def test_parse_model_metadata_exception():
"""This function tests the functionality of parse_model_metadata function
in utils_parse_model_metadata.py when an exception occurs
"""
with pytest.raises(Exception, match=r".*Model metadata does not exist:.*"):
sensor, network, simapp_version = parse_model_metadata(
"dummy_file.json")
def test_parse_model_metadata(create_model_metadata):
"""This function tests the functionality of parse_model_metadata function
in utils_parse_model_metadata.py when we pass a model metadata file with
sensor and neural network information
Args:
create_model_metadata (String): Gives the path for model metadata file for testing
"""
sensor, network, simapp_version = parse_model_metadata(
create_model_metadata)
os.remove(create_model_metadata)
assert sensor == ["STEREO_CAMERAS"]
assert network == "DEEP_CONVOLUTIONAL_NETWORK_SHALLOW"
assert simapp_version == SIMAPP_VERSION
def test_parse_model_metadata_only_action(create_model_metadata_action_space):
"""This function tests the functionality of parse_model_metadata function
in utils_parse_model_metadata.py when we pass a model metadata file with only
action space and no sensor or neural network information.
Args:
create_model_metadata_action_space (String): Gives the path for model metadata file for testing
"""
sensor, network, simapp_version = parse_model_metadata(
create_model_metadata_action_space)
os.remove(create_model_metadata_action_space)
assert sensor == [Input.OBSERVATION.value]
assert network == NeuralNetwork.DEEP_CONVOLUTIONAL_NETWORK_SHALLOW.value
assert simapp_version == "1.0"
def create_training_agent(agent_config):
'''Returns an training agent object
agent_config - Dictionary containing the key specified in ConfigParams
'''
model_metadata = agent_config['model_metadata']
observation_list, network, _ = utils_parse_model_metadata.parse_model_metadata(model_metadata)
sensor = construct_sensor(observation_list, SensorFactory)
network_settings = get_network_settings(sensor, network)
sensor = construct_sensor(observation_list, SensorFactory)
ctrl_config = agent_config['car_ctrl_cnfig']
ctrl = TrainingCtrl(ctrl_config[ConfigParams.AGENT_NAME.value],
ctrl_config[ConfigParams.ACTION_SPACE_PATH.value])
return Agent(network_settings, sensor, ctrl, None)
def create_rollout_agent(agent_config, metrics):
'''Returns an rollout agent object
agent_config - Dictionary containing the key specified in ConfigParams
metrics - Metrics object for the agent
'''
model_metadata = agent_config['model_metadata']
observation_list, network, _ = utils_parse_model_metadata.parse_model_metadata(
model_metadata)
sensor = construct_sensor(observation_list, SensorFactory)
network_settings = get_network_settings(sensor, network)
frustum = Frustum.get_instance()
frustum.add_cameras(observation_list)
ctrl_config = agent_config['car_ctrl_cnfig']
ctrl = RolloutCtrl(ctrl_config)
return Agent(network_settings, sensor, ctrl, metrics)
def create_rollout_agent(agent_config, metrics, run_phase_subject):
'''Returns an rollout agent object
agent_config - Dictionary containing the key specified in ConfigParams
metrics - Metrics object for the agent
run_phase_subject - Subject that notifies observers when the run phase changes
'''
model_metadata = agent_config['model_metadata']
observation_list, network, _ = utils_parse_model_metadata.parse_model_metadata(
model_metadata)
agent_name = agent_config[ConfigParams.CAR_CTRL_CONFIG.value][
ConfigParams.AGENT_NAME.value]
sensor = construct_sensor(agent_name, observation_list, SensorFactory)
network_settings = get_network_settings(sensor, network)
FrustumManager.get_instance().add(agent_name=agent_name,
observation_list=observation_list)
ctrl_config = agent_config[ConfigParams.CAR_CTRL_CONFIG.value]
ctrl = RolloutCtrl(ctrl_config, run_phase_subject, metrics)
return Agent(network_settings, sensor, ctrl)
def main():
screen.set_use_colors(False)
logger.info("src/training_worker.py - INIZIO MAIN")
parser = argparse.ArgumentParser()
parser.add_argument('-pk',
'--preset_s3_key',
help="(string) Name of a preset to download from S3",
type=str,
required=False)
parser.add_argument(
'-ek',
'--environment_s3_key',
help="(string) Name of an environment file to download from S3",
type=str,
required=False)
parser.add_argument('--model_metadata_s3_key',
help="(string) Model Metadata File S3 Key",
type=str,
required=False)
parser.add_argument(
'-c',
'--checkpoint-dir',
help=
'(string) Path to a folder containing a checkpoint to write the model to.',
type=str,
default='./checkpoint')
parser.add_argument(
'--pretrained-checkpoint-dir',
help='(string) Path to a folder for downloading a pre-trained model',
type=str,
default=PRETRAINED_MODEL_DIR)
parser.add_argument('--s3_bucket',
help='(string) S3 bucket',
type=str,
default=os.environ.get(
"SAGEMAKER_SHARED_S3_BUCKET_PATH", "gsaur-test"))
parser.add_argument('--s3_prefix',
help='(string) S3 prefix',
type=str,
default='sagemaker')
parser.add_argument('--s3_endpoint_url',
help='(string) S3 endpoint URL',
type=str,
default=os.environ.get("S3_ENDPOINT_URL", None))
parser.add_argument('--framework',
help='(string) tensorflow or mxnet',
type=str,
default='tensorflow')
parser.add_argument('--pretrained_s3_bucket',
help='(string) S3 bucket for pre-trained model',
type=str)
parser.add_argument('--pretrained_s3_prefix',
help='(string) S3 prefix for pre-trained model',
type=str,
default='sagemaker')
parser.add_argument('--aws_region',
help='(string) AWS region',
type=str,
default=os.environ.get("AWS_REGION", "us-east-1"))
args, _ = parser.parse_known_args()
logger.info("S3 bucket: %s \n S3 prefix: %s \n S3 endpoint URL: %s",
args.s3_bucket, args.s3_prefix, args.s3_endpoint_url)
s3_client = SageS3Client(bucket=args.s3_bucket,
s3_prefix=args.s3_prefix,
aws_region=args.aws_region,
s3_endpoint_url=args.s3_endpoint_url)
# Load the model metadata
model_metadata_local_path = os.path.join(CUSTOM_FILES_PATH,
'model_metadata.json')
utils.load_model_metadata(s3_client, args.model_metadata_s3_key,
model_metadata_local_path)
s3_client.upload_file(
os.path.normpath("%s/model/model_metadata.json" % args.s3_prefix),
model_metadata_local_path)
shutil.copy2(model_metadata_local_path, SM_MODEL_OUTPUT_DIR)
success_custom_preset = False
if args.preset_s3_key:
preset_local_path = "./markov/presets/preset.py"
success_custom_preset = s3_client.download_file(
s3_key=args.preset_s3_key, local_path=preset_local_path)
if not success_custom_preset:
logger.info(
"Could not download the preset file. Using the default DeepRacer preset."
)
else:
preset_location = "markov.presets.preset:graph_manager"
graph_manager = short_dynamic_import(preset_location,
ignore_module_case=True)
success_custom_preset = s3_client.upload_file(
s3_key=os.path.normpath("%s/presets/preset.py" %
args.s3_prefix),
local_path=preset_local_path)
if success_custom_preset:
logger.info("Using preset: %s" % args.preset_s3_key)
if not success_custom_preset:
params_blob = os.environ.get('SM_TRAINING_ENV', '')
if params_blob:
params = json.loads(params_blob)
sm_hyperparams_dict = params["hyperparameters"]
else:
sm_hyperparams_dict = {}
#configurazione agente: metadati del modello impostati dall'utente (angolo di sterzo + velocità) + nome
#! TODO each agent should have own config
agent_config = {
'model_metadata': model_metadata_local_path,
ConfigParams.CAR_CTRL_CONFIG.value: {
ConfigParams.LINK_NAME_LIST.value: [],
ConfigParams.VELOCITY_LIST.value: {},
ConfigParams.STEERING_LIST.value: {},
ConfigParams.CHANGE_START.value: None,
ConfigParams.ALT_DIR.value: None,
ConfigParams.ACTION_SPACE_PATH.value:
'custom_files/model_metadata.json',
ConfigParams.REWARD.value: None,
ConfigParams.AGENT_NAME.value: 'racecar'
}
}
agent_list = list()
agent_list.append(create_training_agent(agent_config))
logger.info(
"src/training_worker.py - ora chiamo la get_graph_manager, che recupera l'agente"
)
graph_manager, robomaker_hyperparams_json = get_graph_manager(
hp_dict=sm_hyperparams_dict,
agent_list=agent_list,
run_phase_subject=None)
logger.info("src/training_worker.py - ho l'agente")
s3_client.upload_hyperparameters(robomaker_hyperparams_json)
logger.info("Uploaded hyperparameters.json to S3")
# Attach sample collector to graph_manager only if sample count > 0
max_sample_count = int(sm_hyperparams_dict.get("max_sample_count", 0))
if max_sample_count > 0:
sample_collector = SampleCollector(
s3_client=s3_client,
s3_prefix=args.s3_prefix,
max_sample_count=max_sample_count,
sampling_frequency=int(
sm_hyperparams_dict.get("sampling_frequency", 1)))
graph_manager.sample_collector = sample_collector
host_ip_address = utils.get_ip_from_host()
s3_client.write_ip_config(host_ip_address)
logger.info("Uploaded IP address information to S3: %s" % host_ip_address)
use_pretrained_model = args.pretrained_s3_bucket and args.pretrained_s3_prefix
# Handle backward compatibility
_, network_type, version = parse_model_metadata(model_metadata_local_path)
if use_pretrained_model:
if float(version) < float(SIMAPP_VERSION) and \
not utils.has_current_ckpnt_name(args.pretrained_s3_bucket, args.pretrained_s3_prefix, args.aws_region, args.s3_endpoint_url):
utils.make_compatible(args.pretrained_s3_bucket,
args.pretrained_s3_prefix, args.aws_region,
SyncFiles.TRAINER_READY.value)
#Select the optimal model for the starting weights
utils.do_model_selection(s3_bucket=args.s3_bucket,
s3_prefix=args.s3_prefix,
region=args.aws_region,
s3_endpoint_url=args.s3_endpoint_url)
