def __init__(self, **kwargs):
self.verbose = 0 # 0(warning) | 1(info) | 2(debug)
# training signature
self.machine = "ecegrid" # "machine_id"
self.timestamp = "17082300" # "yymmdd##"
# training configuration
self.mode = 2 # 1(train) | 2(test model_file)
self.config = 1
self.seed = 1
self.render = False # whether render the window from the original envs or not
self.visualize = True # whether do online plotting and stuff or not
self.save_best = False # save model w/ highest reward if True, otherwise always save the latest model
if 'gpu' in kwargs and kwargs['gpu']:
self.use_cuda = torch.cuda.is_available()
self.dtype = torch.cuda.FloatTensor if torch.cuda.is_available(
) else torch.FloatTensor
else:
self.use_cuda = False
self.dtype = torch.FloatTensor
# prefix for model/log/visdom
self.refs = self.machine + "_" + self.timestamp # NOTE: using this as env for visdom
# Unpack possible arguments
if 'mode' in kwargs and kwargs['mode']:
self.mode = kwargs['mode']
if 'config' in kwargs and kwargs['config']:
self.config = kwargs['config']
if 'model' in kwargs and kwargs['model']:
self.refs = kwargs['model']
self.visualize = kwargs['visualize']
self.agent_type, self.env_type, self.game, self.circuit_type = CONFIGS[
self.config]
self.root_dir = os.getcwd()
# model files
# NOTE: will save the current model to model_name
self.model_name = self.root_dir + "/models/" + self.refs + ".pth"
# NOTE: will load pretrained model_file if not None
self.model_file = None #self.root_dir + "/models/{TODO:FILL_IN_PRETAINED_MODEL_FILE}.pth"
if self.mode == 2:
self.model_file = self.model_name # NOTE: so only need to change self.mode to 2 to test the current training
assert self.model_file is not None, "Pre-Trained model is None, Testing aborted!!!"
self.refs = self.refs + "_test" # NOTE: using this as env for visdom for testing, to avoid accidentally redraw on the training plots
# logging configs
self.log_name = self.root_dir + "/logs/" + self.refs + ".log"
self.logger = loggerConfig(self.log_name, self.verbose)
self.logger.warning("<===================================>")
if self.visualize:
self.vis = visdom.Visdom()
self.logger.warning("bash$: python -m visdom.server"
) # activate visdom server on bash
self.logger.warning("http://localhost:8097/env/" +
self.refs) # open this address on browser
def __init__(self):
self.verbose = 0 # 0(warning) | 1(info) | 2(debug)
# training signature
self.machine = "hpcgpu2" # "machine_id"
self.timestamp = "17112500" # "yymmdd## "
# training configuration
self.mode = 1 # 1(train) | 2(test) | 3(generate image)
self.config = 0
self.train_target = "semantic" # depth|semantic
self.seed = 1
self.render = False # whether render the window from the original envs or not
self.visualize = True # whether do online plotting and stuff or not
self.save_best = False # save model w/ highest reward if True, otherwise always save the latest model
self.agent_type, self.model_type = CONFIGS[self.config]
self.use_cuda = torch.cuda.is_available()
self.dtype = torch.cuda.FloatTensor if torch.cuda.is_available(
) else torch.FloatTensor
# prefix for model/log/visdom
self.refs = self.machine + "_" + self.timestamp # NOTE: using this as env for visdom
self.root_dir = os.getcwd()
# model files
# NOTE: will save the current model to model_name
self.model_name = self.root_dir + "/models/" + self.refs + ".pth"
# NOTE: will load pretrained model_file if not None
self.model_file = self.root_dir + "/models/pretrained.pth"
#self.model_file = None
if self.mode == 2:
self.model_file = self.model_name
assert self.model_file is not None, "Pre-Trained model is None, Testing aborted!!!"
self.refs = self.refs + "_test"
if self.mode == 3:
self.model_file = self.model_name
assert self.model_file is not None, "Pre-Trained model is None, Testing aborted!!!"
