def main(unused_argv):
# Get input data location from flags. If we're reading a TFDS dataset, get
# train, validation, and test.
input_filenames_list, output_filenames, sample_rate = audio_to_embeddings_beam_utils.read_input_glob_and_sample_rate_from_flags(
FLAGS.input_glob, FLAGS.sample_rate, FLAGS.tfds_dataset,
FLAGS.output_filename)
# Check that inputs and flags are formatted correctly.
audio_to_embeddings_beam_utils.validate_inputs(input_filenames_list,
output_filenames,
FLAGS.embedding_modules,
FLAGS.embedding_names,
FLAGS.module_output_keys)
logging.info('Starting to create flume pipeline...')
with beam.Pipeline() as root:
for i, (input_filenames, output_filename) in enumerate(
zip(input_filenames_list, output_filenames)):
audio_to_embeddings_beam_utils.make_beam_pipeline(
root,
input_filenames,
sample_rate,
FLAGS.debug,
FLAGS.embedding_names,
FLAGS.embedding_modules,
FLAGS.module_output_keys,
FLAGS.audio_key,
FLAGS.sample_rate_key,
FLAGS.label_key,
FLAGS.speaker_id_key,
FLAGS.average_over_time,
FLAGS.delete_audio_from_output,
output_filename,
suffix=i)
def main(unused_argv):
# Get input data location from flags. If we're reading a TFDS dataset, get
# train, validation, and test.
input_filenames_list, output_filenames, sample_rate = audio_to_embeddings_beam_utils.read_input_glob_and_sample_rate_from_flags(
FLAGS.input_glob, FLAGS.sample_rate, FLAGS.tfds_dataset,
FLAGS.output_filename, FLAGS.tfds_data_dir)
# Check that inputs and flags are formatted correctly.
audio_to_embeddings_beam_utils.validate_inputs(input_filenames_list,
output_filenames,
FLAGS.embedding_modules,
FLAGS.embedding_names,
FLAGS.module_output_keys)
input_format = 'tfrecord'
output_format = 'tfrecord'
# If you have custom beam options, add them here.
beam_options = None
logging.info('Starting to create flume pipeline...')
with beam.Pipeline(beam_options) as root:
for i, (input_filenames_or_glob, output_filename) in enumerate(
zip(input_filenames_list, output_filenames)):
audio_to_embeddings_beam_utils.make_beam_pipeline(
root,
input_filenames_or_glob,
sample_rate,
FLAGS.debug,
FLAGS.embedding_names,
FLAGS.embedding_modules,
FLAGS.module_output_keys,
FLAGS.audio_key,
FLAGS.sample_rate_key,
FLAGS.label_key,
FLAGS.speaker_id_key,
FLAGS.average_over_time,
FLAGS.delete_audio_from_output,
output_filename,
split_embeddings_into_separate_tables=FLAGS.
split_embeddings_into_separate_tables, # pylint:disable=line-too-long
use_frontend_fn=FLAGS.use_frontend_fn,
model_input_min_length=FLAGS.model_input_min_length,
input_format=input_format,
output_format=output_format,
suffix=i)
def main(unused_argv):
# Get input data location fromm flags.
input_filenames, sample_rate = audio_to_embeddings_beam_utils.read_input_glob_and_sample_rate_from_flags(
FLAGS.input_glob, FLAGS.sample_rate, FLAGS.tfds_dataset)
# Check that flags are formatted correctly.
audio_to_embeddings_beam_utils.validate_inputs(
FLAGS.output_filename, FLAGS.embedding_modules,
FLAGS.embedding_names, FLAGS.module_output_keys)
logging.info('Starting to create flume pipeline...')