ds_params_instance_pretrained = S3BotoDataStoreParameters(
aws_region=args.aws_region,
bucket_names={'agent': args.pretrained_s3_bucket},
base_checkpoint_dir=args.pretrained_checkpoint_dir,
s3_folders={'agent': args.pretrained_s3_prefix},
s3_endpoint_url=args.s3_endpoint_url)
data_store_pretrained = S3BotoDataStore(ds_params_instance_pretrained,
graph_manager, True)
data_store_pretrained.load_from_store()
memory_backend_params = DeepRacerRedisPubSubMemoryBackendParameters(
redis_address="localhost",
redis_port=6379,
run_type=str(RunType.TRAINER),
channel=args.s3_prefix,
network_type=network_type)
graph_manager.memory_backend_params = memory_backend_params
ds_params_instance = S3BotoDataStoreParameters(
aws_region=args.aws_region,
bucket_names={'agent': args.s3_bucket},
base_checkpoint_dir=args.checkpoint_dir,
s3_folders={'agent': args.s3_prefix},
s3_endpoint_url=args.s3_endpoint_url)
graph_manager.data_store_params = ds_params_instance
graph_manager.data_store = S3BotoDataStore(ds_params_instance,
graph_manager)
task_parameters = TaskParameters()
task_parameters.experiment_path = SM_MODEL_OUTPUT_DIR
task_parameters.checkpoint_save_secs = 20
if use_pretrained_model:
task_parameters.checkpoint_restore_path = args.pretrained_checkpoint_dir
task_parameters.checkpoint_save_dir = args.checkpoint_dir
#funzione riga 48
#prende in input:
# - il grafo (creato con la get_graph_manager)
# - robomaker_hyperparams_json (ritornato dalla get_graph_manager)
training_worker(
graph_manager=graph_manager,
task_parameters=task_parameters,
user_batch_size=json.loads(robomaker_hyperparams_json)["batch_size"],
user_episode_per_rollout=json.loads(
robomaker_hyperparams_json)["num_episodes_between_training"])
def main():
screen.set_use_colors(False)
parser = argparse.ArgumentParser()
parser.add_argument('-pk', '--preset_s3_key',
help="(string) Name of a preset to download from S3",
type=str,
required=False)
parser.add_argument('-ek', '--environment_s3_key',
help="(string) Name of an environment file to download from S3",
type=str,
required=False)
parser.add_argument('--model_metadata_s3_key',
help="(string) Model Metadata File S3 Key",
type=str,
required=False)
parser.add_argument('-c', '--checkpoint-dir',
help='(string) Path to a folder containing a checkpoint to write the model to.',
type=str,
default='./checkpoint')
parser.add_argument('--pretrained-checkpoint-dir',
help='(string) Path to a folder for downloading a pre-trained model',
type=str,
default=PRETRAINED_MODEL_DIR)
parser.add_argument('--s3_bucket',
help='(string) S3 bucket',
type=str,
default=os.environ.get("SAGEMAKER_SHARED_S3_BUCKET_PATH", "gsaur-test"))
parser.add_argument('--s3_prefix',
help='(string) S3 prefix',
type=str,
default='sagemaker')
parser.add_argument('--framework',
help='(string) tensorflow or mxnet',
type=str,
default='tensorflow')
parser.add_argument('--pretrained_s3_bucket',
help='(string) S3 bucket for pre-trained model',
type=str)
parser.add_argument('--pretrained_s3_prefix',
help='(string) S3 prefix for pre-trained model',
type=str,
default='sagemaker')
parser.add_argument('--aws_region',
help='(string) AWS region',
type=str,
default=os.environ.get("AWS_REGION", "us-east-1"))
start_redis_server()
args, _ = parser.parse_known_args()
s3_client = SageS3Client(bucket=args.s3_bucket, s3_prefix=args.s3_prefix, aws_region=args.aws_region)
# Load the model metadata
model_metadata_local_path = os.path.join(CUSTOM_FILES_PATH, 'model_metadata.json')
utils.load_model_metadata(s3_client, args.model_metadata_s3_key, model_metadata_local_path)
s3_client.upload_file(os.path.normpath("%s/model/model_metadata.json" % args.s3_prefix), model_metadata_local_path)
shutil.copy2(model_metadata_local_path, SM_MODEL_OUTPUT_DIR)
success_custom_preset = False
if args.preset_s3_key:
preset_local_path = "./markov/presets/preset.py"
success_custom_preset = s3_client.download_file(s3_key=args.preset_s3_key, local_path=preset_local_path)
if not success_custom_preset:
logger.info("Could not download the preset file. Using the default DeepRacer preset.")
else:
preset_location = "markov.presets.preset:graph_manager"
graph_manager = short_dynamic_import(preset_location, ignore_module_case=True)
success_custom_preset = s3_client.upload_file(
s3_key=os.path.normpath("%s/presets/preset.py" % args.s3_prefix), local_path=preset_local_path)
if success_custom_preset:
logger.info("Using preset: %s" % args.preset_s3_key)
if not success_custom_preset:
params_blob = os.environ.get('SM_TRAINING_ENV', '')
if params_blob:
params = json.loads(params_blob)
sm_hyperparams_dict = params["hyperparameters"]
else:
sm_hyperparams_dict = {}
#! TODO each agent should have own config
agent_config = {'model_metadata': model_metadata_local_path,
'car_ctrl_cnfig': {ConfigParams.LINK_NAME_LIST.value: [],
ConfigParams.VELOCITY_LIST.value : {},
ConfigParams.STEERING_LIST.value : {},
ConfigParams.CHANGE_START.value : None,
ConfigParams.ALT_DIR.value : None,
ConfigParams.ACTION_SPACE_PATH.value : 'custom_files/model_metadata.json',
ConfigParams.REWARD.value : None,
ConfigParams.AGENT_NAME.value : 'racecar'}}
agent_list = list()
agent_list.append(create_training_agent(agent_config))
#agent_list.append(create_training_agent(agent_config))
graph_manager, robomaker_hyperparams_json = get_graph_manager(sm_hyperparams_dict, agent_list)
s3_client.upload_hyperparameters(robomaker_hyperparams_json)
logger.info("Uploaded hyperparameters.json to S3")
host_ip_address = utils.get_ip_from_host()
s3_client.write_ip_config(host_ip_address)
logger.info("Uploaded IP address information to S3: %s" % host_ip_address)
use_pretrained_model = args.pretrained_s3_bucket and args.pretrained_s3_prefix
if use_pretrained_model:
# Handle backward compatibility
_, _, version = parse_model_metadata(model_metadata_local_path)
if float(version) < float(utils.SIMAPP_VERSION) and \
not utils.has_current_ckpnt_name(args.pretrained_s3_bucket, args.pretrained_s3_prefix, args.aws_region):
utils.make_compatible(args.pretrained_s3_bucket, args.pretrained_s3_prefix,
args.aws_region, SyncFiles.TRAINER_READY.value)
ds_params_instance_pretrained = S3BotoDataStoreParameters(aws_region=args.aws_region,
bucket_name=args.pretrained_s3_bucket,
checkpoint_dir=args.pretrained_checkpoint_dir,
s3_folder=args.pretrained_s3_prefix)
data_store_pretrained = S3BotoDataStore(ds_params_instance_pretrained)
data_store_pretrained.load_from_store()
memory_backend_params = RedisPubSubMemoryBackendParameters(redis_address="localhost",
redis_port=6379,
run_type=str(RunType.TRAINER),
channel=args.s3_prefix)
graph_manager.memory_backend_params = memory_backend_params
ds_params_instance = S3BotoDataStoreParameters(aws_region=args.aws_region,
bucket_name=args.s3_bucket,
checkpoint_dir=args.checkpoint_dir,
s3_folder=args.s3_prefix)
graph_manager.data_store_params = ds_params_instance
data_store = S3BotoDataStore(ds_params_instance)
data_store.graph_manager = graph_manager
graph_manager.data_store = data_store
task_parameters = TaskParameters()
task_parameters.experiment_path = SM_MODEL_OUTPUT_DIR
task_parameters.checkpoint_save_secs = 20
if use_pretrained_model:
task_parameters.checkpoint_restore_path = args.pretrained_checkpoint_dir
task_parameters.checkpoint_save_dir = args.checkpoint_dir
training_worker(
graph_manager=graph_manager,
task_parameters=task_parameters,
user_batch_size=json.loads(robomaker_hyperparams_json)["batch_size"],
user_episode_per_rollout=json.loads(robomaker_hyperparams_json)["num_episodes_between_training"]
)
def validate(s3_bucket, s3_prefix, custom_files_path, aws_region):
screen.set_use_colors(False)
logger.info("S3 bucket: %s \n S3 prefix: %s", s3_bucket, s3_prefix)
if not os.path.exists(custom_files_path):
os.makedirs(custom_files_path)
else:
GenericValidatorException(
"Custom Files Path already exists!").log_except_and_exit()
s3_client = SageS3Client(bucket=s3_bucket,
s3_prefix=s3_prefix,
aws_region=aws_region)
# Load the model metadata
model_metadata_local_path = os.path.join(custom_files_path,
'model_metadata.json')
utils.load_model_metadata(
s3_client,
os.path.normpath("%s/model/model_metadata.json" % s3_prefix),
model_metadata_local_path)
# Create model local path
local_model_dir = os.path.join(custom_files_path, 'checkpoint')
os.makedirs(local_model_dir)
try:
# Handle backward compatibility
observation_list, _, version = parse_model_metadata(
model_metadata_local_path)
except Exception as ex:
log_and_exit("Failed to parse model_metadata file: {}".format(ex),
SIMAPP_VALIDATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_400)
transitions = get_transition_data(observation_list)
if float(version) < float(SIMAPP_VERSION) and \
not utils.has_current_ckpnt_name(s3_bucket, s3_prefix, aws_region):
utils.make_compatible(s3_bucket, s3_prefix, aws_region,
SyncFiles.TRAINER_READY.value)
agent_config = {
'model_metadata': model_metadata_local_path,
ConfigParams.CAR_CTRL_CONFIG.value: {
ConfigParams.LINK_NAME_LIST.value: [],
ConfigParams.VELOCITY_LIST.value: {},
ConfigParams.STEERING_LIST.value: {},
ConfigParams.CHANGE_START.value: None,
ConfigParams.ALT_DIR.value: None,
ConfigParams.ACTION_SPACE_PATH.value: model_metadata_local_path,
ConfigParams.REWARD.value: None,
ConfigParams.AGENT_NAME.value: 'racecar'
}
}
agent_list = list()
agent_list.append(create_training_agent(agent_config))
sm_hyperparams_dict = {}
graph_manager, _ = get_graph_manager(hp_dict=sm_hyperparams_dict,
agent_list=agent_list,
run_phase_subject=None)
