def get_derender_config(dataset_name):
_C = CfgNode()
_C.DEBUG = False
_C.TYPE = "derender"
_C.ATTRIBUTES = CfgNode()
_C.RESUME = False
_C.RESUME_DIR = ""
_C.SEED = -1
_C.CUDNN_BENCHMARK = False
# -----------------------------------------------------------------------------
# Model
# -----------------------------------------------------------------------------
_C.MODEL = CfgNode()
# Number of derender visual feature channels
_C.MODEL.FEATURE_CHANNELS = 512
# number of hidden layers after backbone
_C.MODEL.NUM_MID_LAYERS = 2
# Number of intermediate layer channels
_C.MODEL.MID_CHANNELS = 256
_C.INPUT = CfgNode()
_C.DATASETS = CfgNode()
_C.DATASETS.USE_PREDICTED_BOXES = False
_C.DATASETS.BASE_NAME = dataset_name
# -----------------------------------------------------------------------------
# DataLoader
# -----------------------------------------------------------------------------
_C.DATALOADER = CfgNode()
# Number of data loading threads
if _C.DEBUG:
_C.DATALOADER.NUM_WORKERS = 0
else:
_C.DATALOADER.NUM_WORKERS = 6
if _C.DEBUG:
_C.DATALOADER.VAL_BATCH_SIZE = 80
else:
_C.DATALOADER.VAL_BATCH_SIZE = 160
# ---------------------------------------------------------------------------- #
# Solver
# ---------------------------------------------------------------------------- #
_C.SOLVER = CfgNode()
#maximum number of seconds for training
_C.SOLVER.MAX_TIME_SECS = 43200
# Print metrics every _ seconds
_C.SOLVER.PRINT_METRICS_TIME = 180 #TODO: set back to 180
# write to tensorboard summary every_ secconds
_C.SOLVER.TENSORBOARD_SECS = 1
# Checkpoint every _ seconds
_C.SOLVER.CHECKPOINT_SECS = 600
# Run validation every _ seconds
_C.SOLVER.VALIDATION_SECS = 600 #TODO: change back to 300
_C.SOLVER.VALIDATION_MAX_SECS = 60
_C.SOLVER.BASE_LR = 6.658777172739463e-5
_C.SOLVER.BIAS_LR_FACTOR = 2
_C.SOLVER.OPT_TYPE = "Adam" #options "Adam" "SGD"
_C.SOLVER.MOMENTUM = 0.9960477666835778 #found via Bayesian Optimization
_C.SOLVER.ADAM_BETA = 0.9999427846237621
_C.SOLVER.WEIGHT_DECAY = 0.0005
_C.SOLVER.WEIGHT_DECAY_BIAS = 0
#Factor of reduction at iteration == el for el in SOLVER.STEPS
_C.SOLVER.GAMMA = 0.3
_C.SOLVER.STEPS = (80000, 100000)
# _C.SOLVER.STEPS = (3000,5000)
_C.SOLVER.WARMUP_FACTOR = 1.0 / 3
_C.SOLVER.WARMUP_ITERS = 500
_C.SOLVER.WARMUP_METHOD = "linear"
######### INTPHYS ###############
if _C.DATASETS.BASE_NAME == "intphys":
_C.DATASETS.TRAIN = ("intphys_train", )
# _C.DATASETS.TRAIN = ("intphys_val",)
_C.DATASETS.TEST = ("intphys_val", )
_C.DATASETS.USE_DEPTH = True
_C.DATALOADER.OBJECTS_PER_BATCH = 160 # TODO: get back to 160
_C.ATTRIBUTES.NAME = "intphys"
_C.MODEL.ADD_CAMERA = True
# Input channels for the model (segmented depth map, depth map)
_C.MODEL.IN_CHANNELS = 2
# The size of pooling kernel in the last layer of the resnet34
_C.MODEL.POOLING_KERNEL_SIZE = (8, 8)
####### ADEPT #################
elif _C.DATASETS.BASE_NAME == "adept":
_C.DATASETS.TRAIN = ("adept_train", )
# _C.DATASETS.TRAIN = ("adept_val",)
_C.DATASETS.TEST = ("adept_val", )
_C.DATASETS.USE_DEPTH = False
_C.ATTRIBUTES.NAME = "adept"
_C.MODEL.ADD_CAMERA = False
if _C.DEBUG:
_C.DATALOADER.OBJECTS_PER_BATCH = 20 # TODO: get back to 40
else:
_C.DATALOADER.OBJECTS_PER_BATCH = 120 # TODO: get back to 40
# Input channels for the model (segmented depth map, depth map)
_C.MODEL.IN_CHANNELS = 12
# The size of pooling kernel in the last layer of the resnet34
_C.MODEL.POOLING_KERNEL_SIZE = (10, 15)
elif _C.DATASETS.BASE_NAME == "ai2thor-intphys":
_C.DATASETS.TRAIN = ("ai2thor-intphys_train", )
# _C.DATASETS.TRAIN = ("ai2thor-intphys_val",)
_C.DATASETS.TEST = ("ai2thor-intphys_val", )
_C.DATASETS.USE_DEPTH = True
_C.ATTRIBUTES.NAME = "ai2thor"
_C.MODEL.ADD_CAMERA = False
if _C.DEBUG:
_C.DATALOADER.OBJECTS_PER_BATCH = 20
else:
_C.DATALOADER.OBJECTS_PER_BATCH = 120
# Input channels for the model (segmented depth map, depth map)
_C.MODEL.IN_CHANNELS = 2
# The size of pooling kernel in the last layer of the resnet34
_C.MODEL.POOLING_KERNEL_SIZE = (8, 16)
else:
raise NotImplementedError
return _C
def get_adept_cfg(dataset_basename):
_C = CfgNode()
_C.TYPE = "adept"
_C.DEBUG = False
_C.VERSION = "paper-adept" #options: "paper-adept", "intphys-adept"
_C.RESUME = False
_C.RESUME_DIR = ""
_C.SEED = -1
_C.CUDNN_BENCHMARK = False
_C.DEBUG_VIDEOS = [
] #["output/intphys/.data_tmp/adept_jsons/pred_attr_82649/intphys_dev_O1/video_00054.json"]
_C.ANALYZE_RESULTS_FOLDER = "None"
#"output/intphys/adept/bk_distributed_exp"
#"/home/aldo/cora-derender/output/adept/adept/bk_distributed_exp"
#"/all/home/aldo/cora-derenderer/output/adept/adept/distributed_exp/"
#'/all/home/aldo/cora-derenderer/output/intphys/adept/distributed_exp_complete_bk' #"None" #"output/intphys/adept/exp_00025"
# -----------------------------------------------------------------------------
# Datasets
# -----------------------------------------------------------------------------
_C.DATASETS = CfgNode()
_C.DATASETS.BASE_NAME = dataset_basename
if _C.DATASETS.BASE_NAME == "intphys":
####### INTPHYS ###########
_C.ATTRIBUTES_KEYS = (
"pred_attr_82649",
# "pred_attr_03227",
# "pred_attr_06472",
# "pred_attr_12664",
# "pred_attr_22318",
# "pred_attr_41337",
)
_C.DATASETS.TEST = (
"intphys_dev_O1",
"intphys_dev_O2",
"intphys_dev_O3",
# "intphys_dev-meta_O1",
# "intphys_dev-meta_O2",
# "intphys_dev-meta_O3"
)
elif _C.DATASETS.BASE_NAME == "adept":
_C.ATTRIBUTES_KEYS = (
# "attributes",
"pred_attr_43044",
# "pred_attr_00650",
# 'pred_attr_10580',
# "pred_attr_18377",
# "pred_attr_34216"
)
_C.DATASETS.TEST = (
# "adept_val",
# "adept_train", #TODO get back to only test
"adept_human_create",
"adept_human_vanish",
"adept_human_short-overturn",
"adept_human_long-overturn",
"adept_human_visible-discontinuous",
"adept_human_invisible-discontinuous",
"adept_human_delay",
"adept_human_block",
)
# -----------------------------------------------------------------------------
# Model
# -----------------------------------------------------------------------------
_C.MODEL = CfgNode()
_C.MODEL.META_ARCHITECTURE = "PARTICLE_FILTER"
# Particles to be used in the particle filter
_C.MODEL.N_PARTICLES = 128
# Threshold for minimal area for an objects to be considered visible
_C.MODEL.AREA_THRESHOLD = 200.
