def __init__(self,
bucket,
s3_prefix,
region_name='us-east-1',
s3_endpoint_url=None,
local_dir='./checkpoint/agent',
max_retry_attempts=5,
backoff_time_sec=1.0):
'''This class is for tensorflow model upload and download
Args:
bucket (str): S3 bucket string
s3_prefix (str): S3 prefix string
region_name (str): S3 region name
local_dir (str): local file directory
max_retry_attempts (int): maximum number of retry attempts for S3 download/upload
backoff_time_sec (float): backoff second between each retry
'''
if not bucket or not s3_prefix:
log_and_exit(
"checkpoint S3 prefix or bucket not available for S3. \
bucket: {}, prefix {}".format(bucket, s3_prefix),
SIMAPP_SIMULATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_500)
self._bucket = bucket
self._local_dir = os.path.normpath(
CHECKPOINT_LOCAL_DIR_FORMAT.format(local_dir))
self._s3_key_dir = os.path.normpath(
os.path.join(s3_prefix, CHECKPOINT_POSTFIX_DIR))
self._delete_queue = queue.Queue()
self._s3_client = S3Client(region_name, s3_endpoint_url,
max_retry_attempts, backoff_time_sec)
def __init__(self, bucket, s3_prefix, region_name='us-east-1',
s3_endpoint_url=None,
local_path="./custom_files/agent/ip.json",
max_retry_attempts=5, backoff_time_sec=1.0):
'''ip upload, download, and parse
Args:
bucket (str): s3 bucket
s3_prefix (str): s3 prefix
region_name (str): s3 region name
local_path (str): ip addres json file local path
max_retry_attempts (int): maximum retry attempts
backoff_time_sec (float): retry backoff time in seconds
'''
if not s3_prefix or not bucket:
log_and_exit("Ip config S3 prefix or bucket not available for S3. \
bucket: {}, prefix: {}".format(bucket, s3_prefix),
SIMAPP_SIMULATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_500)
self._bucket = bucket
self._s3_ip_done_key = os.path.normpath(os.path.join(
s3_prefix,
IP_DONE_POSTFIX))
self._s3_ip_address_key = os.path.normpath(os.path.join(
s3_prefix,
IP_ADDRESS_POSTFIX))
self._local_path = local_path
self._s3_client = S3Client(region_name,
s3_endpoint_url,
max_retry_attempts,
backoff_time_sec)
self._ip_file = None
def __init__(self,
upload_type,
bucket,
s3_prefix,
region_name="us-east-1",
local_path="./custom_files/iteration_data/\
agent/file",
s3_endpoint_url=None,
max_retry_attempts=5,
backoff_time_sec=1.0):
'''This class is for all s3 simtrace and video upload
Args:
upload_type (str): upload simtrace or video type
bucket (str): S3 bucket string
s3_prefix (str): S3 prefix string
region_name (str): S3 region name
local_path (str): file local path
max_retry_attempts (int): maximum number of retry attempts for S3 download/upload
backoff_time_sec (float): backoff second between each retry
'''
self._upload_type = upload_type
self._bucket = bucket
self._s3_key = os.path.normpath(
os.path.join(s3_prefix,
SIMTRACE_VIDEO_POSTFIX_DICT[self._upload_type]))
self._local_path = local_path
self._upload_num = 0
self._s3_client = S3Client(region_name, s3_endpoint_url,
max_retry_attempts, backoff_time_sec)
def __init__(self, bucket, s3_key, region_name="us-east-1",
s3_endpoint_url=None,
local_path="./custom_files/agent/model_metadata.json",
max_retry_attempts=5, backoff_time_sec=1.0):
'''Model metadata upload, download, and parse
Args:
bucket (str): S3 bucket string
s3_key: (str): S3 key string.
