def main() -> None:
# pylint: disable=no-member,broad-except
if len(sys.argv) != 3:
print("Usage: run.py <run_ini_file> <test_datasets>")
exit(1)
test_datasets = Configuration()
test_datasets.add_argument('test_datasets')
test_datasets.add_argument('variables')
CONFIG.load_file(sys.argv[1])
CONFIG.build_model()
test_datasets.load_file(sys.argv[2])
test_datasets.build_model()
datesets_model = test_datasets.model
initialize_for_running(CONFIG.model.output, CONFIG.model.tf_manager,
datesets_model.variables)
print("")
evaluators = [(e[0], e[0], e[1]) if len(e) == 2 else e
for e in CONFIG.model.evaluation]
for dataset in datesets_model.test_datasets:
execution_results, output_data = run_on_dataset(
CONFIG.model.tf_manager,
CONFIG.model.runners,
dataset,
CONFIG.model.postprocess,
write_out=True)
# TODO what if there is no ground truth
eval_result = evaluation(evaluators, dataset, CONFIG.model.runners,
execution_results, output_data)
if eval_result:
print_final_evaluation(dataset.name, eval_result)
def main() -> None:
parser = argparse.ArgumentParser(
description="Runs Neural Monkey as a web server.")
parser.add_argument("--port", type=int, default=5000)
parser.add_argument("--host", type=str, default="127.0.0.1")
parser.add_argument("--configuration", type=str, required=True)
parser.add_argument("--preprocess", type=str,
required=False, default=None)
args = parser.parse_args()
print("")
if args.preprocess is not None:
preprocessing = Configuration()
preprocessing.add_argument("preprocess")
preprocessing.load_file(args.preprocess)
preprocessing.build_model()
APP.config["preprocess"] = preprocessing.model.preprocess
else:
APP.config["preprocess"] = []
exp = Experiment(config_path=args.configuration)
exp.build_model()
APP.config["experiment"] = exp
APP.run(port=args.port, host=args.host)
def main() -> None:
# pylint: disable=no-member,broad-except
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("config",
metavar="INI-FILE",
help="the configuration file of the experiment")
parser.add_argument("datasets",
metavar="INI-TEST-DATASETS",
help="the configuration of the test datasets")
parser.add_argument("-g",
"--grid",
dest="grid",
action="store_true",
help="look at the SGE variables for slicing the data")
args = parser.parse_args()
test_datasets = Configuration()
test_datasets.add_argument("test_datasets")
test_datasets.add_argument("variables", cond=lambda x: isinstance(x, list))
test_datasets.load_file(args.datasets)
test_datasets.build_model()
datasets_model = test_datasets.model
exp = Experiment(config_path=args.config)
exp.build_model()
exp.load_variables(datasets_model.variables)
if args.grid and len(datasets_model.test_datasets) > 1:
raise ValueError("Only one test dataset supported when using --grid")
for dataset in datasets_model.test_datasets:
if args.grid:
if ("SGE_TASK_FIRST" not in os.environ
or "SGE_TASK_LAST" not in os.environ
or "SGE_TASK_STEPSIZE" not in os.environ
or "SGE_TASK_ID" not in os.environ):
raise EnvironmentError(
"Some SGE environment variables are missing")
length = int(os.environ["SGE_TASK_STEPSIZE"])
start = int(os.environ["SGE_TASK_ID"]) - 1
end = int(os.environ["SGE_TASK_LAST"]) - 1
if start + length > end:
length = end - start + 1
log("Running grid task {} starting at {} with step {}".format(
start // length, start, length))
dataset = dataset.subset(start, length)
if exp.config.args.evaluation is None:
exp.run_model(dataset, write_out=True)
else:
exp.evaluate(dataset, write_out=True)
for session in exp.config.model.tf_manager.sessions:
session.close()
def load_runtime_config(config_path: str) -> argparse.Namespace:
"""Load a runtime configuration file."""
