (test_x, test_y), n_epoch, batch_size)
if __name__ == "__main__":
App.configure(name='chainer-mnist', logoption='d')
App.add_command(
'train',
train, {
'batch_size':
arg('--batchsize',
'-b',
type=int,
default=100,
help='Number of images in each mini-batch'),
'device':
arg('--device',
type=int,
default=-1,
metavar='ID',
help='Device ID (negative value indicates CPU)'),
pbar.update(len(ts))
pbar.close()
evaluator.report()
logging.info("Number of correct tree: {}/{}".format(
n_corrects, len(test_dataset)))
if __name__ == "__main__":
# App.configure(logdir=App.basedir + '/../logs')
if '--savedir' in sys.argv:
savedir_index = sys.argv.index('--savedir') + 1
savedir = sys.argv[savedir_index]
if '--modelfile' in sys.argv:
savedir_index = sys.argv.index('--modelfile') + 1
savedir = os.path.dirname(sys.argv[savedir_index])
App.configure(logdir=App.basedir + '/' + savedir)
logging.AppLogger.configure(mkdir=True)
App.add_command(
'train', train, {
'batch_size':
arg('--batchsize',
type=int,
default=20,
metavar='NUM',
help='Number of examples in each mini-batch'),
'cache_dir':
arg('--cachedir',
type=str,
default=(App.basedir + '/../cache'),
metavar='DIR',
App.add_command(
'train', train, {
'backend':
arg('--backend',
type=str,
choices=('chainer', 'pytorch'),
default='chainer',
help='Backend framework for computation'),
'batch_size':
arg('--batchsize',
'-b',
type=int,
default=32,
help='Number of examples in each mini-batch'),
'embed_file':
arg('--embedfile',
type=str,
default=None,
help='Pretrained word embedding file'),
'embed_size':
arg('--embedsize',
type=int,
default=100,
help='Size of embeddings'),
'gpu':
arg('--gpu',
'-g',
type=int,
default=-1,
help='GPU ID (negative value indicates CPU)'),
'lr':
arg('--lr', type=float, default=0.002, help='Learning Rate'),
'model_params':
arg('--model',
action='store_dict',
default={},
help='Model hyperparameter'),
'n_epoch':
arg('--epoch',
'-e',
type=int,
default=20,
help='Number of sweeps over the dataset to train'),
'seed':
arg('--seed', type=int, default=None, help='Random seed'),
'save_to':
arg('--out',
type=str,
default=None,
help='Save model to the specified directory'),
'test_file':
arg('--validfile',
type=str,
default=None,
help='validation data file'),
'train_file':
arg('--trainfile',
type=str,
required=True,
help='training data file'),
})
trainer = training.Trainer(optimizer,
model,
loss_func=compute_loss,
accuracy_func=compute_accuracy)
trainer.configure(framework_utils.config)
trainer.fit(train_dataset,
None,
batch_size=batch_size,
epochs=n_epoch,
validation_data=test_dataset,
verbose=App.verbose)
if __name__ == "__main__":
logging.AppLogger.configure(mkdir=True)
App.add_command(
'train', train, {
'train_file': arg('--trainfile', type=str, required=True),
'test_file': arg('--testfile', type=str),
'word_embed_file': arg('--embedfile', type=str),
'n_epoch': arg('--epoch', type=int, default=20),
'batch_size': arg('--batchsize', type=int, default=10),
'lr': arg('--lr', type=float, default=0.01),
'gpu': arg('--gpu', type=int, default=-1),
'seed': arg('--seed', type=int, default=1),
})
chainer.config.debug = False
chainer.config.type_check = False
App.run()
if np.std(W) > 0. else W),
loader.get_embeddings('pos'),
n_lstm_layers=kwargs.get('n_lstm_layers', 3),
lstm_hidden_size=kwargs.get('lstm_hidden_size', 400),
embeddings_dropout=kwargs.get('input_dropout', dropout_ratio),
lstm_dropout=kwargs.get('lstm_dropout', dropout_ratio),
recurrent_dropout=kwargs.get('recurrent_dropout', dropout_ratio)),
arc_mlp_units=kwargs.get('arc_mlp_units', 500),
rel_mlp_units=kwargs.get('rel_mlp_units', 100),
arc_mlp_dropout=kwargs.get('arc_mlp_dropout', dropout_ratio),
rel_mlp_dropout=kwargs.get('rel_mlp_dropout', dropout_ratio))
return parser
if __name__ == "__main__":
App.configure(logdir=App.basedir + '/../logs', loglevel='debug')
logging.AppLogger.configure(mkdir=True)
App.add_command(
'train', train, {
'batch_size':
arg('--batchsize',
type=int,
default=5000,
metavar='NUM',
help='Number of tokens in each mini-batch'),
'cache_dir':
arg('--cachedir',
type=str,
default=(App.basedir + '/../cache'),
metavar='DIR',
help='Cache directory'),
App.add_command('train', train, {
'batch_size':
arg('--batchsize', '-b', type=int, default=32,
help='Number of examples in each mini-batch'),
'embed_file':
arg('--embedfile', type=str, default=None,
help='Pretrained word embedding file'),
'embed_size':
arg('--embedsize', type=int, default=100,
help='Size of embeddings'),
'gpu':
arg('--gpu', '-g', type=int, default=-1,
help='GPU ID (negative value indicates CPU)'),
'grad_clip':
arg('--gradclip', type=float, default=5.0,
help='L2 norm threshold of gradient norm'),
'l2_lambda':
arg('--l2', type=float, default=0.0,
help='Strength of L2 regularization'),
'lr':
arg('--lr', type=float, default=0.001,
help='Learning Rate'),
'n_epoch':
arg('--epoch', '-e', type=int, default=20,
help='Number of sweeps over the dataset to train'),
'seed':
arg('--seed', type=int, default=1,
help='Random seed'),
'save_to':
arg('--out', type=str, default=None,
help='Save model to the specified directory'),
'tasks':
arg('--task', type=str, default='tp',
help='Tasks to train: {t: tagging, p: parsing}'),
'test_file':
arg('--validfile', type=str, default=None,
help='validation data file'),
'train_file':
arg('--trainfile', type=str, required=True,
help='training data file'),
})