def _multiprocess_upload_s3(self, s3_bucket, s3_prefix, aws_region, local_file): if os.path.exists(local_file): s3_client = SageS3Client(bucket=s3_bucket, s3_prefix=s3_prefix, aws_region=aws_region, s3_endpoint_url=self.s3_endpoint_url) s3_keys = "{}/{}/{}-{}".format( s3_prefix, os.path.dirname(re.sub(self.agent_pattern, '', local_file)), self.upload_num, os.path.basename(local_file)) s3_client.upload_file(s3_keys, local_file)
def test_load_model_metadata(s3_bucket, s3_prefix, aws_region, model_metadata_s3_key): """This function checks the functionality of load_model_metadata function in markov/utils.py The function checks if model_metadata.json file is downloaded into the required directory. If the function fails, it will generate an exception which will call log_and_exit internally. Hence the test will fail. Args: s3_bucket (String): S3_BUCKET s3_prefix (String): S3_PREFIX aws_region (String): AWS_REGION model_metadata_s3_key (String): MODEL_METADATA_S3_KEY """ s3_client = SageS3Client(bucket=s3_bucket, s3_prefix=s3_prefix, aws_region=aws_region) model_metadata_local_path = 'test_model_metadata.json' utils.load_model_metadata(s3_client, model_metadata_s3_key, model_metadata_local_path) assert os.path.isfile(model_metadata_local_path) # Remove file downloaded if os.path.isfile(model_metadata_local_path): os.remove(model_metadata_local_path)
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(): 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 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=os.environ.get("MODEL_S3_BUCKET", "gsaur-test")) parser.add_argument('--s3_prefix', help='(string) S3 prefix', type=str, default=os.environ.get("MODEL_S3_PREFIX", "sagemaker")) parser.add_argument('--aws_region', help='(string) AWS region', type=str, default=os.environ.get("APP_REGION", "us-east-1")) parser.add_argument('--number_of_trials', help='(integer) Number of trials', type=int, default=os.environ.get("NUMBER_OF_TRIALS", 15)) 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('--model_metadata_s3_key', help='(string) Model Metadata File S3 Key', type=str, default=os.environ.get("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) register(id=defaults.ENV_ID, entry_point=defaults.ENTRY_POINT, max_episode_steps=defaults.MAX_STEPS, reward_threshold=defaults.THRESHOLD) # Load the model metadata model_metadata_local_path = os.path.join(CUSTOM_FILES_PATH, 'model_metadata.json') load_model_metadata(s3_client, args.model_metadata_s3_key, model_metadata_local_path) # Download the model # s3_client.download_model(args.local_model_directory) preset_file_success, _ = download_custom_files_if_present( s3_client, args.s3_prefix) 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: logger.info("Preset file could not be downloaded. Exiting!") sys.exit(1) ds_params_instance = S3BotoDataStoreParameters( bucket_name=args.s3_bucket, checkpoint_dir=args.local_model_directory, aws_region=args.aws_region, s3_folder=args.s3_prefix) data_store = S3BotoDataStore(ds_params_instance) data_store.get_a_particular_model(checkpoint_number=1) graph_manager.data_store = data_store graph_manager.env_params.seed = 0 evaluation_worker(graph_manager=graph_manager, number_of_trials=args.number_of_trials, local_model_directory=args.local_model_directory)
def main(): screen.set_use_colors(False) try: 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, unknown = parser.parse_known_args() start_redis_server() 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') 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) # Register the gym enviroment, this will give clients the ability to creat the enviroment object register(id=defaults.ENV_ID, entry_point=defaults.ENTRY_POINT, max_episode_steps=defaults.MAX_STEPS, reward_threshold=defaults.THRESHOLD) user_batch_size, user_episode_per_rollout = None, None 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: agent_param_loc = "markov.presets.preset:agent_params" agent_params = short_dynamic_import( agent_param_loc, ignore_module_case=True) user_batch_size = agent_params.network_wrappers[ 'main'].batch_size user_episode_per_rollout = agent_params.algorithm.num_consecutive_playing_steps.num_steps logger.info("Using preset: %s" % args.preset_s3_key) if not success_custom_preset: from markov.sagemaker_graph_manager import get_graph_manager user_batch_size = json.loads( robomaker_hyperparams_json)["batch_size"], user_episode_per_rollout = json.loads( robomaker_hyperparams_json)["num_episodes_between_training"] 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 = {} graph_manager, robomaker_hyperparams_json = get_graph_manager( **sm_hyperparams_dict) s3_client.upload_hyperparameters(robomaker_hyperparams_json) logger.info("Uploaded hyperparameters.json to S3") host_ip_address = 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: s3_client_pretrained = SageS3Client( bucket=args.pretrained_s3_bucket, s3_prefix=args.pretrained_s3_prefix, aws_region=args.aws_region) s3_client_pretrained.download_model(args.pretrained_checkpoint_dir) memory_backend_params = RedisPubSubMemoryBackendParameters( redis_address="localhost", redis_port=6379, run_type='trainer', channel=args.s3_prefix) ds_params_instance = S3BotoDataStoreParameters( bucket_name=args.s3_bucket, checkpoint_dir=args.checkpoint_dir, aws_region=args.aws_region, 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 training_worker(graph_manager=graph_manager, checkpoint_dir=args.checkpoint_dir, use_pretrained_model=use_pretrained_model, framework=args.framework, memory_backend_params=memory_backend_params, user_batch_size=user_batch_size, user_episode_per_rollout=user_episode_per_rollout) except Exception as ex: utils.json_format_logger( "Training worker exited with exception: {}".format(ex), **utils.build_system_error_dict( utils.SIMAPP_TRAINING_WORKER_EXCEPTION, utils.SIMAPP_EVENT_ERROR_CODE_500)) utils.simapp_exit_gracefully()
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 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=os.environ.get("MODEL_S3_BUCKET", "gsaur-test")) parser.add_argument('--s3_prefix', help='(string) S3 prefix', type=str, default=os.environ.get("MODEL_S3_PREFIX", "sagemaker")) parser.add_argument('--aws_region', help='(string) AWS region', type=str, default=os.environ.get("APP_REGION", "us-east-1")) parser.add_argument('--number_of_trials', help='(integer) Number of trials', type=int, default=os.environ.get("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() s3_client = SageS3Client(bucket=args.s3_bucket, s3_prefix=args.s3_prefix, aws_region=args.aws_region) print("S3 bucket: %s" % args.s3_bucket) print("S3 prefix: %s" % args.s3_prefix) # Load the model metadata model_metadata_local_path = os.path.join(CUSTOM_FILES_PATH, 'model_metadata.json') load_model_metadata(s3_client, os.path.normpath("%s/model/model_metadata.json" % args.s3_prefix), model_metadata_local_path) # Download the model s3_client.download_model(args.local_model_directory) # 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: print("Received Sagemaker hyperparameters successfully!") with open("hyperparameters.json") as fp: sm_hyperparams_dict = json.load(fp) else: print("SageMaker hyperparameters not found.") from markov.sagemaker_graph_manager import get_graph_manager graph_manager, _ = get_graph_manager(**sm_hyperparams_dict) ds_params_instance = S3BotoDataStoreParameters(bucket_name=args.s3_bucket, checkpoint_dir=args.local_model_directory, aws_region=args.aws_region, s3_folder=args.s3_prefix) data_store = S3BotoDataStore(ds_params_instance) graph_manager.data_store = data_store evaluation_worker( graph_manager=graph_manager, number_of_trials=args.number_of_trials, local_model_directory=args.local_model_directory )
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=os.environ.get("SAGEMAKER_SHARED_S3_BUCKET", "gsaur-test")) parser.add_argument('--s3_prefix', help='(string) S3 prefix', type=str, default=os.environ.get("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=os.environ.get("APP_REGION", "us-east-1")) parser.add_argument('--reward_file_s3_key', help='(string) Reward File S3 Key', type=str, default=os.environ.get("REWARD_FILE_S3_KEY", None)) parser.add_argument('--model_metadata_s3_key', help='(string) Model Metadata File S3 Key', type=str, default=os.environ.get("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) print("S3 bucket: %s" % args.s3_bucket) print("S3 prefix: %s" % args.s3_prefix) # Load the model metadata model_metadata_local_path = os.path.join(CUSTOM_FILES_PATH, 'model_metadata.json') load_model_metadata(s3_client, args.model_metadata_s3_key, model_metadata_local_path) redis_ip = s3_client.get_ip() print("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: print("Received Sagemaker hyperparameters successfully!") with open("hyperparameters.json") as fp: sm_hyperparams_dict = json.load(fp) else: print("SageMaker hyperparameters not found.") preset_file_success = False environment_file_success = False preset_file_success, environment_file_success = download_custom_files_if_present( s3_client, args.s3_prefix) if not environment_file_success: # Download reward function if environment file is not downloaded if not args.reward_file_s3_key: raise ValueError("Customer reward S3 key not supplied!") download_customer_reward_function(s3_client, args.reward_file_s3_key) import markov.environments print("Using default environment!") else: register_custom_environments() print("Using custom environment!") 