cfg = Configuration()
cfg.add_argument("test_datasets")
cfg.add_argument("variables", cond=lambda x: isinstance(x, list))
cfg.load_file(config_path)
cfg.build_model()
return cfg.model
def main():
# pylint: disable=no-member,broad-except
if len(sys.argv) != 3:
print("Usage: run.py <run_ini_file> <test_datasets>")
exit(1)
test_datasets = Configuration()
test_datasets.add_argument('test_datasets')
args, sess = initialize_for_running(sys.argv[1])
datasets_args = test_datasets.load_file(sys.argv[2])
print("")
try:
for dataset in datasets_args.test_datasets:
check_dataset_and_coders(dataset, args.encoders)
except Exception as exc:
log(exc.message, color='red')
exit(1)
for dataset in datasets_args.test_datasets:
_, _, evaluation = run_on_dataset(
sess, args.runner, args.encoders + [args.decoder], args.decoder,
dataset, args.evaluation, args.postprocess, write_out=True)
if evaluation:
print_dataset_evaluation(dataset.name, evaluation)
def create_config(config_file):
config = Configuration()
config.add_argument('name', str)
config.add_argument('random_seed', int, required=False)
config.add_argument('output', str)
config.add_argument('epochs', int, cond=lambda x: x >= 0)
config.add_argument('trainer')
config.add_argument('encoders', list)
config.add_argument('decoder')
config.add_argument('batch_size', int, cond=lambda x: x > 0)
config.add_argument('train_dataset', Dataset)
config.add_argument('val_dataset', Dataset)
config.add_argument('postprocess')
config.add_argument('evaluation', cond=list)
config.add_argument('runner')
config.add_argument('test_datasets', list, required=False, default=[])
config.add_argument('initial_variables', str, required=False, default=[])
config.add_argument('validation_period', int, required=False, default=500)
config.add_argument('logging_period', int, required=False, default=20)
config.add_argument('threads', int, required=False, default=4)
config.add_argument('minimize', bool, required=False, default=False)
config.add_argument('save_n_best', int, required=False, default=1)
config.add_argument('overwrite_output_dir', bool, required=False,
default=False)
return config.load_file(config_file)
def create_config(config_file):
config = Configuration()
config.add_argument('name', str)
config.add_argument('random_seed', int, required=False)
config.add_argument('output', str)
config.add_argument('epochs', int, cond=lambda x: x >= 0)
config.add_argument('trainer')
config.add_argument('encoders', list)
config.add_argument('decoder')
config.add_argument('batch_size', int, cond=lambda x: x > 0)
config.add_argument('train_dataset', Dataset)
config.add_argument('val_dataset', Dataset)
config.add_argument('postprocess')
config.add_argument('evaluation', cond=list)
config.add_argument('runner')
config.add_argument('test_datasets', list, required=False, default=[])
config.add_argument('initial_variables', str, required=False, default=[])
config.add_argument('validation_period', int, required=False, default=500)
config.add_argument('logging_period', int, required=False, default=20)
config.add_argument('threads', int, required=False, default=4)
config.add_argument('minimize', bool, required=False, default=False)
config.add_argument('save_n_best', int, required=False, default=1)
config.add_argument('overwrite_output_dir',
bool,
required=False,
default=False)
return config.load_file(config_file)
def main():
# pylint: disable=no-member,broad-except
if len(sys.argv) != 3:
print("Usage: run.py <run_ini_file> <test_datasets>")
exit(1)
test_datasets = Configuration()
test_datasets.add_argument('test_datasets')
args, sess = initialize_for_running(sys.argv[1])
datasets_args = test_datasets.load_file(sys.argv[2])
print("")
try:
for dataset in datasets_args.test_datasets:
check_dataset_and_coders(dataset, args.encoders)
except Exception as exc:
log(str(exc), color='red')
exit(1)
for dataset in datasets_args.test_datasets:
_, _, evaluation = run_on_dataset(sess,
args.runner,
args.encoders + [args.decoder],
args.decoder,
dataset,
args.evaluation,
args.postprocess,
write_out=True)
if evaluation:
print_dataset_evaluation(dataset.name, evaluation)
def main() -> None:
parser = argparse.ArgumentParser(
description="Runs Neural Monkey as a web server.")
parser.add_argument("--port", type=int, default=5000)
parser.add_argument("--host", type=str, default="127.0.0.1")
parser.add_argument("--configuration", type=str, required=True)
parser.add_argument("--preprocess", type=str, required=False, default=None)
args = parser.parse_args()
print("")
if args.preprocess is not None:
preprocessing = Configuration()
preprocessing.add_argument("preprocess")
preprocessing.load_file(args.preprocess)
preprocessing.build_model()
APP.config["preprocess"] = preprocessing.model.preprocess
else:
APP.config["preprocess"] = []
exp = Experiment(config_path=args.configuration)
exp.build_model()
APP.config["experiment"] = exp
APP.run(port=args.port, host=args.host)
def main() -> None:
# pylint: disable=no-member,broad-except
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("config",
metavar="INI-FILE",
help="the configuration file of the experiment")
parser.add_argument("datasets",
metavar="INI-FILE",
help="the configuration file of the experiment")
parser.add_argument("--beam",
metavar="BEAM_SIZE",
type=int,
default=10,
help="Beam size.")