self.refs = self.refs + "_generate"
# logging configs
self.log_name = self.root_dir + "/logs/" + self.refs + ".log"
self.logger = loggerConfig(self.log_name, self.verbose)
self.logger.warning("<===================================>")
if self.visualize:
self.vis = visdom.Visdom()
#self.logger.warning("bash$: python -m visdom.server") # activate visdom server on bash
#self.logger.warning("http://localhost:8097/env/" + self.refs) # open this address on browser
self.writer = SummaryWriter(self.root_dir + '/runs/' + self.refs)
self.logger.warning("bash$: tensorboardX --logdir run/"
) # activate visdom server on bash
self.logger.warning(
"http://localhost:6006") # open this address on browser
def __init__(self):
self.verbose = 0 # 0(warning) | 1(info) | 2(debug)
# training signature
self.machine = "cpu1" # "machine_id"
self.timestamp = "17072200" # "yymmdd##"
self.visdom_port = 8098
# training configuration
self.mode = 1 # 1(train) | 2(test model_file)
self.continue_training = True # Continues training if a model already exists, otherwise starts from 0
self.seed = 123
self.render = False # whether render the window from the original envs or not
self.visualize = True # whether do online plotting and stuff or not
self.num_processes = 10
self.hist_len = 4
self.hidden_dim = 256
self.use_cuda = False # Not used
self.dtype = torch.FloatTensor
# prefix for model/log/visdom
self.refs = self.machine + "_" + self.timestamp # NOTE: using this as env for visdom
self.root_dir = os.getcwd()
# model files
self.model_name = self.root_dir + "/models/" + self.refs + ".pth"
if self.continue_training:
if os.path.exists(self.model_name):
self.model_file = self.model_name
else:
self.model_file = None
if self.mode == 2:
self.model_file = self.model_name # NOTE: so only need to change self.mode to 2 to test the current training
assert self.model_file is not None, "Pre-Trained model is None, Testing aborted!!!"
self.refs = self.refs + "_test" # NOTE: using this as env for visdom for testing, to avoid accidentally redraw on the training plots
# logging configs
self.log_name = self.root_dir + "/logs/" + self.refs + ".log"
self.logger = loggerConfig(self.log_name, self.verbose)
self.logger.warning("<===================================>")
if self.visualize:
self.vis = visdom.Visdom(port=self.visdom_port)
def __init__(self):
self.verbose = 0 # 0(warning) | 1(info) | 2(debug)
# training signature
self.machine = "CopyBenchmark" # "machine_id"
self.timestamp = "171202" # "yymmdd##"
# training configuration
self.mode = 1 # 1(train) | 2(test model_file)
self.config = 3 #1:copy #3: associative recall
self.seed = 333 #111 #222 #666
self.render = True # whether render the window from the original envs or not
self.visualize = True #whether save bit error on csv # whether diaplay output and save bit error on command line or not
self.save_best = False # save model w/ highest reward if True, otherwise always save the latest model
self.agent_type, self.env_type, self.game, self.circuit_type = CONFIGS[self.config]
self.use_cuda = torch.cuda.is_available()
self.dtype = torch.cuda.FloatTensor if torch.cuda.is_available() else torch.FloatTensor
# prefix for model/log/visdom
self.refs = self.machine + "_" + self.timestamp # NOTE: using this as env for visdom
self.root_dir = os.getcwd()
# model files
# NOTE: will save the current model to model_name
self.model_name = self.root_dir + "/models/" + self.refs + ".pth"
self.model_name_ite = self.root_dir + "/models/" + self.refs
# NOTE: will load pretrained model_file if not None
self.model_file = None#self.root_dir + "/models/{TODO:FILL_IN_PRETAINED_MODEL_FILE}.pth"
if self.mode == 2:
self.model_file = self.model_name # NOTE: so only need to change self.mode to 2 to test the current training
assert self.model_file is not None, "Pre-Trained model is None, Testing aborted!!!"
