def _download_model_metadata(self):
"""Attempt to download model metadata from s3.
Raises:
GenericNonFatalException: An non fatal exception which we will
catch and proceed with work loop.
Returns:
sensors, version, model_metadata: The needed information from model metadata.
"""
model_metadata_s3_key = get_s3_key(
self._current_racer.inputModel.s3KeyPrefix, MODEL_METADATA_S3_POSTFIX
)
try:
model_metadata = ModelMetadata(
bucket=self._current_racer.inputModel.s3BucketName,
s3_key=model_metadata_s3_key,
region_name=self._region,
local_path=MODEL_METADATA_LOCAL_PATH_FORMAT.format(self._agent_name),
)
model_metadata_info = model_metadata.get_model_metadata_info()
sensors = model_metadata_info[ModelMetadataKeys.SENSOR.value]
simapp_version = model_metadata_info[ModelMetadataKeys.VERSION.value]
except botocore.exceptions.ClientError as err:
error_msg = "[s3] Client Error: Failed to download model_metadata file: \
s3_bucket: {}, s3_key: {}, {}.".format(
self._current_racer.inputModel.s3BucketName, model_metadata_s3_key, err
)
raise GenericNonFatalException(
error_msg=error_msg,
error_code=SIMAPP_EVENT_ERROR_CODE_400,
error_name=SIMAPP_EVENT_USER_ERROR,
)
except Exception as err:
error_msg = "[s3] System Error: Failed to download model_metadata file: \
s3_bucket: {}, s3_key: {}, {}.".format(
self._current_racer.inputModel.s3BucketName, model_metadata_s3_key, err
)
raise GenericNonFatalException(
error_msg=error_msg,
error_code=SIMAPP_EVENT_ERROR_CODE_500,
error_name=SIMAPP_EVENT_SYSTEM_ERROR,
)
return sensors, simapp_version, model_metadata
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))
# download model metadata
model_metadata = ModelMetadata(bucket=s3_bucket,
s3_key=get_s3_key(
s3_prefix, MODEL_METADATA_S3_POSTFIX),
region_name=aws_region,
local_path=MODEL_METADATA_LOCAL_PATH)
# Create model local path
os.makedirs(LOCAL_MODEL_DIR)
try:
# Handle backward compatibility
model_metadata_info = model_metadata.get_model_metadata_info()
observation_list = model_metadata_info[ModelMetadataKeys.SENSOR.value]
version = model_metadata_info[ModelMetadataKeys.VERSION.value]
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)
checkpoint = Checkpoint(bucket=s3_bucket,
s3_prefix=s3_prefix,
region_name=args.aws_region,
agent_name='agent',
checkpoint_dir=LOCAL_MODEL_DIR)
# make coach checkpoint compatible
if version < SIMAPP_VERSION_2 and not checkpoint.rl_coach_checkpoint.is_compatible(
):
checkpoint.rl_coach_checkpoint.make_compatible(
checkpoint.syncfile_ready)
# add checkpoint into checkpoint_dict
checkpoint_dict = {'agent': checkpoint}
agent_config = {
'model_metadata': model_metadata,
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.MODEL_METADATA.value: model_metadata,
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(
checkpoint_dict=checkpoint_dict)
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('-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"))
args, _ = parser.parse_known_args()
s3_client = S3Client(region_name=args.aws_region, max_retry_attempts=0)
# download model metadata
# TODO: replace 'agent' with name of each agent
model_metadata_download = ModelMetadata(
bucket=args.s3_bucket,
s3_key=args.model_metadata_s3_key,
region_name=args.aws_region,
local_path=MODEL_METADATA_LOCAL_PATH_FORMAT.format('agent'))
model_metadata_info = model_metadata_download.get_model_metadata_info()
network_type = model_metadata_info[ModelMetadataKeys.NEURAL_NETWORK.value]
version = model_metadata_info[ModelMetadataKeys.VERSION.value]
# upload model metadata
model_metadata_upload = ModelMetadata(
bucket=args.s3_bucket,
s3_key=get_s3_key(args.s3_prefix, MODEL_METADATA_S3_POSTFIX),
region_name=args.aws_region,
local_path=MODEL_METADATA_LOCAL_PATH_FORMAT.format('agent'))
model_metadata_upload.persist(
s3_kms_extra_args=utils.get_s3_kms_extra_args())
shutil.copy2(model_metadata_download.local_path, SM_MODEL_OUTPUT_DIR)
success_custom_preset = False
if args.preset_s3_key:
preset_local_path = "./markov/presets/preset.py"
try:
s3_client.download_file(bucket=args.s3_bucket,
s3_key=args.preset_s3_key,
local_path=preset_local_path)
success_custom_preset = True
except botocore.exceptions.ClientError:
pass
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)