region_name (str): S3 region name
local_path (str): file local path
max_retry_attempts (int): maximum number of retry attempts for S3 download/upload
backoff_time_sec (float): backoff second between each retry
'''
# check s3 key and s3 bucket exist
if not bucket or not s3_key:
log_and_exit("model_metadata S3 key or bucket not available for S3. \
bucket: {}, key {}"
.format(bucket, s3_key),
SIMAPP_SIMULATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_500)
self._bucket = bucket
# Strip the s3://<bucket> from uri, if s3_key past in as uri
self._s3_key = s3_key.replace('s3://{}/'.format(self._bucket), '')
self._local_path = local_path
self._local_dir = os.path.dirname(self._local_path)
self._model_metadata = None
self._s3_client = S3Client(region_name,
s3_endpoint_url,
max_retry_attempts,
backoff_time_sec)
def __init__(self,
bucket,
s3_prefix,
region_name,
s3_endpoint_url=None,
max_sample_count=None,
sampling_frequency=None,
max_retry_attempts=5,
backoff_time_sec=1.0):
'''Sample Collector class to collect sample and persist to S3.
Args:
bucket (str): S3 bucket string
s3_prefix (str): S3 prefix string
region_name (str): S3 region name
max_sample_count (int): max sample count
sampling_frequency (int): sampleing frequency
max_retry_attempts (int): maximum number of retry attempts for S3 download/upload
backoff_time_sec (float): backoff second between each retry
'''
self.max_sample_count = max_sample_count or 0
self.sampling_frequency = sampling_frequency or 1
if self.sampling_frequency < 1:
err_msg = "sampling_frequency must be larger or equal to 1. (Given: {})".format(
self.sampling_frequency)
raise GenericTrainerException(err_msg)
self.s3_prefix = s3_prefix
self._cur_sample_count = 0
self._cur_frequency = 0
self._bucket = bucket
self._s3_client = S3Client(region_name, s3_endpoint_url,
max_retry_attempts, backoff_time_sec)
def __init__(self,
syncfile_type,
bucket,
s3_prefix,
region_name="us-east-1",
local_dir='./checkpoint',
max_retry_attempts=5,
backoff_time_sec=1.0):
'''This class is for rl coach sync file: .finished, .lock, and .ready
Args:
syncfile_type (str): sync file type
bucket (str): S3 bucket string
s3_prefix (str): S3 prefix string
local_dir (str): local file directory
checkpoint_dir (str): checkpoint directory
max_retry_attempts (int): maximum number of retry attempts for S3 download/upload
backoff_time_sec (float): backoff second between each retry
'''
if not bucket or not s3_prefix:
log_and_exit(
"checkpoint S3 prefix or bucket not available for S3. \
bucket: {}, prefix {}".format(bucket, s3_prefix),
SIMAPP_SIMULATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_500)
self._syncfile_type = syncfile_type
self._bucket = bucket
# deepracer checkpoint json s3 key
self._s3_key = os.path.normpath(
os.path.join(s3_prefix, SYNC_FILES_POSTFIX_DICT[syncfile_type]))
# deepracer checkpoint json local path
self._local_path = os.path.normpath(
SYNC_FILES_LOCAL_PATH_FORMAT_DICT[syncfile_type].format(local_dir))
self._s3_client = S3Client(region_name, max_retry_attempts,
backoff_time_sec)
def __init__(self,
bucket,
s3_key,
region_name='us-east-1',
max_retry_attempts=5,
backoff_time_sec=1.0,
s3_endpoint_url=None):
'''metrics upload
Args:
bucket (str): s3 bucket
s3_key (str): s3 key
region_name (str): s3 region name
max_retry_attempts (int): maximum retry attempts
backoff_time_sec (float): retry backoff time in seconds
'''
if not s3_key or not bucket:
log_and_exit(
"Metrics S3 key or bucket not available for S3. \
bucket: {}, key: {}".format(bucket, s3_key),
SIMAPP_SIMULATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_500)
self._bucket = bucket
self._s3_key = s3_key
self._s3_client = S3Client(region_name, s3_endpoint_url,
max_retry_attempts, backoff_time_sec)