ds_params_instance = S3BotoDataStoreParameters(
aws_region=aws_region,
bucket_names={'agent': s3_bucket},
s3_folders={'agent': s3_prefix},
base_checkpoint_dir=local_model_dir)
graph_manager.data_store = S3BotoDataStore(ds_params_instance,
graph_manager,
ignore_lock=True)
task_parameters = TaskParameters()
task_parameters.checkpoint_restore_path = local_model_dir
_validate(graph_manager=graph_manager,
task_parameters=task_parameters,
transitions=transitions,
s3_bucket=s3_bucket,
s3_prefix=s3_prefix,
aws_region=aws_region)
def main():
""" Main function for tournament"""
try:
# parse argument
s3_region = sys.argv[1]
s3_bucket = sys.argv[2]
s3_prefix = sys.argv[3]
s3_yaml_name = sys.argv[4]
# create boto3 session/client and download yaml/json file
session = boto3.session.Session()
s3_endpoint_url = os.environ.get("S3_ENDPOINT_URL", None)
s3_client = session.client('s3',
region_name=s3_region,
endpoint_url=s3_endpoint_url,
config=get_boto_config())
yaml_key = os.path.normpath(os.path.join(s3_prefix, s3_yaml_name))
local_yaml_path = os.path.abspath(
os.path.join(os.getcwd(), s3_yaml_name))
s3_client.download_file(Bucket=s3_bucket,
Key=yaml_key,
Filename=local_yaml_path)
# Intermediate tournament files
queue_pickle_name = 'tournament_candidate_queue.pkl'
queue_pickle_s3_key = os.path.normpath(
os.path.join(s3_prefix, queue_pickle_name))
local_queue_pickle_path = os.path.abspath(
os.path.join(os.getcwd(), queue_pickle_name))
report_pickle_name = 'tournament_report.pkl'
report_pickle_s3_key = os.path.normpath(
os.path.join(s3_prefix, report_pickle_name))
local_report_pickle_path = os.path.abspath(
os.path.join(os.getcwd(), report_pickle_name))
final_report_name = 'tournament_report.json'
final_report_s3_key = os.path.normpath(
os.path.join(s3_prefix, final_report_name))
try:
s3_client.download_file(Bucket=s3_bucket,
Key=queue_pickle_s3_key,
Filename=local_queue_pickle_path)
s3_client.download_file(Bucket=s3_bucket,
Key=report_pickle_s3_key,
Filename=local_report_pickle_path)
except:
pass
# Get values passed in yaml files. Default values are for backward compatibility and for single racecar racing
yaml_dict = get_yaml_dict(local_yaml_path)
# Forcing the yaml parameter to list
force_list_params = [
MODEL_S3_BUCKET_YAML_KEY, MODEL_S3_PREFIX_YAML_KEY,
MODEL_METADATA_FILE_S3_YAML_KEY, METRICS_S3_BUCKET_YAML_KEY,
METRICS_S3_PREFIX_YAML_KEY, SIMTRACE_S3_BUCKET_YAML_KEY,
SIMTRACE_S3_PREFIX_YAML_KEY, MP4_S3_BUCKET_YAML_KEY,
MP4_S3_PREFIX_YAML_KEY, DISPLAY_NAME_YAML_KEY
]
for params in force_list_params:
yaml_dict[params] = force_list(yaml_dict.get(params, None))
# Populate the model_metadata_s3_key values to handle both training and evaluation for all race_formats
if None in yaml_dict[MODEL_METADATA_FILE_S3_YAML_KEY]:
# MODEL_METADATA_FILE_S3_KEY not passed as part of yaml file ==> This happens during evaluation
# Assume model_metadata.json is present in the s3_prefix/model/ folder
yaml_dict[MODEL_METADATA_FILE_S3_YAML_KEY] = list()
for s3_prefix in yaml_dict[MODEL_S3_PREFIX_YAML_KEY]:
yaml_dict[MODEL_METADATA_FILE_S3_YAML_KEY].append(
os.path.join(s3_prefix, 'model/model_metadata.json'))
# Validate the yaml values
validate_yaml_values(yaml_dict)
if os.path.exists(local_queue_pickle_path):
with open(local_queue_pickle_path, 'rb') as f:
tournament_candidate_queue = pickle.load(f)
with open(local_report_pickle_path, 'rb') as f:
tournament_report = pickle.load(f)
logger.info('tournament_candidate_queue loaded from existing file')
else:
logger.info('tournament_candidate_queue initialized')
tournament_candidate_queue = deque()
for agent_idx, _ in enumerate(yaml_dict[MODEL_S3_BUCKET_YAML_KEY]):
tournament_candidate_queue.append(
(yaml_dict[MODEL_S3_BUCKET_YAML_KEY][agent_idx],
yaml_dict[MODEL_S3_PREFIX_YAML_KEY][agent_idx],
yaml_dict[MODEL_METADATA_FILE_S3_YAML_KEY][agent_idx],
yaml_dict[METRICS_S3_BUCKET_YAML_KEY][agent_idx],
yaml_dict[METRICS_S3_PREFIX_YAML_KEY][agent_idx],
yaml_dict[SIMTRACE_S3_BUCKET_YAML_KEY][agent_idx],
yaml_dict[SIMTRACE_S3_PREFIX_YAML_KEY][agent_idx],
yaml_dict[MP4_S3_BUCKET_YAML_KEY][agent_idx],
yaml_dict[MP4_S3_PREFIX_YAML_KEY][agent_idx],
yaml_dict[DISPLAY_NAME_YAML_KEY][agent_idx]))
tournament_report = []
race_idx = len(tournament_report)
while len(tournament_candidate_queue) > 1:
car1 = tournament_candidate_queue.popleft()
car2 = tournament_candidate_queue.popleft()
(car1_model_s3_bucket, car1_s3_prefix, car1_model_metadata,
car1_metrics_bucket, car1_metrics_s3_key, car1_simtrace_bucket,
car1_simtrace_prefix, car1_mp4_bucket, car1_mp4_prefix,
car1_display_name) = car1
(car2_model_s3_bucket, car2_s3_prefix, car2_model_metadata,
car2_metrics_bucket, car2_metrics_s3_key, car2_simtrace_bucket,
car2_simtrace_prefix, car2_mp4_bucket, car2_mp4_prefix,
car2_display_name) = car2
race_yaml_dict = generate_race_yaml(yaml_dict=yaml_dict,
car1=car1,
car2=car2,
race_idx=race_idx)
race_car_colors = ["Orange", "Purple"]
race_model_s3_buckets = [
car1_model_s3_bucket, car2_model_s3_bucket
]
race_model_metadatas = [car1_model_metadata, car2_model_metadata]
# List of directories created
dirs_to_delete = list()
yaml_dir = os.path.abspath(os.path.join(os.getcwd(),
str(race_idx)))
os.makedirs(yaml_dir)
dirs_to_delete.append(yaml_dir)
race_yaml_path = os.path.abspath(
os.path.join(yaml_dir, 'evaluation_params.yaml'))
with open(race_yaml_path, 'w') as race_yaml_file:
yaml.dump(race_yaml_dict, race_yaml_file)
# List of racecar names that should include second camera while launching
racecars_with_stereo_cameras = list()
# List of racecar names that should include lidar while launching
racecars_with_lidars = list()
# List of SimApp versions
simapp_versions = list()
for agent_index, model_s3_bucket in enumerate(
race_model_s3_buckets):
racecar_name = 'racecar_' + str(agent_index)
# Make a local folder with the racecar name to download the model_metadata.json
os.makedirs(os.path.join(os.getcwd(), racecar_name))
dirs_to_delete.append(os.path.join(os.getcwd(), racecar_name))
local_model_metadata_path = os.path.abspath(
os.path.join(os.path.join(os.getcwd(), racecar_name),
'model_metadata.json'))
json_key = race_model_metadatas[agent_index]
json_key = json_key.replace('s3://{}/'.format(model_s3_bucket),
'')
s3_client.download_file(Bucket=model_s3_bucket,
Key=json_key,
Filename=local_model_metadata_path)
sensors, _, simapp_version = utils_parse_model_metadata.parse_model_metadata(
local_model_metadata_path)
simapp_versions.append(simapp_version)
if Input.STEREO.value in sensors:
racecars_with_stereo_cameras.append(racecar_name)
if Input.LIDAR.value in sensors or Input.SECTOR_LIDAR.value in sensors:
racecars_with_lidars.append(racecar_name)
cmd = [
os.path.join(os.path.dirname(os.path.abspath(__file__)),
"tournament_race_node.py"),
str(race_idx), race_yaml_path,
','.join(racecars_with_stereo_cameras),
','.join(racecars_with_lidars), ','.join(race_car_colors),
','.join(simapp_versions)
]
try:
return_code, _, stderr = run_cmd(cmd_args=cmd,
shell=False,
stdout=None,
stderr=None)
except KeyboardInterrupt:
logger.info(
"KeyboardInterrupt raised, SimApp must be faulted! exiting..."
)
return
# Retrieve winner and append tournament report
with open('race_report.pkl', 'rb') as f:
race_report = pickle.load(f)
race_report['race_idx'] = race_idx
winner = car1 if race_report[
'winner'] == car1_display_name else car2
logger.info("race {}'s winner: {}".format(race_idx,
race_report['winner']))
tournament_candidate_queue.append(winner)
tournament_report.append(race_report)
# Clean up directories created
for dir_to_delete in dirs_to_delete:
shutil.rmtree(dir_to_delete, ignore_errors=True)
race_idx += 1
# Persist latest queue and report to use after job restarts.
with open(local_queue_pickle_path, 'wb') as f:
pickle.dump(tournament_candidate_queue, f, protocol=2)
s3_client.upload_file(Filename=local_queue_pickle_path,
Bucket=s3_bucket,
Key=queue_pickle_s3_key)
with open(local_report_pickle_path, 'wb') as f:
pickle.dump(tournament_report, f, protocol=2)
s3_client.upload_file(Filename=local_report_pickle_path,
Bucket=s3_bucket,
Key=report_pickle_s3_key)
# If there is more than 1 candidates then restart the simulation job otherwise
# tournament is finished, persists final report and ends the job.
if len(tournament_candidate_queue) > 1:
restart_simulation_job(
os.environ.get('AWS_ROBOMAKER_SIMULATION_JOB_ARN'),
s3_region)
break
else:
# Persist final tournament report in json format
# and terminate the job by canceling it
s3_client.put_object(Bucket=s3_bucket,
Key=final_report_s3_key,
Body=json.dumps(tournament_report))
cancel_simulation_job(
os.environ.get('AWS_ROBOMAKER_SIMULATION_JOB_ARN'),
s3_region)
except Exception as e:
log_and_exit(
"Tournament node failed: s3_bucket: {}, yaml_key: {}, {}".format(
s3_bucket, yaml_key, e), SIMAPP_SIMULATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_500)
def main():
""" Main function for downloading yaml params """
try:
# parse argument
s3_region = sys.argv[1]
s3_bucket = sys.argv[2]
s3_prefix = sys.argv[3]
s3_yaml_name = sys.argv[4]
launch_name = sys.argv[5]
# create boto3 session/client and download yaml/json file
session = boto3.session.Session()
s3_endpoint_url = os.environ.get("S3_ENDPOINT_URL", None)
if s3_endpoint_url is not None:
LOG.info('Endpoint URL {}'.format(s3_endpoint_url))
rospy.set_param('S3_ENDPOINT_URL', s3_endpoint_url)
else:
# create boto3 session/client and download yaml/json file
ec2_client = session.client('ec2', s3_region)
LOG.info('Checking internet connection...')