s3_client.upload_file(
bucket=args.s3_bucket,
s3_key=os.path.normpath("%s/presets/preset.py" %
args.s3_prefix),
local_path=preset_local_path,
s3_kms_extra_args=utils.get_s3_kms_extra_args())
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_download,
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.MODEL_METADATA.value: model_metadata_download,
ConfigParams.REWARD.value: None,
ConfigParams.AGENT_NAME.value: 'racecar'
}
}
agent_list = list()
agent_list.append(create_training_agent(agent_config))
graph_manager, robomaker_hyperparams_json = get_graph_manager(
hp_dict=sm_hyperparams_dict,
agent_list=agent_list,
run_phase_subject=None,
run_type=str(RunType.TRAINER))
# Upload hyperparameters to SageMaker shared s3 bucket
hyperparameters = Hyperparameters(bucket=args.s3_bucket,
s3_key=get_s3_key(
args.s3_prefix,
HYPERPARAMETER_S3_POSTFIX),
region_name=args.aws_region)
hyperparameters.persist(
hyperparams_json=robomaker_hyperparams_json,
s3_kms_extra_args=utils.get_s3_kms_extra_args())
# 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(
bucket=args.s3_bucket,
s3_prefix=args.s3_prefix,
region_name=args.aws_region,
max_sample_count=max_sample_count,
sampling_frequency=int(
sm_hyperparams_dict.get("sampling_frequency", 1)))
graph_manager.sample_collector = sample_collector
# persist IP config from sagemaker to s3
ip_config = IpConfig(bucket=args.s3_bucket,
s3_prefix=args.s3_prefix,
region_name=args.aws_region)
ip_config.persist(s3_kms_extra_args=utils.get_s3_kms_extra_args())
training_algorithm = model_metadata_download.training_algorithm
output_head_format = FROZEN_HEAD_OUTPUT_GRAPH_FORMAT_MAPPING[
training_algorithm]
use_pretrained_model = args.pretrained_s3_bucket and args.pretrained_s3_prefix
# Handle backward compatibility
if use_pretrained_model:
# checkpoint s3 instance for pretrained model
# TODO: replace 'agent' for multiagent training
checkpoint = Checkpoint(bucket=args.pretrained_s3_bucket,
s3_prefix=args.pretrained_s3_prefix,
region_name=args.aws_region,
agent_name='agent',
checkpoint_dir=args.pretrained_checkpoint_dir,
output_head_format=output_head_format)
# make coach checkpoint compatible
if version < SIMAPP_VERSION_2 and not checkpoint.rl_coach_checkpoint.is_compatible(
):
checkpoint.rl_coach_checkpoint.make_compatible(
checkpoint.syncfile_ready)
# get best model checkpoint string
model_checkpoint_name = checkpoint.deepracer_checkpoint_json.get_deepracer_best_checkpoint(
)
# Select the best checkpoint model by uploading rl coach .coach_checkpoint file
checkpoint.rl_coach_checkpoint.update(
model_checkpoint_name=model_checkpoint_name,
s3_kms_extra_args=utils.get_s3_kms_extra_args())
# add checkpoint into checkpoint_dict
checkpoint_dict = {'agent': checkpoint}
# load pretrained model
ds_params_instance_pretrained = S3BotoDataStoreParameters(
checkpoint_dict=checkpoint_dict)
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
# checkpoint s3 instance for training model
checkpoint = Checkpoint(bucket=args.s3_bucket,
s3_prefix=args.s3_prefix,
region_name=args.aws_region,
agent_name='agent',
checkpoint_dir=args.checkpoint_dir,
output_head_format=output_head_format)
checkpoint_dict = {'agent': checkpoint}
ds_params_instance = S3BotoDataStoreParameters(
checkpoint_dict=checkpoint_dict)
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
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"],
training_algorithm=training_algorithm)
def __init__(self,
queue_url,
aws_region='us-east-1',
race_duration=180,
number_of_trials=3,
number_of_resets=10000,
penalty_seconds=2.0,
off_track_penalty=2.0,
collision_penalty=5.0,
is_continuous=False,
race_type="TIME_TRIAL"):
# constructor arguments
self._model_updater = ModelUpdater.get_instance()
self._deepracer_path = rospkg.RosPack().get_path(
DeepRacerPackages.DEEPRACER_SIMULATION_ENVIRONMENT)
body_shell_path = os.path.join(self._deepracer_path, "meshes", "f1")
self._valid_body_shells = \
set(".".join(f.split(".")[:-1]) for f in os.listdir(body_shell_path) if os.path.isfile(
os.path.join(body_shell_path, f)))
self._valid_body_shells.add(const.BodyShellType.DEFAULT.value)
self._valid_car_colors = set(e.value for e in const.CarColorType
if "f1" not in e.value)
self._num_sectors = int(rospy.get_param("NUM_SECTORS", "3"))
