def main():
config = get_config()
# Wraps arg parse functionallity around train function so that it can be provided as arguments
parser = argparse.ArgumentParser(description='Trains a language model from a wiki dataset')
parser.add_argument('dump', help='The wiki dump name to train a language model for')
parser.add_argument('name', help='Name of the model, used in exported files etc')
parser.add_argument('--test-mode', help="makes dataset smaller to see if the script actually runs", action='store_true')
parser.add_argument('--epochs',type=int,default=5, help="Number of epochs to run for")
parser.add_argument('--batch_size', type=int, default=64, help="Batch size")
parser.add_argument('--gpu',type=int, default=-1, help="Gpu to use")
parser.add_argument('--out',default='result',help="Folder to put results")
parser.add_argument('--grad-clip', default=True, help="Clip gradients")
parser.add_argument('--brpoplen', type=int, default=35)
parser.add_argument('--resume', default='')
parser.add_argument('--max-seq-size', default=250000, type=int)
args = parser.parse_args()
com = Communication(args.out)
com.add_text("Type", "language model")
train(args.dump, args.name, args.test_mode, args.epochs, args.batch_size, args.gpu, args.out, args.grad_clip, args.brpoplen, args.resume, args.max_seq_size,com)
com.send_slack(config.get('slack','channel'), config.get('slack','api_token'))
def main():
config = get_config()
# Wraps arg parse functionallity around train function so that it can be provided as arguments
parser = argparse.ArgumentParser(description='Evaluates a TRNN ')
parser.add_argument('dump', help='The wiki dump name to train a language model for')
parser.add_argument('lm', help='Path to language model')
parser.add_argument('--test-mode', help="makes dataset smaller to see if the script actually runs", action='store_true')
parser.add_argument('--batch_size', type=int, default=64, help="Batch size")
parser.add_argument('--gpu',type=int, default=-1, help="Gpu to use")
parser.add_argument('--max-seq-size', default=250000,type=int)
parser.add_argument('--out', default='result', help="Folder to put results")
args = parser.parse_args()
com = Communication(args.out)
com.add_text("Type", "Translation matrix")
# keep time
com.add_text("Start date", time.strftime("%c"))
start = time.time()
check_loss(com, args.lm, args.dump, args.gpu, args.batch_size, args.max_seq_size, args.test_mode)
diff = time.time() - start
com.add_text('time',seconds_to_str(diff))
com.send_slack(config.get('slack','channel'),config.get('slack','api_token'))
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--batchsize',
'-b',
type=int,
default=20,
help='Number of examples in each mini-batch')
parser.add_argument('--bproplen',
'-l',
type=int,
default=35,
help='Number of words in each mini-batch '
'(= length of truncated BPTT)')
parser.add_argument('--epoch',
'-e',
type=int,
default=39,
help='Number of sweeps over the dataset to train')
parser.add_argument('--gpu',
'-g',
type=int,
default=-1,
help='GPU ID (negative value indicates CPU)')
parser.add_argument('--gradclip',
'-c',
type=float,
default=5,
help='Gradient norm threshold to clip')
parser.add_argument('--out',
'-o',
default='result',
help='Directory to output the result')
parser.add_argument('--resume',
'-r',
default='',
help='Resume the training from snapshot')
parser.add_argument('--test',
action='store_true',
help='Use tiny datasets for quick tests')
parser.set_defaults(test=False)
parser.add_argument('--unit',
'-u',
type=int,
default=650,
help='Number of LSTM units in each layer')
args = parser.parse_args()
com = Communication(args.out)
com.add_text("TYPE", "PBT")
# Load the Penn Tree Bank long word sequence dataset
train, val, test = chainer.datasets.get_ptb_words()
n_vocab = max(train) + 1 # train is just an array of integers
print('#vocab =', n_vocab)
if args.test:
train = train[:100]
val = val[:100]
test = test[:100]
train_iter = ParallelSequentialIterator(train, args.batchsize)
val_iter = ParallelSequentialIterator(val, 1, repeat=False)
test_iter = ParallelSequentialIterator(test, 1, repeat=False)
# Prepare an RNNLM model
rnn = RNNForLM(n_vocab, args.unit)
model = L.Classifier(rnn)
model.compute_accuracy = False # we only want the perplexity
if args.gpu >= 0:
chainer.cuda.get_device(args.gpu).use() # make the GPU current
model.to_gpu()
# Set up an optimizer
optimizer = chainer.optimizers.SGD(lr=1.0)
optimizer.setup(model)
optimizer.add_hook(chainer.optimizer.GradientClipping(args.gradclip))
# Set up a trainer
updater = BPTTUpdater(train_iter, optimizer, args.bproplen, args.gpu)
trainer = training.Trainer(updater, (args.epoch, 'epoch'), out=args.out)
eval_model = model.copy() # Model with shared params and distinct states
eval_rnn = eval_model.predictor
eval_rnn.train = False
trainer.extend(
extensions.Evaluator(
val_iter,
eval_model,
device=args.gpu,
# Reset the RNN state at the beginning of each evaluation
eval_hook=lambda _: eval_rnn.reset_state()))
interval = 5 if args.test else 500
trainer.extend(
extensions.LogReport(postprocess=compute_perplexity,
trigger=(interval, 'iteration')))
trainer.extend(extensions.PrintReport(
['epoch', 'iteration', 'perplexity', 'val_perplexity']),
trigger=(interval, 'iteration'))
trainer.extend(
extensions.ProgressBar(update_interval=1 if args.test else 10))
#trainer.extend(extensions.snapshot())
#trainer.extend(extensions.snapshot_object(
# model, 'model_iter_{.updater.iteration}'))
start = time.time()
loss_r = extensions.PlotReport(['validation/main/loss', 'main/loss'],
'epoch',
file_name='loss.png')
trainer.extend(loss_r)
if args.resume:
chainer.serializers.load_npz(args.resume, trainer)
date = time.strftime("%Y-%m-%d_%H-%M-%S")
trainer.run()
diff = time.time() - start
com.add_text('time', seconds_to_str(diff))
com.add_file(os.path.join(args.out, 'loss.png'), "Loss")
#save plots
# Evaluate the final model
print('test')
eval_rnn.reset_state()
evaluator = extensions.Evaluator(test_iter, eval_model, device=args.gpu)
result = evaluator()
print('test perplexity:', np.exp(float(result['main/loss'])))
com.add_text("Loss", result['main/loss'])
config = get_config()
com.send_slack(config.get('slack', 'channel'),
config.get('slack', 'api_token'))