# -----------------------------------------------------------------------------
# Dynamics Model
# -----------------------------------------------------------------------------
_C.MODEL.STEP = CfgNode()
_C.MODEL.STEP.PERTURBATION = CfgNode()
# Whether to perturb the objects
_C.MODEL.STEP.PERTURBATION.TO_PERTURB = True
# Sigma in the velocity term
_C.MODEL.STEP.PERTURBATION.VELOCITY_SIGMA = [.01, .06]
_C.MODEL.STEP.PERTURBATION.SCALE_SIGMA = .0005
# Sigma in the location term
_C.MODEL.STEP.PERTURBATION.LOCATION_SIGMA = [.01, .06]
# Sigma in the velocity term, multiplicative
_C.MODEL.STEP.PERTURBATION.VELOCITY_LAMBDA = [.01, .06]
# -----------------------------------------------------------------------------
# Magic in the dynamics model
# -----------------------------------------------------------------------------
_C.MODEL.STEP.MAGIC = CfgNode()
# Whether to use magic
_C.MODEL.STEP.MAGIC.USE_MAGIC = True
# The probability to disappear
_C.MODEL.STEP.MAGIC.DISAPPEAR_PROBABILITY = .02
# The penalty for magically disappearing
_C.MODEL.STEP.MAGIC.DISAPPEAR_PENALTY = 10.
# The probability for magically stopping
_C.MODEL.STEP.MAGIC.STOP_PROBABILITY = .02
# The penalty for magically stopping
_C.MODEL.STEP.MAGIC.STOP_PENALTY = 1.
# The probability for magically accelerating
_C.MODEL.STEP.MAGIC.ACCELERATE_PROBABILITY = .04
# The penalty for magically accelerating
_C.MODEL.STEP.MAGIC.ACCELERATE_PENALTY = 1.
# The magnitude for magically accelerating
_C.MODEL.STEP.MAGIC.ACCELERATE_LAMBDA = 1.5
# -----------------------------------------------------------------------------
# Particle filter
# -----------------------------------------------------------------------------
# The period for particle filter to resample
_C.MODEL.RESAMPLE = CfgNode()
# Resample every period
_C.MODEL.RESAMPLE.PERIOD = 1
# Scaling on nll
_C.MODEL.RESAMPLE.FACTOR = 1.
# -----------------------------------------------------------------------------
# Mass sampler
# -----------------------------------------------------------------------------
_C.MODEL.MASS = CfgNode()
# Whether to sample mass
_C.MODEL.MASS.TO_SAMPLE_MASS = False
# The log mean of mass
_C.MODEL.MASS.LOG_MASS_MU = 0
# The log stdev of mass
_C.MODEL.MASS.LOG_MASS_SIGMA = 1
# -----------------------------------------------------------------------------
# Observation Model
# -----------------------------------------------------------------------------
_C.MODEL.UPDATING = CfgNode()
_C.MODEL.UPDATING.MATCHED = CfgNode()
# Loss for matched object updating
_C.MODEL.UPDATING.MATCHED.LOSS = "Smoothed_L_Half"
# Sigma in the location term
_C.MODEL.UPDATING.MATCHED.LOCATION_SIGMA = .2
# Sigma in the velocity term
_C.MODEL.UPDATING.MATCHED.VELOCITY_SIGMA = .2
_C.MODEL.UPDATING.MATCHED.SCALE_SIGMA = .05
_C.MODEL.UPDATING.UNMATCHED_BELIEF = CfgNode()
# Base Penalty coefficient for unseen object
_C.MODEL.UPDATING.UNMATCHED_BELIEF.BASE_PENALTY = 1.
# Penalty coefficient for unseen object w.r.t. mask area shown
_C.MODEL.UPDATING.UNMATCHED_BELIEF.MASK_PENALTY = .0001
_C.MODEL.UPDATING.UNMATCHED_OBSERVATION = CfgNode()
# Penalty for object appearing
_C.MODEL.UPDATING.UNMATCHED_OBSERVATION.PENALTY = .02
_C.MODEL.UPDATING.UNMATCHED_OBSERVATION.MAX_PENALTY = 12.