def __init__(self,
bucket,
s3_prefix,
region_name='us-east-1',
local_dir='.checkpoint/agent',
max_retry_attempts=0,
backoff_time_sec=1.0):
'''This class is for deepracer checkpoint json file upload and download
Args:
bucket (str): S3 bucket string
s3_prefix (str): S3 prefix string
region_name (str): S3 region name
local_dir (str): local file directory
max_retry_attempts (int): maximum number of retry attempts for S3 download/upload
backoff_time_sec (float): backoff second between each retry
'''
if not bucket or not s3_prefix:
log_and_exit(
"checkpoint S3 prefix or bucket not available for S3. \
bucket: {}, prefix {}".format(bucket, s3_prefix),
SIMAPP_SIMULATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_500)
self._bucket = bucket
# deepracer checkpoint json s3 key
self._s3_key = os.path.normpath(
os.path.join(s3_prefix, DEEPRACER_CHECKPOINT_KEY_POSTFIX))
# deepracer checkpoint json local path
self._local_path = os.path.normpath(
DEEPRACER_CHECKPOINT_LOCAL_PATH_FORMAT.format(local_dir))
self._s3_client = S3Client(region_name, max_retry_attempts,
backoff_time_sec)
def download_custom_files_if_present(s3_bucket, s3_prefix, aws_region):
'''download custom environment and preset files
Args:
s3_bucket (str): s3 bucket string
s3_prefix (str): s3 prefix string
aws_region (str): aws region string
Returns:
tuple (bool, bool): tuple of bool on whether preset and environemnt
is downloaded successfully
'''
success_environment_download, success_preset_download = False, False
try:
s3_client = S3Client(region_name=aws_region, max_retry_attempts=0)
environment_file_s3_key = os.path.normpath(
s3_prefix + "/environments/deepracer_racetrack_env.py")
environment_local_path = os.path.join(CUSTOM_FILES_PATH,
"deepracer_racetrack_env.py")
s3_client.download_file(bucket=s3_bucket,
s3_key=environment_file_s3_key,
local_path=environment_local_path)
success_environment_download = True
except botocore.exceptions.ClientError:
pass
try:
preset_file_s3_key = os.path.normpath(s3_prefix + "/presets/preset.py")
preset_local_path = os.path.join(CUSTOM_FILES_PATH, "preset.py")
s3_client.download_file(bucket=s3_bucket,
s3_key=preset_file_s3_key,
local_path=preset_local_path)
success_preset_download = True
except botocore.exceptions.ClientError:
pass
return success_preset_download, success_environment_download
def __init__(self,
bucket,
s3_key,
region_name="us-east-1",
local_path="./custom_files/agent/hyperparameters.json",
max_retry_attempts=5,
backoff_time_sec=1.0):
'''Hyperparameters upload, download, and parse
Args:
bucket (str): S3 bucket string
s3_key (str): S3 key string
local_path (str): file local path
region_name (str): S3 region name
max_retry_attempts (int): maximum number of retry attempts for S3 download/upload
backoff_time_sec (float): backoff second between each retry
'''
# check s3 key and bucket exist for hyperparamer
if not s3_key or not bucket:
log_and_exit(
"hyperparameters S3 key or bucket not available for S3. \
bucket: {}, key: {}".format(bucket, s3_key),
SIMAPP_SIMULATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_500)
self._bucket = bucket
# Strip the s3://<bucket> from uri, if s3_key past in as uri
self._s3_key = s3_key.replace('s3://{}/'.format(self._bucket), '')
self._local_path = local_path
self._hyperparameters = None
self._s3_client = S3Client(region_name, max_retry_attempts,
backoff_time_sec)
def __init__(self,
agent_type,
bucket,
s3_key,
region_name="us-east-1",
s3_endpoint_url=None,
local_path="params.yaml",
max_retry_attempts=5,
backoff_time_sec=1.0):
'''yaml upload, download, and parse
Args:
agent_type (str): rollout for training, evaluation for eval, tournament for tournament
bucket (str): S3 bucket string
s3_key: (str): S3 key string.