response = ec2_client.describe_vpcs()
if not response['Vpcs']:
log_and_exit("No VPC attached to instance",
SIMAPP_SIMULATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_500)
LOG.info('Verified internet connection')
s3_client = session.client('s3',
region_name=s3_region,
endpoint_url=s3_endpoint_url,
config=get_boto_config())
yaml_key = os.path.normpath(os.path.join(s3_prefix, s3_yaml_name))
local_yaml_path = os.path.abspath(
os.path.join(os.getcwd(), s3_yaml_name))
s3_client.download_file(Bucket=s3_bucket,
Key=yaml_key,
Filename=local_yaml_path)
# Get values passed in yaml files. Default values are for backward compatibility and for single racecar racing
default_yaml_values = {
RACE_TYPE_YAML_KEY: TIME_TRIAL_RACE_TYPE,
MODEL_S3_BUCKET_YAML_KEY: s3_bucket,
MODEL_S3_PREFIX_YAML_KEY: s3_prefix,
CAR_COLOR_YAML_KEY: DEFAULT_COLOR,
MODEL_METADATA_FILE_S3_YAML_KEY: None
}
yaml_dict = get_yaml_dict(local_yaml_path)
yaml_values = get_yaml_values(yaml_dict, default_yaml_values)
# Forcing the yaml parameter to list
force_list_params = [
MODEL_METADATA_FILE_S3_YAML_KEY, MODEL_S3_BUCKET_YAML_KEY,
MODEL_S3_PREFIX_YAML_KEY, CAR_COLOR_YAML_KEY
]
for params in force_list_params:
yaml_values[params] = force_list(yaml_values[params])
# Populate the model_metadata_s3_key values to handle both training and evaluation for all race_formats
if None in yaml_values[MODEL_METADATA_FILE_S3_YAML_KEY]:
# MODEL_METADATA_FILE_S3_KEY not passed as part of yaml file ==> This happens during evaluation
# Assume model_metadata.json is present in the s3_prefix/model/ folder
yaml_values[MODEL_METADATA_FILE_S3_YAML_KEY] = list()
for s3_prefix in yaml_values[MODEL_S3_PREFIX_YAML_KEY]:
yaml_values[MODEL_METADATA_FILE_S3_YAML_KEY].append(
os.path.join(s3_prefix, 'model/model_metadata.json'))
# Set multicar value if its a head to model racetype
multicar = yaml_values[RACE_TYPE_YAML_KEY] == HEAD_TO_MODEL_RACE_TYPE
# Validate the yaml values
validate_yaml_values(yaml_values, multicar)
# List of racecar names that should include second camera while launching
racecars_with_stereo_cameras = list()
# List of racecar names that should include lidar while launching
racecars_with_lidars = list()
# List of SimApp versions
simapp_versions = list()
for agent_index, model_s3_bucket in enumerate(
yaml_values[MODEL_S3_BUCKET_YAML_KEY]):
racecar_name = 'racecar_' + str(agent_index) if len(
yaml_values[MODEL_S3_BUCKET_YAML_KEY]) > 1 else 'racecar'
# Make a local folder with the racecar name to download the model_metadata.json
if not os.path.exists(os.path.join(os.getcwd(), racecar_name)):
os.makedirs(os.path.join(os.getcwd(), racecar_name))
local_model_metadata_path = os.path.abspath(
os.path.join(os.path.join(os.getcwd(), racecar_name),
'model_metadata.json'))
json_key = yaml_values[MODEL_METADATA_FILE_S3_YAML_KEY][
agent_index]
json_key = json_key.replace('s3://{}/'.format(model_s3_bucket), '')
s3_client.download_file(Bucket=model_s3_bucket,
Key=json_key,
Filename=local_model_metadata_path)
sensors, _, simapp_version = utils_parse_model_metadata.parse_model_metadata(
local_model_metadata_path)
simapp_versions.append(simapp_version)
if Input.STEREO.value in sensors:
racecars_with_stereo_cameras.append(racecar_name)
if Input.LIDAR.value in sensors or Input.SECTOR_LIDAR.value in sensors:
racecars_with_lidars.append(racecar_name)
cmd = [
''.join(("roslaunch deepracer_simulation_environment {} ".format(
launch_name), "local_yaml_path:={} ".format(local_yaml_path),
"racecars_with_stereo_cameras:={} ".format(
','.join(racecars_with_stereo_cameras)),
"racecars_with_lidars:={} multicar:={} ".format(
','.join(racecars_with_lidars), multicar),
"car_colors:={} simapp_versions:={}".format(
','.join(yaml_values[CAR_COLOR_YAML_KEY]),
','.join(simapp_versions))))
]
Popen(cmd, shell=True, executable="/bin/bash")
except botocore.exceptions.ClientError as ex:
log_and_exit(
"Download params and launch of agent node failed: s3_bucket: {}, yaml_key: {}, {}"
.format(s3_bucket, yaml_key, ex),
SIMAPP_SIMULATION_WORKER_EXCEPTION, SIMAPP_EVENT_ERROR_CODE_400)
except botocore.exceptions.EndpointConnectionError:
log_and_exit("No Internet connection or s3 service unavailable",
SIMAPP_SIMULATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_500)
except Exception as ex:
log_and_exit(
"Download params and launch of agent node failed: s3_bucket: {}, yaml_key: {}, {}"
.format(s3_bucket, yaml_key, ex),
SIMAPP_SIMULATION_WORKER_EXCEPTION, SIMAPP_EVENT_ERROR_CODE_500)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('-p',
'--preset',
help="(string) Name of a preset to run \
(class name from the 'presets' directory.)",
type=str,
required=False)
parser.add_argument('--s3_bucket',
help='(string) S3 bucket',
type=str,
default=rospy.get_param("MODEL_S3_BUCKET",
"gsaur-test"))
parser.add_argument('--s3_prefix',
help='(string) S3 prefix',
type=str,
default=rospy.get_param("MODEL_S3_PREFIX",
"sagemaker"))
parser.add_argument('--aws_region',
help='(string) AWS region',
type=str,
default=rospy.get_param("AWS_REGION", "us-east-1"))
parser.add_argument('--number_of_trials',
help='(integer) Number of trials',
type=int,
default=int(rospy.get_param("NUMBER_OF_TRIALS", 10)))
parser.add_argument(
'-c',
'--local_model_directory',
help='(string) Path to a folder containing a checkpoint \
to restore the model from.',
type=str,
default='./checkpoint')
args = parser.parse_args()
logger.info("S3 bucket: %s \n S3 prefix: %s", args.s3_bucket,
args.s3_prefix)
s3_client = SageS3Client(bucket=args.s3_bucket,
s3_prefix=args.s3_prefix,
aws_region=args.aws_region)
# Load the model metadata
model_metadata_local_path = os.path.join(CUSTOM_FILES_PATH,
'model_metadata.json')
utils.load_model_metadata(
s3_client,
os.path.normpath("%s/model/model_metadata.json" % args.s3_prefix),
model_metadata_local_path)
# Handle backward compatibility
_, _, version = parse_model_metadata(model_metadata_local_path)
if float(version) < float(utils.SIMAPP_VERSION) and \
not utils.has_current_ckpnt_name(args.s3_bucket, args.s3_prefix, args.aws_region):
utils.make_compatible(args.s3_bucket, args.s3_prefix, args.aws_region,
SyncFiles.TRAINER_READY.value)
# Download hyperparameters from SageMaker
hyperparameters_file_success = False
hyperparams_s3_key = os.path.normpath(args.s3_prefix +
"/ip/hyperparameters.json")
hyperparameters_file_success = s3_client.download_file(
s3_key=hyperparams_s3_key, local_path="hyperparameters.json")
sm_hyperparams_dict = {}
if hyperparameters_file_success:
logger.info("Received Sagemaker hyperparameters successfully!")
with open("hyperparameters.json") as file:
sm_hyperparams_dict = json.load(file)
else:
logger.info("SageMaker hyperparameters not found.")
#! TODO each agent should have own config
_, _, version = utils_parse_model_metadata.parse_model_metadata(
model_metadata_local_path)
agent_config = {
'model_metadata': model_metadata_local_path,
'car_ctrl_cnfig': {
ConfigParams.LINK_NAME_LIST.value:
LINK_NAMES,
ConfigParams.VELOCITY_LIST.value:
VELOCITY_TOPICS,
ConfigParams.STEERING_LIST.value:
STEERING_TOPICS,
ConfigParams.CHANGE_START.value:
utils.str2bool(rospy.get_param('CHANGE_START_POSITION', False)),
ConfigParams.ALT_DIR.value:
utils.str2bool(
rospy.get_param('ALTERNATE_DRIVING_DIRECTION', False)),
ConfigParams.ACTION_SPACE_PATH.value:
'custom_files/model_metadata.json',
ConfigParams.REWARD.value:
reward_function,
ConfigParams.AGENT_NAME.value:
'racecar',
ConfigParams.VERSION.value:
version
}
}
#! TODO each agent should have own s3 bucket
metrics_s3_config = {
MetricsS3Keys.METRICS_BUCKET.value:
rospy.get_param('METRICS_S3_BUCKET'),
MetricsS3Keys.METRICS_KEY.value:
rospy.get_param('METRICS_S3_OBJECT_KEY'),
MetricsS3Keys.REGION.value:
rospy.get_param('AWS_REGION'),
MetricsS3Keys.STEP_BUCKET.value:
rospy.get_param('MODEL_S3_BUCKET'),
MetricsS3Keys.STEP_KEY.value:
os.path.join(rospy.get_param('MODEL_S3_PREFIX'),
EVALUATION_SIMTRACE_DATA_S3_OBJECT_KEY)
}
agent_list = list()
agent_list.append(
create_rollout_agent(agent_config, EvalMetrics(metrics_s3_config)))
agent_list.append(create_obstacles_agent())
agent_list.append(create_bot_cars_agent())
graph_manager, _ = get_graph_manager(sm_hyperparams_dict, agent_list)
ds_params_instance = S3BotoDataStoreParameters(
aws_region=args.aws_region,
bucket_name=args.s3_bucket,
checkpoint_dir=args.local_model_directory,
s3_folder=args.s3_prefix)
data_store = S3BotoDataStore(ds_params_instance)
data_store.graph_manager = graph_manager
graph_manager.data_store = data_store
graph_manager.env_params.seed = 0
task_parameters = TaskParameters()
task_parameters.checkpoint_restore_path = args.local_model_directory
evaluation_worker(
graph_manager=graph_manager,
data_store=data_store,
number_of_trials=args.number_of_trials,
task_parameters=task_parameters,
)
def main():
screen.set_use_colors(False)
parser = argparse.ArgumentParser()
parser.add_argument(
'-c',
'--checkpoint_dir',
help=
'(string) Path to a folder containing a checkpoint to restore the model from.',
type=str,
default='./checkpoint')
parser.add_argument('--s3_bucket',
help='(string) S3 bucket',
type=str,
default=rospy.get_param("SAGEMAKER_SHARED_S3_BUCKET",
"gsaur-test"))
parser.add_argument('--s3_prefix',
help='(string) S3 prefix',
type=str,
default=rospy.get_param("SAGEMAKER_SHARED_S3_PREFIX",
"sagemaker"))
parser.add_argument(
'--num-workers',
help="(int) The number of workers started in this pool",
type=int,
default=1)
parser.add_argument('-r',
'--redis_ip',
help="(string) IP or host for the redis server",
default='localhost',
type=str)
parser.add_argument('-rp',
'--redis_port',
help="(int) Port of the redis server",
default=6379,
type=int)
parser.add_argument('--aws_region',
help='(string) AWS region',
type=str,
default=rospy.get_param("AWS_REGION", "us-east-1"))
parser.add_argument('--reward_file_s3_key',
help='(string) Reward File S3 Key',
type=str,
default=rospy.get_param("REWARD_FILE_S3_KEY", None))
parser.add_argument('--model_metadata_s3_key',
help='(string) Model Metadata File S3 Key',
type=str,
default=rospy.get_param("MODEL_METADATA_FILE_S3_KEY",
None))
args = parser.parse_args()
s3_client = SageS3Client(bucket=args.s3_bucket,
s3_prefix=args.s3_prefix,
aws_region=args.aws_region)
logger.info("S3 bucket: %s" % args.s3_bucket)
logger.info("S3 prefix: %s" % args.s3_prefix)
# Load the model metadata
model_metadata_local_path = os.path.join(CUSTOM_FILES_PATH,
'model_metadata.json')
utils.load_model_metadata(s3_client, args.model_metadata_s3_key,
model_metadata_local_path)
# Download and import reward function
if not args.reward_file_s3_key:
utils.log_and_exit(
"Reward function code S3 key not available for S3 bucket {} and prefix {}"
.format(args.s3_bucket,
args.s3_prefix), utils.SIMAPP_SIMULATION_WORKER_EXCEPTION,
utils.SIMAPP_EVENT_ERROR_CODE_500)
download_customer_reward_function(s3_client, args.reward_file_s3_key)
try:
from custom_files.customer_reward_function import reward_function
except Exception as e:
utils.log_and_exit(
"Failed to import user's reward_function: {}".format(e),
utils.SIMAPP_SIMULATION_WORKER_EXCEPTION,
utils.SIMAPP_EVENT_ERROR_CODE_400)
# Instantiate Cameras
configure_camera()
redis_ip = s3_client.get_ip()
logger.info("Received IP from SageMaker successfully: %s" % redis_ip)
# Download hyperparameters from SageMaker
hyperparameters_file_success = False
hyperparams_s3_key = os.path.normpath(args.s3_prefix +
"/ip/hyperparameters.json")
hyperparameters_file_success = s3_client.download_file(
s3_key=hyperparams_s3_key, local_path="hyperparameters.json")
sm_hyperparams_dict = {}
if hyperparameters_file_success:
logger.info("Received Sagemaker hyperparameters successfully!")