self._queue_url = queue_url
self._region = aws_region
self._number_of_trials = number_of_trials
self._number_of_resets = number_of_resets
self._penalty_seconds = penalty_seconds
self._off_track_penalty = off_track_penalty
self._collision_penalty = collision_penalty
self._is_continuous = is_continuous
self._race_type = race_type
self._is_save_simtrace_enabled = False
self._is_save_mp4_enabled = False
self._is_event_end = False
self._done_condition = any
self._race_duration = race_duration
self._enable_domain_randomization = False
# sqs client
# The boto client errors out after polling for 1 hour.
self._sqs_client = SQSClient(queue_url=self._queue_url,
region_name=self._region,
max_num_of_msg=MAX_NUM_OF_SQS_MESSAGE,
wait_time_sec=SQS_WAIT_TIME_SEC,
session=refreshed_session(self._region))
self._s3_client = S3Client(region_name=self._region)
# tracking current state information
self._track_data = TrackData.get_instance()
self._start_lane = self._track_data.center_line
# keep track of the racer specific info, e.g. s3 locations, alias, car color etc.
self._current_racer = None
# keep track of the current race car we are using. It is always "racecar".
car_model_state = ModelState()
car_model_state.model_name = "racecar"
self._current_car_model_state = car_model_state
self._last_body_shell_type = None
self._last_sensors = None
self._racecar_model = AgentModel()
# keep track of the current control agent we are using
self._current_agent = None
# keep track of the current control graph manager
self._current_graph_manager = None
# Keep track of previous model's name
self._prev_model_name = None
self._hide_position_idx = 0
self._hide_positions = get_hide_positions(race_car_num=1)
self._run_phase_subject = RunPhaseSubject()
self._simtrace_video_s3_writers = []
self._local_model_directory = './checkpoint'
# virtual event only have single agent, so set agent_name to "agent"
self._agent_name = "agent"
# camera manager
self._camera_manager = CameraManager.get_instance()
# setting up virtual event top and follow camera in CameraManager
# virtual event configure camera does not need to wait for car to spawm because
# follow car camera is not tracking any car initially
self._main_cameras, self._sub_camera = configure_camera(
namespaces=[VIRTUAL_EVENT], is_wait_for_model=False)
self._spawn_cameras()
# pop out all cameras after configuration to prevent camera from moving
self._camera_manager.pop(namespace=VIRTUAL_EVENT)
dummy_metrics_s3_config = {
MetricsS3Keys.METRICS_BUCKET.value: "dummy-bucket",
MetricsS3Keys.METRICS_KEY.value: "dummy-key",
MetricsS3Keys.REGION.value: self._region
}
self._eval_metrics = EvalMetrics(
agent_name=self._agent_name,
s3_dict_metrics=dummy_metrics_s3_config,
is_continuous=self._is_continuous,
pause_time_before_start=PAUSE_TIME_BEFORE_START)
# upload a default best sector time for all sectors with time inf for each sector
# if there is not best sector time existed in s3
# use the s3 bucket and prefix for yaml file stored as environment variable because
# here is SimApp use only. For virtual event there is no s3 bucket and prefix past
# through yaml file. All are past through sqs. For simplicity, reuse the yaml s3 bucket
# and prefix environment variable.
virtual_event_best_sector_time = VirtualEventBestSectorTime(
bucket=os.environ.get("YAML_S3_BUCKET", ''),
s3_key=get_s3_key(os.environ.get("YAML_S3_PREFIX", ''),
SECTOR_TIME_S3_POSTFIX),
region_name=os.environ.get("APP_REGION", "us-east-1"),
local_path=SECTOR_TIME_LOCAL_PATH)
response = virtual_event_best_sector_time.list()
# this is used to handle situation such as robomaker job crash, so the next robomaker job
# can catch the best sector time left over from crashed job
if "Contents" not in response:
virtual_event_best_sector_time.persist(
body=json.dumps({
SECTOR_X_FORMAT.format(idx + 1): float("inf")
for idx in range(self._num_sectors)
}),
s3_kms_extra_args=utils.get_s3_kms_extra_args())
# ROS service to indicate all the robomaker markov packages are ready for consumption
signal_robomaker_markov_package_ready()
PhaseObserver('/agent/training_phase', self._run_phase_subject)
# setup mp4 services
self._setup_mp4_services()
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()
logger.info("S3 bucket: %s", args.s3_bucket)
logger.info("S3 prefix: %s", args.s3_prefix)
# Download and import reward function
# TODO: replace 'agent' with name of each agent for multi-agent training
reward_function_file = RewardFunction(
bucket=args.s3_bucket,
s3_key=args.reward_file_s3_key,
region_name=args.aws_region,
local_path=REWARD_FUCTION_LOCAL_PATH_FORMAT.format('agent'))
reward_function = reward_function_file.get_reward_function()
# Instantiate Cameras
configure_camera(namespaces=['racecar'])