region_name (str): S3 region name
local_path (str): file local path
max_retry_attempts (int): maximum number of retry attempts for S3 download/upload
backoff_time_sec (float): backoff second between each retry
'''
if not bucket or not s3_key:
log_and_exit(
"yaml file S3 key or bucket not available for S3. \
bucket: {}, key: {}".format(bucket, s3_key),
SIMAPP_SIMULATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_500)
self._bucket = bucket
# Strip the s3://<bucket> from uri, if s3_key past in as uri
self._s3_key = s3_key.replace('s3://{}/'.format(self._bucket), '')
self._local_path = local_path
self._s3_client = S3Client(region_name, s3_endpoint_url,
max_retry_attempts, backoff_time_sec)
self._agent_type = agent_type
if self._agent_type == AgentType.ROLLOUT.value:
self._model_s3_bucket_yaml_key = YamlKey.SAGEMAKER_SHARED_S3_BUCKET_YAML_KEY.value
self._model_s3_prefix_yaml_key = YamlKey.SAGEMAKER_SHARED_S3_PREFIX_YAML_KEY.value
self._mandatory_yaml_key = TRAINING_MANDATORY_YAML_KEY
elif self._agent_type == AgentType.EVALUATION.value:
self._model_s3_bucket_yaml_key = YamlKey.MODEL_S3_BUCKET_YAML_KEY.value
self._model_s3_prefix_yaml_key = YamlKey.MODEL_S3_PREFIX_YAML_KEY.value
self._mandatory_yaml_key = EVAL_MANDATORY_YAML_KEY
elif self._agent_type == AgentType.TOURNAMENT.value:
self._model_s3_bucket_yaml_key = YamlKey.MODEL_S3_BUCKET_YAML_KEY.value
self._model_s3_prefix_yaml_key = YamlKey.MODEL_S3_PREFIX_YAML_KEY.value
self._mandatory_yaml_key = TOUR_MANDATORY_YAML_KEY
else:
log_and_exit(
"Unknown agent type in launch file: {}".format(
self._agent_type), SIMAPP_SIMULATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_500)
self._yaml_values = None
self._is_multicar = False
self._is_f1 = False
self._model_s3_buckets = list()
self._model_metadata_s3_keys = list()
self._body_shell_types = list()
def __init__(self,
bucket,
s3_prefix,
region_name='us-east-1',
s3_endpoint_url=None,
local_dir='./checkpoint/agent',
max_retry_attempts=5,
backoff_time_sec=1.0):
'''This class is for RL coach checkpoint file
Args:
bucket (str): S3 bucket string
s3_prefix (str): S3 prefix string
region_name (str): S3 region name
local_dir (str): local file directory
max_retry_attempts (int): maximum number of retry attempts for S3 download/upload
backoff_time_sec (float): backoff second between each retry
'''
if not bucket or not s3_prefix:
log_and_exit(
"checkpoint S3 prefix or bucket not available for S3. \
bucket: {}, prefix {}".format(bucket, s3_prefix),
SIMAPP_SIMULATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_500)
self._bucket = bucket
# coach checkpoint s3 key
self._s3_key = os.path.normpath(
os.path.join(s3_prefix, COACH_CHECKPOINT_POSTFIX))
# coach checkpoint local path
self._local_path = os.path.normpath(
COACH_CHECKPOINT_LOCAL_PATH_FORMAT.format(local_dir))
# coach checkpoint local temp path
self._temp_local_path = os.path.normpath(
TEMP_COACH_CHECKPOINT_LOCAL_PATH_FORMAT.format(local_dir))
# old coach checkpoint s3 key to handle backward compatibility
self._old_s3_key = os.path.normpath(
os.path.join(s3_prefix, OLD_COACH_CHECKPOINT_POSTFIX))
# old coach checkpoint local path to handle backward compatibility
self._old_local_path = os.path.normpath(
OLD_COACH_CHECKPOINT_LOCAL_PATH_FORMAT.format(local_dir))
# coach checkpoint state file from rl coach
self._coach_checkpoint_state_file = CheckpointStateFile(
os.path.dirname(self._local_path))
self._s3_client = S3Client(region_name, s3_endpoint_url,
max_retry_attempts, backoff_time_sec)
def __init__(self,
bucket,
s3_key,
region_name="us-east-1",
s3_endpoint_url=None,
local_path="./custom_files/agent/customer_reward_function.py",
max_retry_attempts=5,
backoff_time_sec=1.0):
'''reward function upload, download, and parse
Args:
bucket (str): S3 bucket string
s3_key (str): S3 key string
region_name (str): S3 region name
local_path (str): file local path
max_retry_attempts (int): maximum number of retry attempts for S3 download/upload
backoff_time_sec (float): backoff second between each retry
'''
# check s3 key and bucket exist for reward function
if not s3_key or not bucket:
log_and_exit(
"Reward function code S3 key or bucket not available for S3. \
bucket: {}, key: {}".format(bucket, s3_key),
SIMAPP_SIMULATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_500)
self._bucket = bucket
# Strip the s3://<bucket> from uri, if s3_key past in as uri
self._s3_key = s3_key.replace('s3://{}/'.format(self._bucket), '')
self._local_path_processed = local_path
# if _local_path_processed is test.py then _local_path_preprocessed is test_preprocessed.py
self._local_path_preprocessed = ("_preprocessed.py").join(
local_path.split(".py"))
# if local _local_path_processed is ./custom_files/agent/customer_reward_function.py,
# then the import path should be custom_files.agent.customer_reward_function by
# remove ".py", remove "./", and replace "/" and "."
self._import_path = local_path.replace(".py", "").replace("./",
"").replace(
"/", ".")
self._reward_function = None
self._s3_client = S3Client(region_name, s3_endpoint_url,
max_retry_attempts, backoff_time_sec)
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 = S3Client(region_name=s3_region,
s3_endpoint_url=s3_endpoint_url)
# 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,
s3_key=queue_pickle_s3_key,
local_path=local_queue_pickle_path)
s3_client.download_file(bucket=s3_bucket,
s3_key=report_pickle_s3_key,
local_path=local_report_pickle_path)
except:
pass
# download yaml file
yaml_file = YamlFile(
agent_type=AgentType.TOURNAMENT.value,
bucket=s3_bucket,
s3_key=get_s3_key(s3_prefix, s3_yaml_name),
region_name=s3_region,
s3_endpoint_url=s3_endpoint_url,
local_path=YAML_LOCAL_PATH_FORMAT.format(s3_yaml_name))
yaml_dict = yaml_file.get_yaml_values()
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[YamlKey.MODEL_S3_BUCKET_YAML_KEY.value]):
tournament_candidate_queue.append((
yaml_dict[YamlKey.MODEL_S3_BUCKET_YAML_KEY.value][agent_idx],
yaml_dict[YamlKey.MODEL_S3_PREFIX_YAML_KEY.value][agent_idx],
yaml_dict[YamlKey.MODEL_METADATA_FILE_S3_YAML_KEY.value][agent_idx],
yaml_dict[YamlKey.METRICS_S3_BUCKET_YAML_KEY.value][agent_idx],
yaml_dict[YamlKey.METRICS_S3_PREFIX_YAML_KEY.value][agent_idx],
yaml_dict[YamlKey.SIMTRACE_S3_BUCKET_YAML_KEY.value][agent_idx],
yaml_dict[YamlKey.SIMTRACE_S3_PREFIX_YAML_KEY.value][agent_idx],
yaml_dict[YamlKey.MP4_S3_BUCKET_YAML_KEY.value][agent_idx],
yaml_dict[YamlKey.MP4_S3_PREFIX_YAML_KEY.value][agent_idx],
yaml_dict[YamlKey.DISPLAY_NAME_YAML_KEY.value][agent_idx],
# TODO: Deprecate the DISPLAY_NAME and use only the RACER_NAME without if else check
"" if None in yaml_dict.get(YamlKey.RACER_NAME_YAML_KEY.value, [None]) \
else yaml_dict[YamlKey.RACER_NAME_YAML_KEY.value][agent_idx],
yaml_dict[YamlKey.BODY_SHELL_TYPE_YAML_KEY.value][agent_idx]
))
tournament_report = {"race_results": []}
race_idx = len(tournament_report["race_results"])
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_racer_name, car1_body_shell_type) = 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_racer_name, car2_body_shell_type) = car2
race_yaml_dict = generate_race_yaml(yaml_dict=yaml_dict,
car1=car1,
car2=car2,
race_idx=race_idx)
if s3_endpoint_url is not None:
race_yaml_dict["S3_ENDPOINT_URL"] = s3_endpoint_url
race_model_s3_buckets = [
car1_model_s3_bucket, car2_model_s3_bucket
]
race_model_metadatas = [car1_model_metadata, car2_model_metadata]
body_shell_types = [car1_body_shell_type, car2_body_shell_type]