with open("hyperparameters.json") as fp:
sm_hyperparams_dict = json.load(fp)
else:
logger.info("SageMaker hyperparameters not found.")
preset_file_success, _ = download_custom_files_if_present(
s3_client, args.s3_prefix)
#! TODO each agent should have own config
_, _, version = utils_parse_model_metadata.parse_model_metadata(
model_metadata_local_path)
agent_config = {
'model_metadata': model_metadata_local_path,
'car_ctrl_cnfig': {
ConfigParams.LINK_NAME_LIST.value:
LINK_NAMES,
ConfigParams.VELOCITY_LIST.value:
VELOCITY_TOPICS,
ConfigParams.STEERING_LIST.value:
STEERING_TOPICS,
ConfigParams.CHANGE_START.value:
utils.str2bool(rospy.get_param('CHANGE_START_POSITION', True)),
ConfigParams.ALT_DIR.value:
utils.str2bool(
rospy.get_param('ALTERNATE_DRIVING_DIRECTION', False)),
ConfigParams.ACTION_SPACE_PATH.value:
'custom_files/model_metadata.json',
ConfigParams.REWARD.value:
reward_function,
ConfigParams.AGENT_NAME.value:
'racecar',
ConfigParams.VERSION.value:
version
}
}
#! TODO each agent should have own s3 bucket
metrics_s3_config = {
MetricsS3Keys.METRICS_BUCKET.value:
rospy.get_param('METRICS_S3_BUCKET'),
MetricsS3Keys.METRICS_KEY.value:
rospy.get_param('METRICS_S3_OBJECT_KEY'),
MetricsS3Keys.REGION.value:
rospy.get_param('AWS_REGION'),
MetricsS3Keys.STEP_BUCKET.value:
rospy.get_param('SAGEMAKER_SHARED_S3_BUCKET'),
MetricsS3Keys.STEP_KEY.value:
os.path.join(rospy.get_param('SAGEMAKER_SHARED_S3_PREFIX'),
TRAINING_SIMTRACE_DATA_S3_OBJECT_KEY)
}
agent_list = list()
agent_list.append(
create_rollout_agent(agent_config, TrainingMetrics(metrics_s3_config)))
agent_list.append(create_obstacles_agent())
agent_list.append(create_bot_cars_agent())
if preset_file_success:
preset_location = os.path.join(CUSTOM_FILES_PATH, "preset.py")
preset_location += ":graph_manager"
graph_manager = short_dynamic_import(preset_location,
ignore_module_case=True)
logger.info("Using custom preset file!")
else:
graph_manager, _ = get_graph_manager(sm_hyperparams_dict, agent_list)
memory_backend_params = RedisPubSubMemoryBackendParameters(
redis_address=redis_ip,
redis_port=6379,
run_type=str(RunType.ROLLOUT_WORKER),
channel=args.s3_prefix)
graph_manager.memory_backend_params = memory_backend_params
ds_params_instance = S3BotoDataStoreParameters(
aws_region=args.aws_region,
bucket_name=args.s3_bucket,
checkpoint_dir=args.checkpoint_dir,
s3_folder=args.s3_prefix)
data_store = S3BotoDataStore(ds_params_instance)
data_store.graph_manager = graph_manager
graph_manager.data_store = data_store
task_parameters = TaskParameters()
task_parameters.checkpoint_restore_path = args.checkpoint_dir
rollout_worker(graph_manager=graph_manager,
data_store=data_store,
num_workers=args.num_workers,
task_parameters=task_parameters)
def validate(s3_bucket, s3_prefix, aws_region):
screen.set_use_colors(False)
screen.log_title(" S3 bucket: {} \n S3 prefix: {}".format(
s3_bucket, s3_prefix))
s3_client = SageS3Client(bucket=s3_bucket,
s3_prefix=s3_prefix,
aws_region=aws_region)
# Load the model metadata
utils.load_model_metadata(
s3_client,
os.path.normpath("%s/model/model_metadata.json" % s3_prefix),
MODEL_METADATA_LOCAL_PATH)
# Create model local path
os.makedirs(LOCAL_MODEL_DIR)
try:
# Handle backward compatibility
observation_list, _, version = parse_model_metadata(
MODEL_METADATA_LOCAL_PATH)
except Exception as ex:
log_and_exit("Failed to parse model_metadata file: {}".format(ex),
SIMAPP_VALIDATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_400)
# Below get_transition_data function must called before create_training_agent function
# to avoid 500 in case unsupported Sensor is received.
# create_training_agent will exit with 500 if unsupported sensor is received,
# and get_transition_data function below will exit with 400 if unsupported sensor is received.
# We want to return 400 in model validation case if unsupported sensor is received.
# Thus, call this get_transition_data function before create_traning_agent function!
transitions = get_transition_data(observation_list)
if float(version) < float(SIMAPP_VERSION) and \
not utils.has_current_ckpnt_name(s3_bucket, s3_prefix, aws_region):
utils.make_compatible(s3_bucket, s3_prefix, aws_region,
SyncFiles.TRAINER_READY.value)
agent_config = {
'model_metadata': MODEL_METADATA_LOCAL_PATH,
ConfigParams.CAR_CTRL_CONFIG.value: {
ConfigParams.LINK_NAME_LIST.value: [],
ConfigParams.VELOCITY_LIST.value: {},
ConfigParams.STEERING_LIST.value: {},
ConfigParams.CHANGE_START.value: None,
ConfigParams.ALT_DIR.value: None,
ConfigParams.ACTION_SPACE_PATH.value: MODEL_METADATA_LOCAL_PATH,
ConfigParams.REWARD.value: None,
ConfigParams.AGENT_NAME.value: 'racecar'
}
}
agent_list = list()
agent_list.append(create_training_agent(agent_config))
sm_hyperparams_dict = {}
graph_manager, _ = get_graph_manager(hp_dict=sm_hyperparams_dict,
agent_list=agent_list,
run_phase_subject=None)
ds_params_instance = S3BotoDataStoreParameters(
aws_region=aws_region,
bucket_names={'agent': s3_bucket},
s3_folders={'agent': s3_prefix},
base_checkpoint_dir=LOCAL_MODEL_DIR)
graph_manager.data_store = S3BotoDataStore(ds_params_instance,
graph_manager,
ignore_lock=True)
task_parameters = TaskParameters()
task_parameters.checkpoint_restore_path = LOCAL_MODEL_DIR
_validate(graph_manager=graph_manager,
task_parameters=task_parameters,
transitions=transitions,
s3_bucket=s3_bucket,
s3_prefix=s3_prefix,
aws_region=aws_region)
def main():
screen.set_use_colors(False)
parser = argparse.ArgumentParser()
parser.add_argument(
'-c',
'--checkpoint_dir',
help=
'(string) Path to a folder containing a checkpoint to restore the model from.',
type=str,
default='./checkpoint')
parser.add_argument('--s3_bucket',
help='(string) S3 bucket',
type=str,
default=rospy.get_param("SAGEMAKER_SHARED_S3_BUCKET",
"gsaur-test"))
parser.add_argument('--s3_prefix',
help='(string) S3 prefix',
type=str,
default=rospy.get_param("SAGEMAKER_SHARED_S3_PREFIX",
"sagemaker"))
parser.add_argument(
'--num_workers',
help="(int) The number of workers started in this pool",
type=int,
default=int(rospy.get_param("NUM_WORKERS", 1)))
parser.add_argument('--rollout_idx',
help="(int) The index of current rollout worker",
type=int,
default=0)
parser.add_argument('-r',
'--redis_ip',
help="(string) IP or host for the redis server",
default='localhost',
type=str)
parser.add_argument('-rp',
'--redis_port',
help="(int) Port of the redis server",
default=6379,
type=int)
parser.add_argument('--aws_region',
help='(string) AWS region',
type=str,
default=rospy.get_param("AWS_REGION", "us-east-1"))
parser.add_argument('--reward_file_s3_key',
help='(string) Reward File S3 Key',
type=str,
default=rospy.get_param("REWARD_FILE_S3_KEY", None))
parser.add_argument('--model_metadata_s3_key',
help='(string) Model Metadata File S3 Key',
type=str,
default=rospy.get_param("MODEL_METADATA_FILE_S3_KEY",
None))
# For training job, reset is not allowed. penalty_seconds, off_track_penalty, and
# collision_penalty will all be 0 be default
parser.add_argument('--number_of_resets',
help='(integer) Number of resets',
type=int,
default=int(rospy.get_param("NUMBER_OF_RESETS", 0)))
parser.add_argument('--penalty_seconds',
help='(float) penalty second',
type=float,
default=float(rospy.get_param("PENALTY_SECONDS", 0.0)))
parser.add_argument('--job_type',
help='(string) job type',
type=str,
default=rospy.get_param("JOB_TYPE", "TRAINING"))
parser.add_argument('--is_continuous',
help='(boolean) is continous after lap completion',