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) print("Using custom preset file!") else: from markov.sagemaker_graph_manager import get_graph_manager graph_manager, _ = get_graph_manager(**sm_hyperparams_dict) memory_backend_params = RedisPubSubMemoryBackendParameters( redis_address=redis_ip, redis_port=6379, run_type='worker', channel=args.s3_prefix) graph_manager.agent_params.memory.register_var('memory_backend_params', memory_backend_params) ds_params_instance = S3BotoDataStoreParameters( bucket_name=args.s3_bucket, checkpoint_dir=args.checkpoint_dir, aws_region=args.aws_region, s3_folder=args.s3_prefix) data_store = S3BotoDataStore(ds_params_instance) data_store.graph_manager = graph_manager graph_manager.data_store = data_store rollout_worker( graph_manager=graph_manager, checkpoint_dir=args.checkpoint_dir, data_store=data_store, num_workers=args.num_workers, )
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=os.environ.get("SAGEMAKER_SHARED_S3_BUCKET", "gsaur-test")) parser.add_argument('--s3_prefix', help='(string) S3 prefix', type=str, default=os.environ.get("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=os.environ.get("APP_REGION", "us-east-1")) parser.add_argument('--reward_file_s3_key', help='(string) Reward File S3 Key', type=str, default=os.environ.get("REWARD_FILE_S3_KEY", None)) parser.add_argument('--model_metadata_s3_key', help='(string) Model Metadata File S3 Key', type=str, default=os.environ.get("MODEL_METADATA_FILE_S3_KEY", None)) parser.add_argument('--aws_endpoint_url', help='(string) AWS region', type=str, default=os.environ.get("AWS_ENDPOINT_URL", None)) args = parser.parse_args() s3_client = SageS3Client(bucket=args.s3_bucket, s3_prefix=args.s3_prefix, aws_region=args.aws_region, endpoint_url=args.aws_endpoint_url) 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') load_model_metadata(s3_client, args.model_metadata_s3_key, model_metadata_local_path) # Download reward function if not args.reward_file_s3_key: utils.json_format_logger( "Reward function code S3 key not available for S3 bucket {} and prefix {}" .format(args.s3_bucket, args.s3_prefix), **utils.build_system_error_dict( utils.SIMAPP_SIMULATION_WORKER_EXCEPTION, utils.SIMAPP_EVENT_ERROR_CODE_500)) traceback.print_exc() utils.simapp_exit_gracefully() download_customer_reward_function(s3_client, args.reward_file_s3_key) # Register the gym enviroment, this will give clients the ability to creat the enviroment object register(id=defaults.ENV_ID, entry_point=defaults.ENTRY_POINT, max_episode_steps=defaults.MAX_STEPS, reward_threshold=defaults.THRESHOLD) 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) 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: from markov.sagemaker_graph_manager import get_graph_manager graph_manager, _ = get_graph_manager(**sm_hyperparams_dict) logger.info("Connecting to redis at %s:%d" % (redis_ip, args.redis_port)) memory_backend_params = RedisPubSubMemoryBackendParameters( redis_address=redis_ip, redis_port=6379, run_type='worker', channel=args.s3_prefix) logger.info("Connecting to s3 boto data store at %s" % args.aws_endpoint_url) ds_params_instance = S3BotoDataStoreParameters( bucket_name=args.s3_bucket, checkpoint_dir=args.checkpoint_dir, aws_region=args.aws_region, s3_folder=args.s3_prefix, aws_endpoint_url=args.aws_endpoint_url) data_store = S3BotoDataStore(ds_params_instance) data_store.graph_manager = graph_manager graph_manager.data_store = data_store rollout_worker(graph_manager=graph_manager, checkpoint_dir=args.checkpoint_dir, data_store=data_store, num_workers=args.num_workers, memory_backend_params=memory_backend_params)