# 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)
json_key = race_model_metadatas[agent_index]
# download model metadata
try:
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))
dirs_to_delete.append(model_metadata.local_dir)
except Exception as e:
log_and_exit(
"Failed to download model_metadata file: s3_bucket: {}, s3_key: {}, {}"
.format(model_s3_bucket, json_key,
e), SIMAPP_SIMULATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_500)
sensors, _, simapp_version = model_metadata.get_model_metadata_info(
)
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:
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(simapp_versions),
','.join(body_shell_types)
]
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["race_results"].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
s3_extra_args = get_s3_kms_extra_args()
# 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(bucket=s3_bucket,
s3_key=queue_pickle_s3_key,
local_path=local_queue_pickle_path,
s3_kms_extra_args=s3_extra_args)
with open(local_report_pickle_path, 'wb') as f:
pickle.dump(tournament_report, f, protocol=2)
s3_client.upload_file(bucket=s3_bucket,
s3_key=report_pickle_s3_key,
local_path=local_report_pickle_path,
s3_kms_extra_args=s3_extra_args)
# 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,
s3_key=final_report_s3_key,
body=json.dumps(tournament_report),
s3_kms_extra_args=s3_extra_args)
cancel_simulation_job(
os.environ.get('AWS_ROBOMAKER_SIMULATION_JOB_ARN'),
s3_region)
except ValueError as ex:
log_and_exit("User modified model_metadata.json: {}".format(ex),
SIMAPP_SIMULATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_400)
except Exception as e:
log_and_exit("Tournament node failed: {}".format(e),
SIMAPP_SIMULATION_WORKER_EXCEPTION,
SIMAPP_EVENT_ERROR_CODE_500)
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('--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(
'--pretrained_checkpoint',
help='(string) Choose which checkpoint to use (best | last)',
type=str,
default="best")
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 = S3Client(region_name=args.aws_region,
s3_endpoint_url=args.s3_endpoint_url,
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,
s3_endpoint_url=args.s3_endpoint_url,
local_path=MODEL_METADATA_LOCAL_PATH_FORMAT.format('agent'))
_, network_type, version = model_metadata_download.get_model_metadata_info(
)
# 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,
s3_endpoint_url=args.s3_endpoint_url,
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.ACTION_SPACE_PATH.value:
model_metadata_download.local_path,
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)
# 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,
s3_endpoint_url=args.s3_endpoint_url)
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,
s3_endpoint_url=args.s3_endpoint_url,
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,
s3_endpoint_url=args.s3_endpoint_url)
ip_config.persist(s3_kms_extra_args=utils.get_s3_kms_extra_args())
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,
s3_endpoint_url=args.s3_endpoint_url,
agent_name='agent',
checkpoint_dir=args.pretrained_checkpoint_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)
# Get the correct pre-trained checkpoint
if args.pretrained_checkpoint.lower() == "best":
# get best model checkpoint string
model_checkpoint_name = checkpoint.deepracer_checkpoint_json.get_deepracer_best_checkpoint(
)
else:
# get the last model checkpoint string
model_checkpoint_name = checkpoint.deepracer_checkpoint_json.get_deepracer_last_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,
s3_endpoint_url=args.s3_endpoint_url,
agent_name='agent',
checkpoint_dir=args.checkpoint_dir)
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"])