type=bool,
default=utils.str2bool(
rospy.get_param("IS_CONTINUOUS", False)))
parser.add_argument('--race_type',
help='(string) Race type',
type=str,
default=rospy.get_param("RACE_TYPE", "TIME_TRIAL"))
parser.add_argument('--off_track_penalty',
help='(float) off track penalty second',
type=float,
default=float(rospy.get_param("OFF_TRACK_PENALTY",
0.0)))
parser.add_argument('--collision_penalty',
help='(float) collision penalty second',
type=float,
default=float(rospy.get_param("COLLISION_PENALTY",
0.0)))
args = parser.parse_args()
s3_client = SageS3Client(bucket=args.s3_bucket,
s3_prefix=args.s3_prefix,
aws_region=args.aws_region)
logger.info("S3 bucket: %s", args.s3_bucket)
logger.info("S3 prefix: %s", args.s3_prefix)
# Load the model metadata
model_metadata_local_path = os.path.join(CUSTOM_FILES_PATH,
'model_metadata.json')
utils.load_model_metadata(s3_client, args.model_metadata_s3_key,
model_metadata_local_path)
# Download and import reward function
if not args.reward_file_s3_key:
log_and_exit(
"Reward function code S3 key not available for S3 bucket {} and prefix {}"
.format(args.s3_bucket, args.s3_prefix),
SIMAPP_SIMULATION_WORKER_EXCEPTION, SIMAPP_EVENT_ERROR_CODE_500)
download_customer_reward_function(s3_client, args.reward_file_s3_key)
try:
from custom_files.customer_reward_function import reward_function
except Exception as e:
log_and_exit("Failed to import user's reward_function: {}".format(e),
SIMAPP_SIMULATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_400)
# Instantiate Cameras
configure_camera(namespaces=['racecar'])
preset_file_success, _ = download_custom_files_if_present(
s3_client, args.s3_prefix)
#! TODO each agent should have own config
_, _, version = utils_parse_model_metadata.parse_model_metadata(
model_metadata_local_path)
agent_config = {
'model_metadata': model_metadata_local_path,
ConfigParams.CAR_CTRL_CONFIG.value: {
ConfigParams.LINK_NAME_LIST.value:
LINK_NAMES,
ConfigParams.VELOCITY_LIST.value:
VELOCITY_TOPICS,
ConfigParams.STEERING_LIST.value:
STEERING_TOPICS,
ConfigParams.CHANGE_START.value:
utils.str2bool(rospy.get_param('CHANGE_START_POSITION', True)),
ConfigParams.ALT_DIR.value:
utils.str2bool(
rospy.get_param('ALTERNATE_DRIVING_DIRECTION', False)),
ConfigParams.ACTION_SPACE_PATH.value:
'custom_files/model_metadata.json',
ConfigParams.REWARD.value:
reward_function,
ConfigParams.AGENT_NAME.value:
'racecar',
ConfigParams.VERSION.value:
version,
ConfigParams.NUMBER_OF_RESETS.value:
args.number_of_resets,
ConfigParams.PENALTY_SECONDS.value:
args.penalty_seconds,
ConfigParams.NUMBER_OF_TRIALS.value:
None,
ConfigParams.IS_CONTINUOUS.value:
args.is_continuous,
ConfigParams.RACE_TYPE.value:
args.race_type,
ConfigParams.COLLISION_PENALTY.value:
args.collision_penalty,
ConfigParams.OFF_TRACK_PENALTY.value:
args.off_track_penalty
}
}
#! TODO each agent should have own s3 bucket
step_metrics_prefix = rospy.get_param('SAGEMAKER_SHARED_S3_PREFIX')
if args.num_workers > 1:
step_metrics_prefix = os.path.join(step_metrics_prefix,
str(args.rollout_idx))
metrics_s3_config = {
MetricsS3Keys.METRICS_BUCKET.value:
rospy.get_param('METRICS_S3_BUCKET'),
MetricsS3Keys.METRICS_KEY.value:
rospy.get_param('METRICS_S3_OBJECT_KEY'),
MetricsS3Keys.REGION.value: rospy.get_param('AWS_REGION')
}
metrics_s3_model_cfg = {
MetricsS3Keys.METRICS_BUCKET.value:
args.s3_bucket,
MetricsS3Keys.METRICS_KEY.value:
os.path.join(args.s3_prefix, DEEPRACER_CHKPNT_KEY_SUFFIX),
MetricsS3Keys.REGION.value:
args.aws_region
}
run_phase_subject = RunPhaseSubject()
agent_list = list()
agent_list.append(
create_rollout_agent(
agent_config,
TrainingMetrics(agent_name='agent',
s3_dict_metrics=metrics_s3_config,
s3_dict_model=metrics_s3_model_cfg,
ckpnt_dir=args.checkpoint_dir,
run_phase_sink=run_phase_subject,
use_model_picker=(args.rollout_idx == 0)),
run_phase_subject))
agent_list.append(create_obstacles_agent())
agent_list.append(create_bot_cars_agent())
# ROS service to indicate all the robomaker markov packages are ready for consumption
signal_robomaker_markov_package_ready()
PhaseObserver('/agent/training_phase', run_phase_subject)
aws_region = rospy.get_param('AWS_REGION', args.aws_region)
simtrace_s3_bucket = rospy.get_param('SIMTRACE_S3_BUCKET', None)
mp4_s3_bucket = rospy.get_param('MP4_S3_BUCKET',
None) if args.rollout_idx == 0 else None
if simtrace_s3_bucket:
simtrace_s3_object_prefix = rospy.get_param('SIMTRACE_S3_PREFIX')
if args.num_workers > 1:
simtrace_s3_object_prefix = os.path.join(simtrace_s3_object_prefix,
str(args.rollout_idx))
if mp4_s3_bucket:
mp4_s3_object_prefix = rospy.get_param('MP4_S3_OBJECT_PREFIX')
s3_writer_job_info = []
if simtrace_s3_bucket:
s3_writer_job_info.append(
IterationData(
'simtrace', simtrace_s3_bucket, simtrace_s3_object_prefix,
aws_region,
os.path.join(
ITERATION_DATA_LOCAL_FILE_PATH, 'agent',
IterationDataLocalFileNames.SIM_TRACE_TRAINING_LOCAL_FILE.
value)))
if mp4_s3_bucket:
s3_writer_job_info.extend([
IterationData(
'pip', mp4_s3_bucket, mp4_s3_object_prefix, aws_region,
os.path.join(
ITERATION_DATA_LOCAL_FILE_PATH, 'agent',
IterationDataLocalFileNames.
CAMERA_PIP_MP4_VALIDATION_LOCAL_PATH.value)),
IterationData(
'45degree', mp4_s3_bucket, mp4_s3_object_prefix, aws_region,
os.path.join(
ITERATION_DATA_LOCAL_FILE_PATH, 'agent',
IterationDataLocalFileNames.
CAMERA_45DEGREE_MP4_VALIDATION_LOCAL_PATH.value)),
IterationData(
'topview', mp4_s3_bucket, mp4_s3_object_prefix, aws_region,
os.path.join(
ITERATION_DATA_LOCAL_FILE_PATH, 'agent',
IterationDataLocalFileNames.
CAMERA_TOPVIEW_MP4_VALIDATION_LOCAL_PATH.value))
])
s3_writer = S3Writer(job_info=s3_writer_job_info)
redis_ip = s3_client.get_ip()
logger.info("Received IP from SageMaker successfully: %s", redis_ip)
# Download hyperparameters from SageMaker
hyperparameters_file_success = False
hyperparams_s3_key = os.path.normpath(args.s3_prefix +
"/ip/hyperparameters.json")
hyperparameters_file_success = s3_client.download_file(
s3_key=hyperparams_s3_key, local_path="hyperparameters.json")
sm_hyperparams_dict = {}
if hyperparameters_file_success:
logger.info("Received Sagemaker hyperparameters successfully!")
with open("hyperparameters.json") as filepointer:
sm_hyperparams_dict = json.load(filepointer)
else:
logger.info("SageMaker hyperparameters not found.")
enable_domain_randomization = utils.str2bool(
rospy.get_param('ENABLE_DOMAIN_RANDOMIZATION', False))
if preset_file_success:
preset_location = os.path.join(CUSTOM_FILES_PATH, "preset.py")
preset_location += ":graph_manager"
graph_manager = short_dynamic_import(preset_location,
ignore_module_case=True)
logger.info("Using custom preset file!")
else:
graph_manager, _ = get_graph_manager(
hp_dict=sm_hyperparams_dict,
agent_list=agent_list,
run_phase_subject=run_phase_subject,
enable_domain_randomization=enable_domain_randomization)
# If num_episodes_between_training is smaller than num_workers then cancel worker early.
episode_steps_per_rollout = graph_manager.agent_params.algorithm.num_consecutive_playing_steps.num_steps
# Reduce number of workers if allocated more than num_episodes_between_training
if args.num_workers > episode_steps_per_rollout:
logger.info(
"Excess worker allocated. Reducing from {} to {}...".format(
args.num_workers, episode_steps_per_rollout))
args.num_workers = episode_steps_per_rollout
if args.rollout_idx >= episode_steps_per_rollout or args.rollout_idx >= args.num_workers:
err_msg_format = "Exiting excess worker..."