parser.add_argument("--kenlm",
type=str,
default=None,
help="Path to a KenLM model arpa file.")
parser.add_argument("--lm-weight",
type=float,
help="Weight of the language model.")
parser.add_argument("--null-trail-weight",
type=float,
help="Weight of the null-trailing feature.")
parser.add_argument("--nt-ratio-weight",
type=float,
help="Weight of the null-token ratio feature.")
parser.add_argument("--out", type=str, help="Path to the output file.")
args = parser.parse_args()
test_datasets = Configuration()
test_datasets.add_argument("test_datasets")
test_datasets.add_argument("batch_size", cond=lambda x: x > 0)
test_datasets.add_argument("variables", cond=lambda x: isinstance(x, list))
test_datasets.load_file(args.datasets)
test_datasets.build_model()
datasets_model = test_datasets.model
exp = Experiment(config_path=args.config)
exp.build_model()
exp.load_variables(datasets_model.variables)
ctc_decoder = None
for runner in exp.model.runners:
if (isinstance(runner, PlainRunner)
and isinstance(runner.decoder, CTCDecoder)):
ctc_decoder = runner.decoder
break
if ctc_decoder is None:
raise ValueError(
"Was not able to detect CTC decoder in the configuration.")
logits_runner = RepresentationRunner(output_series="logits",
encoder=ctc_decoder,
attribute="logits")
exp.model.runners = [logits_runner]
dataset = datasets_model.test_datasets[0]
singleton_batches = dataset.batches(BatchingScheme(1))
print("Loading language model")
lm = NGramModel(args.kenlm)
print("LM loaded")
weights = {}
if args.lm_weight:
weights['lm_score'] = args.lm_weight
if args.null_trail_weight:
weights['null_trailing'] = args.null_trail_weight
if args.nt_ratio_weight:
weights['null_token_ratio'] = args.nt_ratio_weight
print("Weights:", weights)
i = 0
stats = []
with open(args.out, 'w') as out_file:
for sent_dataset in singleton_batches:
t1 = timeit.default_timer()
ctc_model_result = exp.run_model(sent_dataset,
write_out=False,
batch_size=1)
t2 = timeit.default_timer()
logits = np.squeeze(ctc_model_result[1]['logits'], axis=1)
t3 = timeit.default_timer()
best_hyp = decode_beam(logits,
args.beam,
ctc_decoder.vocabulary,
lm=lm,
weights=weights)
t4 = timeit.default_timer()
stats.append([len(best_hyp.tokens), t2 - t1, t4 - t3])
output = " ".join([best_hyp.tokens][0])
out_file.write(output + "\n")
if i % 10 == 0:
print("[{}] {}".format(i, output))
i += 1
with open(args.out + ".stats", 'w') as stats_file:
for line in stats:
stats_file.write("{} {:.3f} {:.3f}\n".format(*line))
for session in exp.config.model.tf_manager.sessions:
session.close()
def main() -> None:
# pylint: disable=no-member,broad-except
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("config",
metavar="INI-FILE",
help="the configuration file of the experiment")
parser.add_argument('datasets',
metavar='INI-TEST-DATASETS',
help="the configuration of the test datasets")
parser.add_argument("-g",
"--grid",
dest="grid",
action="store_true",
help="look at the SGE variables for slicing the data")
args = parser.parse_args()
test_datasets = Configuration()
test_datasets.add_argument('test_datasets')
test_datasets.add_argument('variables')
CONFIG.load_file(args.config)
CONFIG.build_model()
test_datasets.load_file(args.datasets)
test_datasets.build_model()
datasets_model = test_datasets.model
initialize_for_running(CONFIG.model.output, CONFIG.model.tf_manager,
datasets_model.variables)
print("")
evaluators = [(e[0], e[0], e[1]) if len(e) == 2 else e
for e in CONFIG.model.evaluation]
if args.grid and len(datasets_model.test_datasets) > 1:
raise ValueError("Only one test dataset supported when using --grid")
for dataset in datasets_model.test_datasets:
if args.grid:
if ("SGE_TASK_FIRST" not in os.environ
or "SGE_TASK_LAST" not in os.environ
or "SGE_TASK_STEPSIZE" not in os.environ
or "SGE_TASK_ID" not in os.environ):
raise EnvironmentError(
"Some SGE environment variables are missing")
length = int(os.environ["SGE_TASK_STEPSIZE"])
start = int(os.environ["SGE_TASK_ID"]) - 1
end = int(os.environ["SGE_TASK_LAST"]) - 1
if start + length > end:
length = end - start + 1
log("Running grid task {} starting at {} with step {}".format(
start // length, start, length))
dataset = dataset.subset(start, length)
if CONFIG.model.runners_batch_size is None:
runners_batch_size = CONFIG.model.batch_size
else:
runners_batch_size = CONFIG.model.runners_batch_size
execution_results, output_data = run_on_dataset(
CONFIG.model.tf_manager,
CONFIG.model.runners,
dataset,
CONFIG.model.postprocess,
write_out=True,
batch_size=runners_batch_size,
log_progress=60)
# TODO what if there is no ground truth
eval_result = evaluation(evaluators, dataset, CONFIG.model.runners,
execution_results, output_data)
if eval_result:
print_final_evaluation(dataset.name, eval_result)
def main() -> None:
# pylint: disable=no-member,broad-except
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("config",
metavar="INI-FILE",
help="the configuration file of the experiment")
parser.add_argument("datasets",
metavar="INI-FILE",
help="the configuration file of the experiment")
parser.add_argument("--beam",
metavar="BEAM_SIZE",
type=int,
default=10,
help="Beam size.")