preset_file_success, _ = download_custom_files_if_present(
s3_bucket=args.s3_bucket,
s3_prefix=args.s3_prefix,
aws_region=args.aws_region)
# download model metadata
# TODO: replace 'agent' with name of each agent
model_metadata = ModelMetadata(
bucket=args.s3_bucket,
s3_key=args.model_metadata_s3_key,
region_name=args.aws_region,
local_path=MODEL_METADATA_LOCAL_PATH_FORMAT.format('agent'))
model_metadata_info = model_metadata.get_model_metadata_info()
version = model_metadata_info[ModelMetadataKeys.VERSION.value]
agent_config = {
'model_metadata': model_metadata,
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.MODEL_METADATA.value:
model_metadata,
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
metrics_key = rospy.get_param('METRICS_S3_OBJECT_KEY')
if args.num_workers > 1 and args.rollout_idx > 0:
key_tuple = os.path.splitext(metrics_key)
metrics_key = "{}_{}{}".format(key_tuple[0], str(args.rollout_idx),
key_tuple[1])
metrics_s3_config = {
MetricsS3Keys.METRICS_BUCKET.value:
rospy.get_param('METRICS_S3_BUCKET'),
MetricsS3Keys.METRICS_KEY.value: metrics_key,
MetricsS3Keys.REGION.value: rospy.get_param('AWS_REGION')
}
run_phase_subject = RunPhaseSubject()
agent_list = list()
#TODO: replace agent for multi agent training
# checkpoint s3 instance
# TODO replace agent with agent_0 and so on for multiagent case
checkpoint = Checkpoint(bucket=args.s3_bucket,
s3_prefix=args.s3_prefix,
region_name=args.aws_region,
agent_name='agent',
checkpoint_dir=args.checkpoint_dir)
agent_list.append(
create_rollout_agent(
agent_config,
TrainingMetrics(
agent_name='agent',
s3_dict_metrics=metrics_s3_config,
deepracer_checkpoint_json=checkpoint.deepracer_checkpoint_json,
ckpnt_dir=os.path.join(args.checkpoint_dir, 'agent'),
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')
simtrace_video_s3_writers = []
#TODO: replace 'agent' with 'agent_0' for multi agent training and
# mp4_s3_object_prefix, mp4_s3_bucket will be a list, so need to access with index
if simtrace_s3_bucket:
simtrace_video_s3_writers.append(
SimtraceVideo(
upload_type=SimtraceVideoNames.SIMTRACE_TRAINING.value,
bucket=simtrace_s3_bucket,
s3_prefix=simtrace_s3_object_prefix,
region_name=aws_region,
local_path=SIMTRACE_TRAINING_LOCAL_PATH_FORMAT.format(
'agent')))
if mp4_s3_bucket:
simtrace_video_s3_writers.extend([
SimtraceVideo(
upload_type=SimtraceVideoNames.PIP.value,
bucket=mp4_s3_bucket,
s3_prefix=mp4_s3_object_prefix,
region_name=aws_region,
local_path=CAMERA_PIP_MP4_LOCAL_PATH_FORMAT.format('agent')),
SimtraceVideo(
upload_type=SimtraceVideoNames.DEGREE45.value,
bucket=mp4_s3_bucket,
s3_prefix=mp4_s3_object_prefix,
region_name=aws_region,
local_path=CAMERA_45DEGREE_LOCAL_PATH_FORMAT.format('agent')),
SimtraceVideo(
upload_type=SimtraceVideoNames.TOPVIEW.value,
bucket=mp4_s3_bucket,
s3_prefix=mp4_s3_object_prefix,
region_name=aws_region,
local_path=CAMERA_TOPVIEW_LOCAL_PATH_FORMAT.format('agent'))
])
# TODO: replace 'agent' with specific agent name for multi agent training
ip_config = IpConfig(bucket=args.s3_bucket,
s3_prefix=args.s3_prefix,
region_name=args.aws_region,
local_path=IP_ADDRESS_LOCAL_PATH.format('agent'))
redis_ip = ip_config.get_ip_config()
# Download hyperparameters from SageMaker shared s3 bucket
# TODO: replace 'agent' with name of each agent
hyperparameters = Hyperparameters(
bucket=args.s3_bucket,
s3_key=get_s3_key(args.s3_prefix, HYPERPARAMETER_S3_POSTFIX),
region_name=args.aws_region,
local_path=HYPERPARAMETER_LOCAL_PATH_FORMAT.format('agent'))
sm_hyperparams_dict = hyperparameters.get_hyperparameters_dict()
enable_domain_randomization = utils.str2bool(
rospy.get_param('ENABLE_DOMAIN_RANDOMIZATION', False))
# Make the clients that will allow us to pause and unpause the physics
rospy.wait_for_service('/gazebo/pause_physics_dr')
rospy.wait_for_service('/gazebo/unpause_physics_dr')
pause_physics = ServiceProxyWrapper('/gazebo/pause_physics_dr', Empty)
unpause_physics = ServiceProxyWrapper('/gazebo/unpause_physics_dr', Empty)
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,
pause_physics=pause_physics,
unpause_physics=unpause_physics)
# 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()
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
checkpoint_dict = {'agent': checkpoint}
ds_params_instance = S3BotoDataStoreParameters(
checkpoint_dict=checkpoint_dict)
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,
simtrace_video_s3_writers=simtrace_video_s3_writers,
pause_physics=pause_physics,
unpause_physics=unpause_physics)
def main():
""" Main function for evaluation 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)
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]):
log_and_exit(