err_msg_format += "(rollout_idx[{}] >= num_workers[{}] or num_episodes_between_training[{}])"
logger.info(
err_msg_format.format(args.rollout_idx, args.num_workers,
episode_steps_per_rollout))
# Close the down the job
utils.cancel_simulation_job(
os.environ.get('AWS_ROBOMAKER_SIMULATION_JOB_ARN'),
rospy.get_param('AWS_REGION'))
memory_backend_params = DeepRacerRedisPubSubMemoryBackendParameters(
redis_address=redis_ip,
redis_port=6379,
run_type=str(RunType.ROLLOUT_WORKER),
channel=args.s3_prefix,
num_workers=args.num_workers,
rollout_idx=args.rollout_idx)
graph_manager.memory_backend_params = memory_backend_params
ds_params_instance = S3BotoDataStoreParameters(
aws_region=args.aws_region,
bucket_names={'agent': args.s3_bucket},
base_checkpoint_dir=args.checkpoint_dir,
s3_folders={'agent': args.s3_prefix})
graph_manager.data_store = S3BotoDataStore(ds_params_instance,
graph_manager)
task_parameters = TaskParameters()
task_parameters.checkpoint_restore_path = args.checkpoint_dir
rollout_worker(graph_manager=graph_manager,
num_workers=args.num_workers,
rollout_idx=args.rollout_idx,
task_parameters=task_parameters,
s3_writer=s3_writer)
def main():
""" Main function for tournament worker """
parser = argparse.ArgumentParser()
parser.add_argument('-p',
'--preset',
help="(string) Name of a preset to run \
(class name from the 'presets' directory.)",
type=str,
required=False)
parser.add_argument('--s3_bucket',
help='list(string) S3 bucket',
type=str,
nargs='+',
default=rospy.get_param("MODEL_S3_BUCKET",
["gsaur-test"]))
parser.add_argument('--s3_prefix',
help='list(string) S3 prefix',
type=str,
nargs='+',
default=rospy.get_param("MODEL_S3_PREFIX",
["sagemaker"]))
parser.add_argument('--aws_region',
help='(string) AWS region',
type=str,
default=rospy.get_param("AWS_REGION", "us-east-1"))
parser.add_argument('--number_of_trials',
help='(integer) Number of trials',
type=int,
default=int(rospy.get_param("NUMBER_OF_TRIALS", 10)))
parser.add_argument(
'-c',
'--local_model_directory',
help='(string) Path to a folder containing a checkpoint \
to restore the model from.',
type=str,
default='./checkpoint')
parser.add_argument('--number_of_resets',
help='(integer) Number of resets',
type=int,
default=int(rospy.get_param("NUMBER_OF_RESETS", 0)))
parser.add_argument('--penalty_seconds',
help='(float) penalty second',
type=float,
default=float(rospy.get_param("PENALTY_SECONDS", 2.0)))
parser.add_argument('--job_type',
help='(string) job type',
type=str,
default=rospy.get_param("JOB_TYPE", "EVALUATION"))
parser.add_argument('--is_continuous',
help='(boolean) is continous after lap completion',
type=bool,
default=utils.str2bool(
rospy.get_param("IS_CONTINUOUS", False)))
parser.add_argument('--race_type',
help='(string) Race type',
type=str,
default=rospy.get_param("RACE_TYPE", "TIME_TRIAL"))
parser.add_argument('--off_track_penalty',
help='(float) off track penalty second',
type=float,
default=float(rospy.get_param("OFF_TRACK_PENALTY",
2.0)))
parser.add_argument('--collision_penalty',
help='(float) collision penalty second',
type=float,
default=float(rospy.get_param("COLLISION_PENALTY",
5.0)))
args = parser.parse_args()
arg_s3_bucket = args.s3_bucket
arg_s3_prefix = args.s3_prefix
logger.info("S3 bucket: %s \n S3 prefix: %s", arg_s3_bucket, arg_s3_prefix)
# tournament_worker: names to be displayed in MP4.
# This is racer alias in tournament worker case.
display_names = rospy.get_param('DISPLAY_NAME', "")
metrics_s3_buckets = rospy.get_param('METRICS_S3_BUCKET')
metrics_s3_object_keys = rospy.get_param('METRICS_S3_OBJECT_KEY')
arg_s3_bucket, arg_s3_prefix = utils.force_list(
arg_s3_bucket), utils.force_list(arg_s3_prefix)
metrics_s3_buckets = utils.force_list(metrics_s3_buckets)
metrics_s3_object_keys = utils.force_list(metrics_s3_object_keys)
validate_list = [
arg_s3_bucket, arg_s3_prefix, metrics_s3_buckets,
metrics_s3_object_keys
]
simtrace_s3_bucket = rospy.get_param('SIMTRACE_S3_BUCKET', None)
mp4_s3_bucket = rospy.get_param('MP4_S3_BUCKET', None)
if simtrace_s3_bucket:
simtrace_s3_object_prefix = rospy.get_param('SIMTRACE_S3_PREFIX')
simtrace_s3_bucket = utils.force_list(simtrace_s3_bucket)
simtrace_s3_object_prefix = utils.force_list(simtrace_s3_object_prefix)
validate_list.extend([simtrace_s3_bucket, simtrace_s3_object_prefix])
if mp4_s3_bucket:
mp4_s3_object_prefix = rospy.get_param('MP4_S3_OBJECT_PREFIX')
mp4_s3_bucket = utils.force_list(mp4_s3_bucket)
mp4_s3_object_prefix = utils.force_list(mp4_s3_object_prefix)
validate_list.extend([mp4_s3_bucket, mp4_s3_object_prefix])
if not all([lambda x: len(x) == len(validate_list[0]), validate_list]):
utils.log_and_exit(
"Eval worker error: Incorrect arguments passed: {}".format(
validate_list), utils.SIMAPP_SIMULATION_WORKER_EXCEPTION,
utils.SIMAPP_EVENT_ERROR_CODE_500)
if args.number_of_resets != 0 and args.number_of_resets < MIN_RESET_COUNT:
raise GenericRolloutException(
"number of resets is less than {}".format(MIN_RESET_COUNT))
# Instantiate Cameras
if len(arg_s3_bucket) == 1:
configure_camera(namespaces=['racecar'])
else:
configure_camera(namespaces=[
'racecar_{}'.format(str(agent_index))
for agent_index in range(len(arg_s3_bucket))
])
agent_list = list()
s3_bucket_dict = dict()
s3_prefix_dict = dict()
s3_writers = list()
# tournament_worker: list of required S3 locations
simtrace_s3_bucket_dict = dict()
simtrace_s3_prefix_dict = dict()
metrics_s3_bucket_dict = dict()
metrics_s3_obect_key_dict = dict()
mp4_s3_bucket_dict = dict()
mp4_s3_object_prefix_dict = dict()
for agent_index, s3_bucket_val in enumerate(arg_s3_bucket):
agent_name = 'agent' if len(arg_s3_bucket) == 1 else 'agent_{}'.format(
str(agent_index))
racecar_name = 'racecar' if len(
arg_s3_bucket) == 1 else 'racecar_{}'.format(str(agent_index))
s3_bucket_dict[agent_name] = arg_s3_bucket[agent_index]
s3_prefix_dict[agent_name] = arg_s3_prefix[agent_index]
# tournament_worker: remap key with agent_name instead of agent_index for list of S3 locations.
simtrace_s3_bucket_dict[agent_name] = simtrace_s3_bucket[agent_index]
simtrace_s3_prefix_dict[agent_name] = simtrace_s3_object_prefix[
agent_index]
metrics_s3_bucket_dict[agent_name] = metrics_s3_buckets[agent_index]
metrics_s3_obect_key_dict[agent_name] = metrics_s3_object_keys[
agent_index]
mp4_s3_bucket_dict[agent_name] = mp4_s3_bucket[agent_index]
mp4_s3_object_prefix_dict[agent_name] = mp4_s3_object_prefix[
agent_index]
s3_client = SageS3Client(bucket=arg_s3_bucket[agent_index],
s3_prefix=arg_s3_prefix[agent_index],
aws_region=args.aws_region)
# Load the model metadata
if not os.path.exists(os.path.join(CUSTOM_FILES_PATH, agent_name)):
os.makedirs(os.path.join(CUSTOM_FILES_PATH, agent_name))
model_metadata_local_path = os.path.join(
os.path.join(CUSTOM_FILES_PATH, agent_name), 'model_metadata.json')
utils.load_model_metadata(
s3_client,
os.path.normpath("%s/model/model_metadata.json" %
arg_s3_prefix[agent_index]),
model_metadata_local_path)
# Handle backward compatibility
_, _, version = parse_model_metadata(model_metadata_local_path)
if float(version) < float(utils.SIMAPP_VERSION) and \
not utils.has_current_ckpnt_name(arg_s3_bucket[agent_index], arg_s3_prefix[agent_index], args.aws_region):
utils.make_compatible(arg_s3_bucket[agent_index],
arg_s3_prefix[agent_index], args.aws_region,
SyncFiles.TRAINER_READY.value)
# Select the optimal model
utils.do_model_selection(s3_bucket=arg_s3_bucket[agent_index],
s3_prefix=arg_s3_prefix[agent_index],
region=args.aws_region)
# Download hyperparameters from SageMaker
if not os.path.exists(agent_name):
os.makedirs(agent_name)
hyperparameters_file_success = False
hyperparams_s3_key = os.path.normpath(arg_s3_prefix[agent_index] +
"/ip/hyperparameters.json")
hyperparameters_file_success = s3_client.download_file(
s3_key=hyperparams_s3_key,
local_path=os.path.join(agent_name, "hyperparameters.json"))
sm_hyperparams_dict = {}
if hyperparameters_file_success:
logger.info("Received Sagemaker hyperparameters successfully!")
with open(os.path.join(agent_name,
"hyperparameters.json")) as file:
sm_hyperparams_dict = json.load(file)
else:
logger.info("SageMaker hyperparameters not found.")
agent_config = {
'model_metadata': model_metadata_local_path,
ConfigParams.CAR_CTRL_CONFIG.value: {
ConfigParams.LINK_NAME_LIST.value: [
link_name.replace('racecar', racecar_name)
for link_name in LINK_NAMES
],
ConfigParams.VELOCITY_LIST.value: [
velocity_topic.replace('racecar', racecar_name)
for velocity_topic in VELOCITY_TOPICS
],
ConfigParams.STEERING_LIST.value: [
steering_topic.replace('racecar', racecar_name)
for steering_topic in STEERING_TOPICS
],
ConfigParams.CHANGE_START.value:
utils.str2bool(rospy.get_param('CHANGE_START_POSITION',
False)),
ConfigParams.ALT_DIR.value:
utils.str2bool(
rospy.get_param('ALTERNATE_DRIVING_DIRECTION', False)),
ConfigParams.ACTION_SPACE_PATH.value:
'custom_files/' + agent_name + '/model_metadata.json',
ConfigParams.REWARD.value:
reward_function,
ConfigParams.AGENT_NAME.value:
racecar_name,
ConfigParams.VERSION.value:
version,
ConfigParams.NUMBER_OF_RESETS.value:
args.number_of_resets,
ConfigParams.PENALTY_SECONDS.value:
args.penalty_seconds,
ConfigParams.NUMBER_OF_TRIALS.value:
args.number_of_trials,
ConfigParams.IS_CONTINUOUS.value:
args.is_continuous,
ConfigParams.RACE_TYPE.value:
args.race_type,
ConfigParams.COLLISION_PENALTY.value:
args.collision_penalty,
ConfigParams.OFF_TRACK_PENALTY.value:
args.off_track_penalty
}
}
metrics_s3_config = {
MetricsS3Keys.METRICS_BUCKET.value:
metrics_s3_buckets[agent_index],
MetricsS3Keys.METRICS_KEY.value:
metrics_s3_object_keys[agent_index],
# Replaced rospy.get_param('AWS_REGION') to be equal to the argument being passed
# or default argument set
MetricsS3Keys.REGION.value:
args.aws_region,
# Replaced rospy.get_param('MODEL_S3_BUCKET') to be equal to the argument being passed
# or default argument set
MetricsS3Keys.STEP_BUCKET.value:
arg_s3_bucket[agent_index],
# Replaced rospy.get_param('MODEL_S3_PREFIX') to be equal to the argument being passed
# or default argument set
MetricsS3Keys.STEP_KEY.value:
os.path.join(arg_s3_prefix[agent_index],
EVALUATION_SIMTRACE_DATA_S3_OBJECT_KEY)
}
aws_region = rospy.get_param('AWS_REGION', args.aws_region)
s3_writer_job_info = []
if simtrace_s3_bucket:
s3_writer_job_info.append(
IterationData(
'simtrace', simtrace_s3_bucket[agent_index],
simtrace_s3_object_prefix[agent_index], aws_region,
os.path.join(
ITERATION_DATA_LOCAL_FILE_PATH, agent_name,
IterationDataLocalFileNames.