self.refs = self.refs + "_test" # NOTE: using this as env for visdom for testing, to avoid accidentally redraw on the training plots
# logging configs
self.log_name = self.root_dir + "/logs/" + self.refs + ".log"
self.logger = loggerConfig(self.log_name, self.verbose)
self.logger.warning("<===================================>")
if self.visualize:
self.vis = visdom.Visdom()
self.logger.warning("bash$: python -m visdom.server") # activate visdom server on bash
self.logger.warning("http://localhost:8097/env/" + self.refs) # open this address on browser
def __init__(self):
self.verbose = 0 # 0(warning) | 1(info) | 2(debug)
# training signature
self.machine = "aisdaim" # "machine_id"
self.timestamp = "17082400" # "yymmdd##"
# training configuration
self.mode = 1 # 1(train) | 2(test model_file)
self.config = 7
self.seed = 123
self.render = False # whether render the window from the original envs or not
self.visualize = True # whether do online plotting and stuff or not
self.save_best = False # save model w/ highest reward if True, otherwise always save the latest model
self.agent_type, self.env_type, self.game, self.model_type, self.memory_type = CONFIGS[self.config]
if self.agent_type == "dqn":
self.enable_double_dqn = False
self.enable_dueling = False
self.dueling_type = 'avg' # avg | max | naive
if self.env_type == "gym":
self.hist_len = 1
self.hidden_dim = 16
else:
self.hist_len = 4
self.hidden_dim = 256
self.use_cuda = torch.cuda.is_available()
self.dtype = torch.cuda.FloatTensor if torch.cuda.is_available() else torch.FloatTensor
elif self.agent_type == "a3c":
self.enable_log_at_train_step = True # when False, x-axis would be frame_step instead of train_step
self.enable_lstm = True
if "-con" in self.model_type:
self.enable_continuous = True
else:
self.enable_continuous = False
self.num_processes = 16
self.hist_len = 1
self.hidden_dim = 128
self.use_cuda = False
self.dtype = torch.FloatTensor
elif self.agent_type == "acer":
self.enable_bias_correction = True
self.enable_1st_order_trpo = True
self.enable_log_at_train_step = True # when False, x-axis would be frame_step instead of train_step
self.enable_lstm = True
if "-con" in self.model_type:
self.enable_continuous = True
else:
self.enable_continuous = False
self.num_processes = 16
self.hist_len = 1
self.hidden_dim = 32
self.use_cuda = False
self.dtype = torch.FloatTensor
else:
self.hist_len = 1
self.hidden_dim = 256
self.use_cuda = torch.cuda.is_available()
self.dtype = torch.cuda.FloatTensor if torch.cuda.is_available() else torch.FloatTensor
# prefix for model/log/visdom
self.refs = self.machine + "_" + self.timestamp # NOTE: using this as env for visdom
self.root_dir = os.getcwd()
# model files
# NOTE: will save the current model to model_name
self.model_name = self.root_dir + "/models/" + self.refs + ".pth"
# NOTE: will load pretrained model_file if not None
self.model_file = None#self.root_dir + "/models/{TODO:FILL_IN_PRETAINED_MODEL_FILE}.pth"
if self.mode == 2:
self.model_file = self.model_name # NOTE: so only need to change self.mode to 2 to test the current training
assert self.model_file is not None, "Pre-Trained model is None, Testing aborted!!!"
self.refs = self.refs + "_test" # NOTE: using this as env for visdom for testing, to avoid accidentally redraw on the training plots
# logging configs
self.log_name = self.root_dir + "/logs/" + self.refs + ".log"
self.logger = loggerConfig(self.log_name, self.verbose)
self.logger.warning("<===================================>")
if self.visualize:
self.vis = visdom.Visdom()
self.logger.warning("bash$: python -m visdom.server") # activate visdom server on bash
self.logger.warning("http://localhost:8097/env/" + self.refs) # open this address on browser
def __init__(self):
self.verbose = 2 # 0(warning) | 1(info) | 2(debug)