"Eval worker error: Incorrect arguments passed: {}".format(
validate_list), SIMAPP_SIMULATION_WORKER_EXCEPTION,
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()
checkpoint_dict = dict()
simtrace_video_s3_writers = []
start_positions = get_start_positions(len(arg_s3_bucket))
done_condition = utils.str_to_done_condition(
rospy.get_param("DONE_CONDITION", any))
park_positions = utils.pos_2d_str_to_list(
rospy.get_param("PARK_POSITIONS", []))
# if not pass in park positions for all done condition case, use default
if not park_positions:
park_positions = [DEFAULT_PARK_POSITION for _ in arg_s3_bucket]
for agent_index, _ 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]
# download model metadata
model_metadata = ModelMetadata(
bucket=arg_s3_bucket[agent_index],
s3_key=get_s3_key(arg_s3_prefix[agent_index],
MODEL_METADATA_S3_POSTFIX),
region_name=args.aws_region,
local_path=MODEL_METADATA_LOCAL_PATH_FORMAT.format(agent_name))
model_metadata_info = model_metadata.get_model_metadata_info()
version = model_metadata_info[ModelMetadataKeys.VERSION.value]
# checkpoint s3 instance
checkpoint = Checkpoint(bucket=arg_s3_bucket[agent_index],
s3_prefix=arg_s3_prefix[agent_index],
region_name=args.aws_region,
agent_name=agent_name,
checkpoint_dir=args.local_model_directory)
# make coach checkpoint compatible
if version < SIMAPP_VERSION_2 and not checkpoint.rl_coach_checkpoint.is_compatible(
):
checkpoint.rl_coach_checkpoint.make_compatible(
checkpoint.syncfile_ready)
# get best model checkpoint string
model_checkpoint_name = checkpoint.deepracer_checkpoint_json.get_deepracer_best_checkpoint(
)
# Select the best checkpoint model by uploading rl coach .coach_checkpoint file
checkpoint.rl_coach_checkpoint.update(
model_checkpoint_name=model_checkpoint_name,
s3_kms_extra_args=utils.get_s3_kms_extra_args())
checkpoint_dict[agent_name] = checkpoint
agent_config = {
'model_metadata': model_metadata,
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.MODEL_METADATA.value:
model_metadata,
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,
ConfigParams.START_POSITION.value:
start_positions[agent_index],
ConfigParams.DONE_CONDITION.value:
done_condition
}
}
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
}
aws_region = rospy.get_param('AWS_REGION', args.aws_region)
if simtrace_s3_bucket:
simtrace_video_s3_writers.append(
SimtraceVideo(
upload_type=SimtraceVideoNames.SIMTRACE_EVAL.value,
bucket=simtrace_s3_bucket[agent_index],
s3_prefix=simtrace_s3_object_prefix[agent_index],
region_name=aws_region,
local_path=SIMTRACE_EVAL_LOCAL_PATH_FORMAT.format(
agent_name)))
if mp4_s3_bucket:
simtrace_video_s3_writers.extend([
SimtraceVideo(
upload_type=SimtraceVideoNames.PIP.value,
bucket=mp4_s3_bucket[agent_index],
s3_prefix=mp4_s3_object_prefix[agent_index],
region_name=aws_region,
local_path=CAMERA_PIP_MP4_LOCAL_PATH_FORMAT.format(
agent_name)),
SimtraceVideo(
upload_type=SimtraceVideoNames.DEGREE45.value,
bucket=mp4_s3_bucket[agent_index],
s3_prefix=mp4_s3_object_prefix[agent_index],
region_name=aws_region,
local_path=CAMERA_45DEGREE_LOCAL_PATH_FORMAT.format(
agent_name)),
SimtraceVideo(
upload_type=SimtraceVideoNames.TOPVIEW.value,
bucket=mp4_s3_bucket[agent_index],
s3_prefix=mp4_s3_object_prefix[agent_index],
region_name=aws_region,
local_path=CAMERA_TOPVIEW_LOCAL_PATH_FORMAT.format(
agent_name))
])
run_phase_subject = RunPhaseSubject()
agent_list.append(
create_rollout_agent(
agent_config,
EvalMetrics(agent_name, metrics_s3_config, args.is_continuous),
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)
enable_domain_randomization = utils.str2bool(
rospy.get_param('ENABLE_DOMAIN_RANDOMIZATION', False))
sm_hyperparams_dict = {}
# Make the clients that will allow us to pause and unpause the physics
rospy.wait_for_service('/gazebo/pause_physics_dr')
rospy.wait_for_service('/gazebo/unpause_physics_dr')
pause_physics = ServiceProxyWrapper('/gazebo/pause_physics_dr', Empty)
unpause_physics = ServiceProxyWrapper('/gazebo/unpause_physics_dr', Empty)
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,
done_condition=done_condition,
pause_physics=pause_physics,
unpause_physics=unpause_physics)
ds_params_instance = S3BotoDataStoreParameters(
checkpoint_dict=checkpoint_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
evaluation_worker(graph_manager=graph_manager,
number_of_trials=args.number_of_trials,
task_parameters=task_parameters,
simtrace_video_s3_writers=simtrace_video_s3_writers,
is_continuous=args.is_continuous,
park_positions=park_positions,
race_type=args.race_type,
pause_physics=pause_physics,
unpause_physics=unpause_physics)
def __init__(self, current_sector=0):
"""initialize Run state and log
Args:
current_sector (int): current sector index 0-based.