def main(): screen.set_use_colors(False) parser = argparse.ArgumentParser() parser.add_argument( '-c', '--checkpoint-dir', help= '(string) Path to a local folder containing a checkpoint to write the model to.', type=str, default='./checkpoint') parser.add_argument( '--pretrained-checkpoint-dir', help= '(string) Path to a local 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('--RLCOACH_PRESET', help='(string) Default preset to use', type=str, default='object_tracker') parser.add_argument('--aws_region', help='(string) AWS region', type=str, required=True) args, unknown = parser.parse_known_args() s3_client = SageS3Client(bucket=args.s3_bucket, s3_prefix=args.s3_prefix, aws_region=args.aws_region) # Import to register the environment with Gym import robomaker.environments preset_location = "robomaker.presets.%s:graph_manager" % args.RLCOACH_PRESET graph_manager = short_dynamic_import(preset_location, ignore_module_case=True) host_ip_address = get_ip_from_host() s3_client.write_ip_config(host_ip_address) print("Uploaded IP address information to S3: %s" % host_ip_address) use_pretrained_model = False if args.pretrained_s3_bucket and args.pretrained_s3_prefix: s3_client_pretrained = SageS3Client( bucket=args.pretrained_s3_bucket, s3_prefix=args.pretrained_s3_prefix, aws_region=args.aws_region) s3_client_pretrained.download_model(PRETRAINED_MODEL_DIR) use_pretrained_model = True memory_backend_params = RedisPubSubMemoryBackendParameters( redis_address="localhost", redis_port=6379, run_type='trainer', channel=args.s3_prefix) graph_manager.agent_params.memory.register_var('memory_backend_params', memory_backend_params) ds_params_instance = S3BotoDataStoreParameters( bucket_name=args.s3_bucket, checkpoint_dir=args.checkpoint_dir, s3_folder=args.s3_prefix, aws_region=args.aws_region) 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 training_worker(graph_manager=graph_manager, checkpoint_dir=args.checkpoint_dir, use_pretrained_model=use_pretrained_model, framework=args.framework)
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(): """ 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 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(): 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, unknown = 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') 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_environment = False if args.environment_s3_key: environment_local_path = "./markov/environments/deepracer_racetrack_env.py" success_custom_environment = s3_client.download_file( s3_key=args.environment_s3_key, local_path=environment_local_path) if not success_custom_environment: print( "Could not download the environment file. Using the default DeepRacer environment." ) else: success_custom_environment = s3_client.upload_file( s3_key=os.path.normpath( "%s/environments/deepracer_racetrack_env.py" % args.s3_prefix), local_path=environment_local_path) if success_custom_environment: print("Using environment: %s" % args.environment_s3_key) # Import to register the environment with Gym import markov.environments 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: print( "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: print("Using preset: %s" % args.preset_s3_key) if not success_custom_preset: from markov.sagemaker_graph_manager import get_graph_manager 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 = {} graph_manager, robomaker_hyperparams_json = get_graph_manager( **sm_hyperparams_dict) s3_client.upload_hyperparameters(robomaker_hyperparams_json) print("Uploaded hyperparameters.json to S3") host_ip_address = get_ip_from_host() s3_client.write_ip_config(host_ip_address) print("Uploaded IP address information to S3: %s" % host_ip_address) use_pretrained_model = False if args.pretrained_s3_bucket and args.pretrained_s3_prefix: s3_client_pretrained = SageS3Client( bucket=args.pretrained_s3_bucket, s3_prefix=args.pretrained_s3_prefix, aws_region=args.aws_region) s3_client_pretrained.download_model(args.pretrained_checkpoint_dir) use_pretrained_model = True memory_backend_params = RedisPubSubMemoryBackendParameters( redis_address="localhost", redis_port=6379, run_type='trainer', channel=args.s3_prefix) graph_manager.agent_params.memory.register_var('memory_backend_params', memory_backend_params) ds_params_instance = S3BotoDataStoreParameters( bucket_name=args.s3_bucket, checkpoint_dir=args.checkpoint_dir, aws_region=args.aws_region, 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 training_worker(graph_manager=graph_manager, checkpoint_dir=args.checkpoint_dir, use_pretrained_model=use_pretrained_model, framework=args.framework)
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)