# training signature
# TODO: fix action stats for multi-robot!
# self.machine = "aiscpu4" # "machine_id"
# self.timestamp = "18032100" # "yymmdd##"
# self.step = ""
# signatures of the best models
self.machine = "aiscpu4"
self.timestamp = "18032100"
self.step = "3000021"
self.icm_step = "3000021"
#
# self.machine = "aiscpu4"
# self.timestamp = "18031601"
# self.step = "2844054"
# self.icm_step = "2844054"
# self.machine = "aiscpu2"
# self.timestamp = "18031700"
# self.step = "2556792"
# self.machine = "aiscpu4"
# self.timestamp = "18031600"
# self.step = "2976216"
# self.icm_step = "2976216" # "60109" # "115896"
# self.machine = "aiscpu4"
# self.timestamp = "18031300"
# self.step = "2760065"
# self.machine = "aiscpu2"
# self.timestamp = "18031300"
# self.step = "1585315"
# self.machine = "aiscpu4"
# self.timestamp = "18031000"
# self.step = "1299783"
# self.test_ref_postfix = '_' + self.step + "_title"
self.test_ref_postfix = '_' + self.step + "_test"
# self.test_ref_postfix = '_' + self.step + "_test_gen"
# self.test_ref_postfix = '_' + self.step + "_test_gen2"
# self.test_ref_postfix = '_' + self.step + "_test_gen3"
# self.test_ref_postfix = '_' + self.step + "_test_gen_hard"
# training configuration
self.mode = 2 # 1(train) | 2(test model_file)
self.config = 18
self.seed = 123
self.render = False # whether render the window from the original envs or not
self.visualize = True # whether do online plotting and stuff or not
self.save_best = False # save model w/ highest reward if True, otherwise always save the latest model
self.icm_save_best = False
self.plot_icm_test = False
self.plot_env_picture = False
self.verbose_test = False
self.agent_type, self.env_type, self.game, self.model_type, self.memory_type = CONFIGS[
self.config]
self.icm = False
if self.mode != 2:
self.step = None
if self.agent_type == "dqn":
self.enable_double_dqn = False
self.enable_dueling = False
self.dueling_type = 'avg' # avg | max | naive
if self.env_type == "gym":
self.hist_len = 1
self.hidden_dim = 16
else:
self.hist_len = 4
self.hidden_dim = 256
self.use_cuda = torch.cuda.is_available()
self.dtype = torch.cuda.FloatTensor if torch.cuda.is_available(
) else torch.FloatTensor
elif self.agent_type == "a3c":
self.enable_log_at_train_step = True # when False, x-axis would be frame_step instead of train_step
self.enable_lstm = True
if "-con" in self.model_type:
self.enable_continuous = True
else:
self.enable_continuous = False
self.num_processes = 16
self.hist_len = 1
if self.env_type == "minisim":
from core.minisim.models.icm.icm_inverse import ICMInverseModel
# from core.minisim.models.icm.icm_inverse_same_features import ICMInverseModelSameFeatures
from core.minisim.models.icm.icm_forward import ICMForwardModel
self.icm = True
# self.icm = False # !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
self.icm_inv_model = ICMInverseModel
# self.icm_inv_model = ICMInverseModelSameFeatures
self.icm_fwd_model = ICMForwardModel
self.num_processes = 22 # 6, 23 # 22 seems to be twice faster than 23, why? try other?
if minisim_num_robots > 1:
self.num_processes = 22 # 4, 23
self.use_cuda = False
self.dtype = torch.FloatTensor
else:
self.hist_len = 1
self.hidden_dim = 256
self.use_cuda = torch.cuda.is_available()
self.dtype = torch.cuda.FloatTensor if torch.cuda.is_available(
) else torch.FloatTensor
# prefix for model/log/visdom
self.refs = self.machine + "_" + self.timestamp # NOTE: using this as env for visdom
self.root_dir = os.getcwd()
# model files
if self.icm:
self.icm_inv_model_name = "{0}/models/{1}_icm_inv{2}.pth".format(
self.root_dir, self.refs,
("_step_" +
self.icm_step) if self.icm_step is not None else "")
self.icm_fwd_model_name = "{0}/models/{1}_icm_fwd{2}.pth".format(
self.root_dir, self.refs,
("_step_" +
self.icm_step) if self.icm_step is not None else "")
self.icm_inv_model_file = None
self.icm_fwd_model_file = None
if self.mode == 2: # NOTE: so only need to change self.mode to 2 to test the current training
self.icm_inv_model_file = self.icm_inv_model_name
self.icm_fwd_model_file = self.icm_fwd_model_name
# NOTE: will save the current model to model_name
self.model_name = "{0}/models/{1}{2}.pth".format(
self.root_dir, self.refs,
("_step_" + self.step) if self.step is not None else "")
# NOTE: will load pretrained model_file if not None
self.model_file = None
# self.model_file = self.root_dir + "/models/aiscpu2_17110500.pth"
if self.mode == 2:
self.model_file = self.model_name # NOTE: so only need to change self.mode to 2 to test the current training
assert self.model_file is not None, "Pre-Trained model is None, Testing aborted!!!"
self.refs = self.refs + self.test_ref_postfix # NOTE: using this as env for visdom for testing, to avoid accidentally redraw on the training plots
# logging configs
self.log_name = self.root_dir + "/logs/" + self.refs + ".log"
self.logger = loggerConfig(self.log_name, self.verbose)
self.logger.warning("<===================================>")
if self.visualize:
self.vis = visdom.Visdom()
self.logger.warning("bash$: python -m visdom.server"
) # activate visdom server on bash
self.logger.warning("http://localhost:8097/env/" +
self.refs) # open this address on browser