"""
self._total_sectors = int(rospy.get_param("NUM_SECTORS", "3"))
if self._total_sectors == 0:
log_and_exit(
"[virtual event]: Virtual event run state with 0 total sectors. \
This needs to be at least 1",
SIMAPP_SIMULATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_500)
# current sector index 0 is sector1 and so on so forth
self._current_sector = current_sector % self._total_sectors
self._target_progress = (100.00 / self._total_sectors) * (
self._current_sector + 1)
self._total_laps = int(rospy.get_param("NUMBER_OF_TRIALS", 3))
self._race_duration = int(
rospy.get_param("RACE_DURATION", DEFAULT_RACE_DURATION)) * 1000
# VirtualEventBestSectorTime S3 upload instance
# use the s3 bucket and prefix for yaml file stored as environment variable because
# here is SimApp use only. For virtual event there is no s3 bucket and prefix past
# through yaml file. All are past through sqs. For simplicity, reuse the yaml s3 bucket
# and prefix environment variable.
self._virtual_event_best_sector_time = VirtualEventBestSectorTime(
bucket=os.environ.get("YAML_S3_BUCKET", ''),
s3_key=get_s3_key(os.environ.get("YAML_S3_PREFIX", ''),
SECTOR_TIME_S3_POSTFIX),
region_name=os.environ.get("APP_REGION", "us-east-1"),
local_path=SECTOR_TIME_LOCAL_PATH)
# Go icon image
self._icon_image = utils.get_image(
VirtualEventIconographicPngs.GO.value)
self._icon_image = cv2.cvtColor(self._icon_image, cv2.COLOR_RGBA2BGRA)
# init number of sectors to plot
# for 3 sectors example
# if racer is at sector 1 (idx 0): plot sector 1, 2, and 3
# if racer is at sector 2 (idx 1): plot sector 1
# if racer is at sector 3 (idx 2): plot sector 1, and 2
num_sectors_to_plot = self._current_sector
if self._current_sector == 0:
num_sectors_to_plot = self._total_sectors
# init number of sectors to plot
self._sectors = [
SECTOR_X_FORMAT.format(idx + 1)
for idx in range(num_sectors_to_plot)
]
# sector format string for best session, best personal, and current personal
self._best_session_format = SECTOR_TIME_FORMAT_DICT[
TrackSectorTime.BEST_SESSION]
self._best_personal_format = SECTOR_TIME_FORMAT_DICT[
TrackSectorTime.BEST_PERSONAL]
self._current_personal_format = SECTOR_TIME_FORMAT_DICT[
TrackSectorTime.CURRENT_PERSONAL]
LOG.info(
"[virtual event]: video edit state at {} for sector {} with target progress {}\
".format(self, self._current_sector + 1, self._target_progress))
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:
s3_endpoint_url = os.environ.get("S3_ENDPOINT_URL", None)
if s3_endpoint_url is not None:
logging.info('Endpoint URL {}'.format(s3_endpoint_url))
rospy.set_param('S3_ENDPOINT_URL', s3_endpoint_url)
if AgentType.ROLLOUT.value in launch_name:
# For rollout, launch_name is "rollout_rl_agent.launch"
agent_type = AgentType.ROLLOUT.value
elif AgentType.EVALUATION.value in launch_name:
# For eval, launch_name is "evaluation_rl_agent.launch"
agent_type = AgentType.EVALUATION.value
elif AgentType.VIRTUAL_EVENT.value in launch_name:
# For virtual event, launch_name is "virtual_event_rl_agent.launch"
agent_type = AgentType.VIRTUAL_EVENT.value
else:
log_and_exit(
"Unknown agent type in launch file: {}".format(launch_name),
SIMAPP_SIMULATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_500)
# download yaml file
yaml_key = get_s3_key(s3_prefix, s3_yaml_name)
yaml_file = YamlFile(
agent_type=agent_type,
bucket=s3_bucket,
s3_key=yaml_key,
region_name=s3_region,
s3_endpoint_url=s3_endpoint_url,
local_path=YAML_LOCAL_PATH_FORMAT.format(s3_yaml_name))
yaml_file.get_yaml_values()
if not agent_type == AgentType.VIRTUAL_EVENT.value:
# 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_file.model_s3_buckets):
racecar_name = 'racecar_{}'.format(agent_index) \
if yaml_file.is_multicar else 'racecar'
json_key = yaml_file.model_metadata_s3_keys[agent_index]
# download model metadata
model_metadata = ModelMetadata(
bucket=model_s3_bucket,
s3_key=json_key,
region_name=s3_region,
s3_endpoint_url=s3_endpoint_url,