parser.add_argument("--kenlm",
type=str,
help="Path to a KenLM model arpa file.")
parser.add_argument("--prefix",
type=str,
help="Path used as a prefix of stored checkpoints.")
parser.add_argument("--lm-weight",
type=float,
help="Default weight of the language model.")
parser.add_argument("--null-trail-weight",
type=float,
help="Default weight of the null-trailing feature.")
parser.add_argument("--nt-ratio-weight",
type=float,
help="Default weight of the null-token ratio feature.")
args = parser.parse_args()
test_datasets = Configuration()
test_datasets.add_argument("test_datasets")
test_datasets.add_argument("batch_size", cond=lambda x: x > 0)
test_datasets.add_argument("variables", cond=lambda x: isinstance(x, list))
test_datasets.load_file(args.datasets)
test_datasets.build_model()
datasets_model = test_datasets.model
exp = Experiment(config_path=args.config)
exp.build_model()
exp.load_variables(datasets_model.variables)
weights = {}
if args.lm_weight is not None:
weights['lm_score'] = args.lm_weight
if args.null_trail_weight is not None:
weights['null_trailing'] = args.null_trail_weight
if args.nt_ratio_weight is not None:
weights['null_token_ratio'] = args.nt_ratio_weight
if not weights:
raise ValueError("No default weights specified, nothing to train.")
ctc_decoder = None
for runner in exp.model.runners:
if (isinstance(runner, PlainRunner)
and isinstance(runner.decoder, CTCDecoder)):
ctc_decoder = runner.decoder
break
if ctc_decoder is None:
raise ValueError(
"Was not able to detect CTC decoder in the configuration.")
print("Loading language model")
lm = NGramModel(args.kenlm)
print("LM loaded")
logits_runner = RepresentationRunner(output_series="logits",
encoder=ctc_decoder,
attribute="logits")
exp.model.runners = [logits_runner]
dataset = datasets_model.test_datasets[0]
singleton_batches = dataset.batches(BatchingScheme(1))
DATASET_SIZE = dataset.length
CHECKPOINTS = 5
CHECKPOINT_ITERS = int(DATASET_SIZE / CHECKPOINTS)
print(
"{} sentences in the dataset, checkpoint every {} sentences ({} checkpoints in total)."
.format(DATASET_SIZE, CHECKPOINT_ITERS, CHECKPOINTS))
for i, sent_dataset in enumerate(singleton_batches):
ctc_model_result = exp.run_model(sent_dataset,
write_out=False,
batch_size=1)
logits = np.squeeze(ctc_model_result[1]['logits'], axis=1)
target = ctc_model_result[2]['target'][0]
train_weights(logits, args.beam, ctc_decoder.vocabulary, target,
weights, lm)
print(
"[{}] Weights:".format(i + 1), ", ".join([
"{}: {:.3f}".format(key, value)
for key, value in weights.items()
]))
if i != 0 and (i + 1) % CHECKPOINT_ITERS == 0:
with open("{}.{}".format(args.prefix, int(i / CHECKPOINT_ITERS)),
"w") as f:
for key, value in weights.items():
f.write("{}={:.3f}\n".format(key.upper(), value))
print("\nCheckpoint saved.\n")
for session in exp.config.model.tf_manager.sessions:
session.close()