def configure_job():
"""Construct jobSpec for ML Engine job."""
# See documentation:
# https://cloud.google.com/ml-engine/reference/rest/v1/projects.jobs#traininginput
training_input = {
'pythonModule': 'tensor2tensor.bin.t2t_trainer',
'args': flags_as_args(),
'region': cloud.default_region(),
'runtimeVersion': '1.4',
'pythonVersion': '3.5' if sys.version_info.major == 3 else '2.7',
'jobDir': FLAGS.output_dir,
'scaleTier': 'CUSTOM',
'masterType': FLAGS.cloud_mlengine_master_type or get_default_master_type(
num_gpus=FLAGS.worker_gpu,
use_tpu=FLAGS.use_tpu)
}
if FLAGS.hparams_range:
tf.logging.info('Configuring hyperparameter tuning.')
training_input['hyperparameters'] = configure_autotune(
FLAGS.hparams_range,
FLAGS.autotune_objective,
FLAGS.autotune_maximize,
FLAGS.autotune_max_trials,
FLAGS.autotune_parallel_trials,
)
timestamp = datetime.datetime.now().strftime('%Y%m%d_%H%M%S')
job_name = '%s_%s_t2t_%s' % (FLAGS.model, FLAGS.problems, timestamp)
job_spec = {'jobId': job_name, 'trainingInput': training_input}
return job_spec
def configure_job():
"""Construct jobSpec for ML Engine job."""
# See documentation:
# https://cloud.google.com/ml-engine/reference/rest/v1/projects.jobs#traininginput
training_input = {
"pythonModule": "tensor2tensor.bin.t2t_trainer",
"args": flags_as_args(),
"region": text_encoder.native_to_unicode(cloud.default_region()),
"runtimeVersion": RUNTIME_VERSION,
"pythonVersion": "3.5" if sys.version_info.major == 3 else "2.7",
"jobDir": FLAGS.output_dir,
"scaleTier": "CUSTOM",
"masterType": FLAGS.cloud_mlengine_master_type or get_default_master_type(
num_gpus=FLAGS.worker_gpu)
}
if FLAGS.use_tpu:
training_input["masterType"] = (FLAGS.cloud_mlengine_master_type or
"standard")
training_input["workerType"] = "cloud_tpu"
training_input["workerCount"] = 1
if FLAGS.hparams_range:
tf.logging.info("Configuring hyperparameter tuning.")
training_input["hyperparameters"] = configure_autotune(
FLAGS.hparams_range,
FLAGS.autotune_objective,
FLAGS.autotune_maximize,
FLAGS.autotune_max_trials,
FLAGS.autotune_parallel_trials,
)
timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
job_name = "%s_%s_t2t_%s" % (FLAGS.model, FLAGS.problem, timestamp)
job_spec = {"jobId": job_name, "trainingInput": training_input}
return job_spec
def configure_job():
"""Construct jobSpec for ML Engine job."""
train_dir = FLAGS.output_dir
assert train_dir.startswith('gs://')
job_name = os.path.basename(train_dir)
# See documentation:
# https://cloud.google.com/ml-engine/reference/rest/v1/projects.jobs#traininginput
training_input = {
'pythonModule': 'tensor2tensor.bin.t2t_trainer',
'args': flags_as_args(),
'region': cloud.default_region(),
'runtimeVersion': '1.4',
'pythonVersion': '3.5' if sys.version_info.major == 3 else '2.7',
'jobDir': train_dir,
}
training_input.update(
machine_config(num_gpus=FLAGS.worker_gpu,
use_tpu=FLAGS.use_tpu,
master_type=FLAGS.cloud_mlengine_master_type))
if FLAGS.hparams_range:
assert FLAGS.autotune_objective
tf.logging.info('Configuring hyperparameter tuning.')
training_input['hyperparameters'] = configure_autotune(
FLAGS.hparams_range,
FLAGS.autotune_objective,
FLAGS.autotune_maximize,
FLAGS.autotune_max_trials,
FLAGS.autotune_parallel_trials,
)
if training_input['scaleTier'] == 'CUSTOM':
assert 'masterType' in training_input
job_spec = {'jobId': job_name, 'trainingInput': training_input}
return job_spec