local_path=MODEL_METADATA_LOCAL_PATH_FORMAT.format(
racecar_name))
model_metadata_info = model_metadata.get_model_metadata_info()
sensors = model_metadata_info[ModelMetadataKeys.SENSOR.value]
simapp_version = model_metadata_info[
ModelMetadataKeys.VERSION.value]
simapp_versions.append(str(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 or \
Input.DISCRETIZED_SECTOR_LIDAR.value in sensors:
racecars_with_lidars.append(racecar_name)
cmd = [
''.join(
("roslaunch deepracer_simulation_environment {} ".format(
launch_name), "local_yaml_path:={} ".format(
yaml_file.local_path),
"racecars_with_stereo_cameras:={} ".format(
','.join(racecars_with_stereo_cameras)),
"racecars_with_lidars:={} ".format(
','.join(racecars_with_lidars)),
"multicar:={} ".format(yaml_file.is_multicar),
"body_shell_types:={} ".format(','.join(
yaml_file.body_shell_types)),
"simapp_versions:={} ".format(','.join(simapp_versions)),
"f1:={} ".format(yaml_file.is_f1),
"publish_to_kinesis_stream:={} ".format(
not yaml_file.is_leaderboard_job)))
]
else:
# Note: SimApp Version is default to 4.0: virtual event only have a single body_shell_types
cmd = [
''.join(
("roslaunch deepracer_simulation_environment {} ".format(
launch_name),
"local_yaml_path:={} ".format(yaml_file.local_path),
"body_shell_types:={} ".format(
yaml_file.body_shell_types),
"simapp_versions:={} ".format('4.0'),
"f1:={} ".format(yaml_file.is_f1),
"kinesis_webrtc_signaling_channel_name:={} ".format(
yaml_file.kinesis_webrtc_signaling_channel_name),
"publish_to_kinesis_stream:={} ".format(
not yaml_file.is_leaderboard_job)))
]
Popen(cmd, shell=True, executable="/bin/bash")
except botocore.exceptions.ClientError as ex:
log_and_exit(
"Download params and launch of agent node S3 ClientError: s3_bucket: {}, yaml_key: {}, {}"
.format(s3_bucket, yaml_key, ex),
SIMAPP_SIMULATION_WORKER_EXCEPTION, SIMAPP_EVENT_ERROR_CODE_500)
except botocore.exceptions.EndpointConnectionError:
log_and_exit("No Internet connection or s3 service unavailable",
SIMAPP_SIMULATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_500)
except ValueError as ex:
log_and_exit("User modified model_metadata.json: {}".format(ex),
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 __init__(self, racecar_name, racecar_info, race_type):
""" Initializing the required data for the head to bot, time-trail. This is used for single agent
Arguments:
racecar_name (str): racecar name in string
racecars_info (list): list of dict having information of the agent
race_type (str): Since this class is reused for all the different race_type
"""
# race duration in milliseconds
self._world_name = rospy.get_param("WORLD_NAME")
self.num_sectors = int(rospy.get_param("NUM_SECTORS", "3"))
self.race_duration = int(
rospy.get_param("RACE_DURATION", DEFAULT_RACE_DURATION)) * 1000
self.racecar_info = racecar_info
self.race_type = race_type
racecar_index = get_racecar_idx(racecar_name)
self.racecar_index = racecar_index if racecar_index else 0
# Store the font which we will use to write the phase with
self.amazon_ember_regular_28px = utils.get_font(
'AmazonEmber-Regular', 28)
self.amazon_ember_regular_14px = utils.get_font(
'AmazonEmber-Regular', 14)
# The track image as iconography
self.track_icongraphy_img = utils.get_track_iconography_image()
# Track image offset
self.track_loc_offset = VirtualEventXYPixelLoc.TRACK_IMG_VIRTUAL_EVENT_LOC.value
self._track_x_min = None
self._track_x_max = None
self._track_y_min = None
self._track_y_max = None
# Gradient overlay image with track and virtual event mock
gradient_img_path = VirtualEventIconographicPngs.OVERLAY_PNG.value
self.gradient_img = self._plot_track_on_gradient(gradient_img_path)
# Time remaining text
loc_x, loc_y = VirtualEventXYPixelLoc.TIME_REMAINING_TEXT.value
self.gradient_img = utils.write_text_on_image(
image=self.gradient_img,
text="TIME REMAINING",
loc=(loc_x, loc_y),
font=self.amazon_ember_regular_14px,
font_color=RaceCarColorToRGB.White.value,