with beam.Pipeline() as root:
audio_to_embeddings_beam_utils.make_beam_pipeline(
root, input_filenames, sample_rate, FLAGS.debug, FLAGS.embedding_names,
FLAGS.embedding_modules, FLAGS.module_output_keys, FLAGS.audio_key,
FLAGS.sample_rate_key, FLAGS.label_key, FLAGS.speaker_id_key,
FLAGS.average_over_time, FLAGS.delete_audio_from_output,
FLAGS.output_filename)
def main(_):
input_filenames_list, output_filenames, beam_params = utils.get_beam_params_from_flags(
)
# Check that inputs and flags are formatted correctly.
utils.validate_inputs(input_filenames_list=input_filenames_list,
output_filenames=output_filenames,
embedding_modules=beam_params['embedding_modules'],
embedding_names=beam_params['embedding_names'],
module_output_keys=beam_params['module_output_keys'])
# If you have custom beam options, add them here.
beam_options = None
logging.info('Starting to create flume pipeline...')
with beam.Pipeline(beam_options) as root:
for i, (input_filenames_or_glob, output_filename) in enumerate(
zip(input_filenames_list, output_filenames)):
utils.make_beam_pipeline(root,
input_filenames=input_filenames_or_glob,
output_filename=output_filename,
suffix=str(i),
**beam_params)
def main(unused_argv):
# Data prep setup.
run_data_prep = True
if FLAGS.train_input_glob:
assert FLAGS.validation_input_glob
assert FLAGS.test_input_glob
input_filenames_list, output_filenames = [], []
for input_glob in [
FLAGS.train_input_glob, FLAGS.validation_input_glob,
FLAGS.test_input_glob,
]:
FLAGS.input_glob = input_glob
cur_inputs, cur_outputs, beam_params = data_prep_utils.get_beam_params_from_flags(
)
input_filenames_list.extend(cur_inputs)
output_filenames.extend(cur_outputs)
else:
input_filenames_list, output_filenames, beam_params = data_prep_utils.get_beam_params_from_flags(
)
assert input_filenames_list, input_filenames_list
assert output_filenames, output_filenames
try:
# Check that inputs and flags are formatted correctly.
data_prep_utils.validate_inputs(
input_filenames_list, output_filenames,
beam_params['embedding_modules'], beam_params['embedding_names'],
beam_params['module_output_keys'])
except ValueError:
if FLAGS.skip_existing_error:
run_data_prep = False
else:
raise
logging.info('beam_params: %s', beam_params)
# Generate sklearn eval experiment parameters based on data prep flags.
if len(output_filenames) != 3:
raise ValueError(f'Data prep output must be 3 files: {output_filenames}')
# Make them globs.
train_glob, eval_glob, test_glob = [f'{x}*' for x in output_filenames]
sklearn_results_output_file = FLAGS.results_output_file
exp_params = sklearn_utils.experiment_params(
embedding_list=beam_params['embedding_names'],
speaker_id_name=FLAGS.speaker_id_key,
label_name=FLAGS.label_key,
label_list=FLAGS.label_list,
train_glob=train_glob,
eval_glob=eval_glob,
test_glob=test_glob,
save_model_dir=None,
save_predictions_dir=None,
eval_metric=FLAGS.eval_metric,
)
logging.info('exp_params: %s', exp_params)
# Make and run beam pipeline.
beam_options = None
if run_data_prep:
logging.info('Data prep on: %s, %s...', input_filenames_list,
output_filenames)
with beam.Pipeline(beam_options) as root:
for i, (input_filenames_or_glob, output_filename) in enumerate(
zip(input_filenames_list, output_filenames)):
data_prep_utils.make_beam_pipeline(
root,
input_filenames=input_filenames_or_glob,
output_filename=output_filename,
suffix=str(i),
**beam_params)
# Check that previous beam pipeline wrote outputs.
sklearn_utils.validate_flags(train_glob, eval_glob, test_glob,
sklearn_results_output_file)
logging.info('Eval sklearn...')
with beam.Pipeline(beam_options) as root:
_ = (
root
| 'MakeCollection' >> beam.Create(exp_params)
| 'CalcScores' >> beam.Map(
lambda d: (d, sklearn_utils.train_and_get_score(**d)))
| 'FormatText' >> beam.Map(sklearn_utils.format_text_line)
| 'Reshuffle' >> beam.Reshuffle()
| 'WriteOutput' >> beam.io.WriteToText(
sklearn_results_output_file, num_shards=1))