SIM_TRACE_EVALUATION_LOCAL_FILE.value)))
if mp4_s3_bucket:
s3_writer_job_info.extend([
IterationData(
'pip', mp4_s3_bucket[agent_index],
mp4_s3_object_prefix[agent_index], aws_region,
os.path.join(
ITERATION_DATA_LOCAL_FILE_PATH, agent_name,
IterationDataLocalFileNames.
CAMERA_PIP_MP4_VALIDATION_LOCAL_PATH.value)),
IterationData(
'45degree', mp4_s3_bucket[agent_index],
mp4_s3_object_prefix[agent_index], aws_region,
os.path.join(
ITERATION_DATA_LOCAL_FILE_PATH, agent_name,
IterationDataLocalFileNames.
CAMERA_45DEGREE_MP4_VALIDATION_LOCAL_PATH.value)),
IterationData(
'topview', mp4_s3_bucket[agent_index],
mp4_s3_object_prefix[agent_index], aws_region,
os.path.join(
ITERATION_DATA_LOCAL_FILE_PATH, agent_name,
IterationDataLocalFileNames.
CAMERA_TOPVIEW_MP4_VALIDATION_LOCAL_PATH.value))
])
s3_writers.append(S3Writer(job_info=s3_writer_job_info))
run_phase_subject = RunPhaseSubject()
agent_list.append(
create_rollout_agent(agent_config,
EvalMetrics(agent_name, metrics_s3_config),
run_phase_subject))
agent_list.append(create_obstacles_agent())
agent_list.append(create_bot_cars_agent())
# ROS service to indicate all the robomaker markov packages are ready for consumption
signal_robomaker_markov_package_ready()
PhaseObserver('/agent/training_phase', run_phase_subject)
graph_manager, _ = get_graph_manager(hp_dict=sm_hyperparams_dict,
agent_list=agent_list,
run_phase_subject=run_phase_subject)
ds_params_instance = S3BotoDataStoreParameters(
aws_region=args.aws_region,
bucket_names=s3_bucket_dict,
base_checkpoint_dir=args.local_model_directory,
s3_folders=s3_prefix_dict)
graph_manager.data_store = S3BotoDataStore(params=ds_params_instance,
graph_manager=graph_manager,
ignore_lock=True)
graph_manager.env_params.seed = 0
task_parameters = TaskParameters()
task_parameters.checkpoint_restore_path = args.local_model_directory
tournament_worker(graph_manager=graph_manager,
number_of_trials=args.number_of_trials,
task_parameters=task_parameters,
s3_writers=s3_writers,
is_continuous=args.is_continuous)
# tournament_worker: write race report to local file.
write_race_report(graph_manager,
model_s3_bucket_map=s3_bucket_dict,
model_s3_prefix_map=s3_prefix_dict,
metrics_s3_bucket_map=metrics_s3_bucket_dict,
metrics_s3_key_map=metrics_s3_obect_key_dict,
simtrace_s3_bucket_map=simtrace_s3_bucket_dict,
simtrace_s3_prefix_map=simtrace_s3_prefix_dict,
mp4_s3_bucket_map=mp4_s3_bucket_dict,
mp4_s3_prefix_map=mp4_s3_object_prefix_dict,
display_names=display_names)
# tournament_worker: terminate tournament_race_node.
terminate_tournament_race()
def main():
""" Main function for downloading yaml params """
# parse argument
s3_region = sys.argv[1]
s3_bucket = sys.argv[2]
s3_prefix = sys.argv[3]
s3_yaml_name = sys.argv[4]
launch_name = sys.argv[5]
yaml_key = os.path.normpath(os.path.join(s3_prefix, s3_yaml_name))
try:
# create boto3 session/client and download yaml/json file
session = boto3.session.Session()
s3_endpoint_url = os.environ.get("S3_ENDPOINT_URL", None)
if s3_endpoint_url is not None:
LOG.info('Endpoint URL {}'.format(s3_endpoint_url))
rospy.set_param('S3_ENDPOINT_URL', s3_endpoint_url)
s3_client = session.client('s3',
region_name=s3_region,
endpoint_url=s3_endpoint_url,
config=get_boto_config())
local_yaml_path = os.path.abspath(
os.path.join(os.getcwd(), s3_yaml_name))
s3_client.download_file(Bucket=s3_bucket,
Key=yaml_key,
Filename=local_yaml_path)
# Get values passed in yaml files. Default values are for backward compatibility and for single racecar racing
default_yaml_values = {
RACE_TYPE_YAML_KEY: TIME_TRIAL_RACE_TYPE,
MODEL_S3_BUCKET_YAML_KEY: s3_bucket,
MODEL_S3_PREFIX_YAML_KEY: s3_prefix,
CAR_COLOR_YAML_KEY: DEFAULT_COLOR,
BODY_SHELL_TYPE_YAML_KEY: None,
MODEL_METADATA_FILE_S3_YAML_KEY: None,
RACER_NAME_YAML_KEY: None
}
yaml_dict = get_yaml_dict(local_yaml_path)
yaml_values = get_yaml_values(yaml_dict, default_yaml_values)
# Forcing the yaml parameter to list
force_list_params = [
MODEL_METADATA_FILE_S3_YAML_KEY, MODEL_S3_BUCKET_YAML_KEY,
MODEL_S3_PREFIX_YAML_KEY, CAR_COLOR_YAML_KEY,
BODY_SHELL_TYPE_YAML_KEY, RACER_NAME_YAML_KEY
]
for params in force_list_params:
yaml_values[params] = force_list(yaml_values[params])
# Populate the model_metadata_s3_key values to handle both training and evaluation for all race_formats
if None in yaml_values[MODEL_METADATA_FILE_S3_YAML_KEY]:
# MODEL_METADATA_FILE_S3_KEY not passed as part of yaml file ==> This happens during evaluation
# Assume model_metadata.json is present in the s3_prefix/model/ folder
yaml_values[MODEL_METADATA_FILE_S3_YAML_KEY] = list()
for s3_prefix in yaml_values[MODEL_S3_PREFIX_YAML_KEY]:
yaml_values[MODEL_METADATA_FILE_S3_YAML_KEY].append(
os.path.join(s3_prefix, 'model/model_metadata.json'))
# Set multicar value if there is more than one value in MODEL_S3_BUCKET_YAML_KEY.
multicar = len(yaml_values[MODEL_S3_BUCKET_YAML_KEY]) > 1
# Set f1 as true if RACE_TYPE is F1
is_f1 = yaml_values[RACE_TYPE_YAML_KEY] == F1_RACE_TYPE
# Validate the yaml values
validate_yaml_values(yaml_values, multicar)
# List of racecar names that should include second camera while launching
racecars_with_stereo_cameras = list()
# List of racecar names that should include lidar while launching
racecars_with_lidars = list()
# List of SimApp versions
simapp_versions = list()
# List of body shell types
body_shell_types = yaml_values[BODY_SHELL_TYPE_YAML_KEY]
racer_names = yaml_values[RACER_NAME_YAML_KEY]
if None in body_shell_types:
# use default shells
if None in racer_names:
body_shell_types = [BodyShellType.DEFAULT.value] * len(
yaml_values[MODEL_S3_BUCKET_YAML_KEY])
# use default shells for regular user and f1 shell for users in F1_SHELL_USERS_LIST
else:
body_shell_types = [
BodyShellType.F1_2021.value if racer_alias
in F1_SHELL_USERS_LIST else BodyShellType.DEFAULT.value
for racer_alias in yaml_values[RACER_NAME_YAML_KEY]
]
yaml_dict[BODY_SHELL_TYPE_YAML_KEY] = body_shell_types
# override local yaml file with updated BODY_SHELL_TYPE
with open(local_yaml_path, 'w') as yaml_file:
yaml.dump(yaml_dict, yaml_file)
for agent_index, model_s3_bucket in enumerate(
yaml_values[MODEL_S3_BUCKET_YAML_KEY]):
racecar_name = 'racecar_' + str(agent_index) if len(
yaml_values[MODEL_S3_BUCKET_YAML_KEY]) > 1 else 'racecar'
# Make a local folder with the racecar name to download the model_metadata.json
if not os.path.exists(os.path.join(os.getcwd(), racecar_name)):
os.makedirs(os.path.join(os.getcwd(), racecar_name))
local_model_metadata_path = os.path.abspath(
os.path.join(os.path.join(os.getcwd(), racecar_name),
'model_metadata.json'))
json_key = yaml_values[MODEL_METADATA_FILE_S3_YAML_KEY][
agent_index]
json_key = json_key.replace('s3://{}/'.format(model_s3_bucket), '')
s3_client.download_file(Bucket=model_s3_bucket,
Key=json_key,
Filename=local_model_metadata_path)
sensors, _, simapp_version = utils_parse_model_metadata.parse_model_metadata(
local_model_metadata_path)
simapp_versions.append(simapp_version)
if Input.STEREO.value in sensors:
racecars_with_stereo_cameras.append(racecar_name)
if Input.LIDAR.value in sensors or Input.SECTOR_LIDAR.value in sensors:
racecars_with_lidars.append(racecar_name)
cmd = [
''.join(("roslaunch deepracer_simulation_environment {} ".format(
launch_name), "local_yaml_path:={} ".format(local_yaml_path),
"racecars_with_stereo_cameras:={} ".format(
','.join(racecars_with_stereo_cameras)),
"racecars_with_lidars:={} ".format(
','.join(racecars_with_lidars)),
"multicar:={} ".format(multicar),
"body_shell_types:={} ".format(
','.join(body_shell_types)),
"simapp_versions:={} ".format(','.join(simapp_versions)),
"f1:={}".format(is_f1)))
]
Popen(cmd, shell=True, executable="/bin/bash")
except botocore.exceptions.ClientError as ex:
log_and_exit(
"Download params and launch of agent node failed: s3_bucket: {}, yaml_key: {}, {}"
.format(s3_bucket, yaml_key, ex),
SIMAPP_SIMULATION_WORKER_EXCEPTION, SIMAPP_EVENT_ERROR_CODE_400)
except botocore.exceptions.EndpointConnectionError:
log_and_exit("No Internet connection or s3 service unavailable",
SIMAPP_SIMULATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_500)
except Exception as ex:
log_and_exit(
"Download params and launch of agent node failed: s3_bucket: {}, yaml_key: {}, {}"
.format(s3_bucket, yaml_key, ex),
SIMAPP_SIMULATION_WORKER_EXCEPTION, SIMAPP_EVENT_ERROR_CODE_500)