font_shadow_color=RaceCarColorToRGB.Black.value)
# Speed text
loc_x, loc_y = VirtualEventXYPixelLoc.SPEED_TEXT.value
self.gradient_img = utils.write_text_on_image(
image=self.gradient_img,
text="m/s",
loc=(loc_x, loc_y),
font=self.amazon_ember_regular_14px,
font_color=RaceCarColorToRGB.White.value,
font_shadow_color=RaceCarColorToRGB.Black.value)
# Reset text
loc_x, loc_y = VirtualEventXYPixelLoc.RESET_TEXT.value
self.gradient_img = utils.write_text_on_image(
image=self.gradient_img,
text="RESET",
loc=(loc_x, loc_y),
font=self.amazon_ember_regular_14px,
font_color=RaceCarColorToRGB.White.value,
font_shadow_color=RaceCarColorToRGB.Black.value)
# current lap time text
loc_x, loc_y = VirtualEventXYPixelLoc.CURRENT_LAP_TIME_TEXT.value
self.gradient_img = utils.write_text_on_image(
image=self.gradient_img,
text="CURRENT LAP TIME",
loc=(loc_x, loc_y),
font=self.amazon_ember_regular_14px,
font_color=RaceCarColorToRGB.White.value,
font_shadow_color=RaceCarColorToRGB.Black.value)
# best lap time text
loc_x, loc_y = VirtualEventXYPixelLoc.BEST_LAP_TIME_TEXT.value
self.gradient_img = utils.write_text_on_image(
image=self.gradient_img,
text="BEST LAP TIME",
loc=(loc_x, loc_y),
font=self.amazon_ember_regular_14px,
font_color=RaceCarColorToRGB.White.value,
font_shadow_color=RaceCarColorToRGB.Black.value)
# apply graident
self.gradient_alpha_rgb_mul, self.one_minus_gradient_alpha = utils.get_gradient_values(
self.gradient_img)
# Top camera information
top_camera_info = utils.get_top_camera_info()
self.top_view_graphics = TopViewGraphics(
top_camera_info.horizontal_fov,
top_camera_info.padding_pct,
top_camera_info.image_width,
top_camera_info.image_height,
racecar_info,
is_virtual_event=True)
# virtual event image editting state machine
self._image_edit_fsm = FSM(initial_state=VirtualEventWaitState())
# if best sector time download from s3 failed. Then, initialize best sector time as None
# and not display sector color
self._sector_times = {}
# declare sector images
self._sectors_img_dict = {}
for idx in range(self.num_sectors):
sector = SECTOR_X_FORMAT.format(idx + 1)
sector_color_img_dict = utils.init_sector_img_dict(
world_name=self._world_name, sector=sector)
self._sectors_img_dict[sector] = sector_color_img_dict
# use the s3 bucket and prefix for yaml file stored as environment variable because
# here is SimApp use only. For virtual event there is no s3 bucket and prefix past
# through yaml file. All are past through sqs. For simplicity, reuse the yaml s3 bucket
# and prefix environment variable.
self._virtual_event_best_sector_time = VirtualEventBestSectorTime(
bucket=os.environ.get("YAML_S3_BUCKET", ''),
s3_key=get_s3_key(os.environ.get("YAML_S3_PREFIX", ''),
SECTOR_TIME_S3_POSTFIX),
region_name=os.environ.get("APP_REGION", "us-east-1"),
local_path=SECTOR_TIME_LOCAL_PATH)
self._sector_times.update(
self._virtual_event_best_sector_time.get_sector_time(
num_sectors=self.num_sectors))
# declare default best personal and current persoanl time to inf
for idx in range(self.num_sectors):
sector = SECTOR_X_FORMAT.format(idx + 1)
self._sector_times[SECTOR_TIME_FORMAT_DICT[
TrackSectorTime.BEST_PERSONAL].format(sector)] = float("inf")
self._sector_times[SECTOR_TIME_FORMAT_DICT[
TrackSectorTime.CURRENT_PERSONAL].format(sector)] = float(
"inf")
self._curr_lap_time = 0
self._last_eval_time = 0
self._curr_progress = 0
self._last_progress = 0
self._current_lap = 1
# Initializing the fader behaviour to pre-compute the gradient values
final_fading_image = utils.get_image(
VirtualEventIconographicPngs.FINAL_FADING_IMAGE_50ALPHA.value,
IconographicImageSize.FULL_IMAGE_SIZE.value)
final_fading_image = cv2.cvtColor(final_fading_image,
cv2.COLOR_RGBA2BGRA)
self._fader_obj = Fader(
final_fading_image,
fading_min_percent=VirtualEventFader.FADING_MIN_PERCENT.value,
fading_max_percent=VirtualEventFader.FADING_MAX_PERCENT.value,
num_frames=VirtualEventFader.NUM_FRAMES.value)