_C.MODEL.MATCHER = CfgNode()
# PENALTY FOR MISMATCHED OBJECT TYPES, ONLY BETWEEN OCCLUDER AND OTHER
_C.MODEL.MATCHER.TYPE_PENALTY = 10.
# PENALTY FOR MISMATCHED OBJECT COLOR
_C.MODEL.MATCHER.COLOR_PENALTY = 12.
# PENALTY FOR MISMATCHED OBJECT WHEN THEY ARE AFAR
_C.MODEL.MATCHER.DISTANCE_PENALTY = 14. if _C.VERSION == "intphys-adept" else 20.
# THE THRESHOLD FOR OBJECT BEING AFAR
_C.MODEL.MATCHER.DISTANCE_THRESHOLD = 2.
# THE BASE PENALTY BETWEEN PLACEHOLDER AND OBJECTS
_C.MODEL.MATCHER.BASE_PENALTY = 8.
# when more than 5 objects creating more objects should not happen
_C.MODEL.MATCHER.BASE_PENALTY_HIGH = 16
return _C
def get_dynamics_cfg(dataset_base_name):
_C = CfgNode()
_C.DEBUG = False
_C.TYPE = "dynamics"
_C.DATASETS = CfgNode()
# _C.DATASETS.USE_PREDICTED_ATTRIBUTES = True
_C.DATASETS.BASE_NAME = dataset_base_name
_C.DATALOADER = CfgNode()
_C.DATALOADER.NUM_WORKERS = 4
_C.DATALOADER.BATCH_SIZE = 15
_C.MODEL = CfgNode()
_C.MODEL.ARCHITECTURE = "interaction"
_C.MODEL.RNN_NUM_LAYERS = 6
_C.MODEL.DROP_OUT = 0.2
_C.MODEL.HIDDEN_SIZE = 300
_C.SOLVER = CfgNode()
_C.SOLVER.BASE_LR = 0.001
_C.SOLVER.BIAS_LR_FACTOR = 2
_C.SOLVER.OPT_TYPE = "Adam"
_C.SOLVER.MOMENTUM = 0.996
_C.SOLVER.ADAM_BETA = 0.9999427846237621
_C.SOLVER.WEIGHT_DECAY = 0.0005
_C.SOLVER.WEIGHT_DECAY_BIAS = 0
_C.SOLVER.GAMMA = 0.5
_C.SOLVER.STEPS = (999999, 999999)
_C.SOLVER.WARMUP_FACTOR = 1.0 / 3
_C.SOLVER.WARMUP_ITERS = 500
_C.SOLVER.WARMUP_METHOD = "linear"
_C.SOLVER.MAX_TIME_SECS = 999999999
# Print metrics every _ seconds
_C.SOLVER.PRINT_METRICS_TIME = 180 #TODO: set back to 180
# write to tensorboard summary every_ secconds
_C.SOLVER.TENSORBOARD_SECS = 1
# Checkpoint every _ seconds
_C.SOLVER.CHECKPOINT_SECS = 1200
# Run validation every _ seconds
_C.SOLVER.VALIDATION_SECS = 60 #TODO: change back to 300
_C.SOLVER.VALIDATION_MAX_SECS = 9999
if _C.DATASETS.BASE_NAME == "intphys":
_C.DATASETS.TRAIN = ("intphys_val", )
_C.DATASETS.TEST = (
"intphys_dev_O1",
"intphys_dev_O2",
"intphys_dev_O3",
# "intphys_dev-meta_O1",
# "intphys_dev-meta_O2",
# "intphys_dev-meta_O3"
)
_C.ATTRIBUTES_KEYS = ("pred_attr_401469", "pred_attr_003227")
elif _C.DATASETS.BASE_NAME == "adept":
_C.ATTRIBUTES_KEYS = (
"attributes",
# "pred_attr_00650",
"pred_attr_43044",
# 'pred_attr_10580',
# "pred_attr_18377",
# "pred_attr_34216"
)
_C.DATASETS.TRAIN = ("adept_train", )
_C.DATASETS.TEST = (
"adept_val",
# "adept_train",
# "adept_human_create",
# "adept_human_vanish",
# "adept_human_short-overturn",
# "adept_human_long-overturn",
# "adept_human_visible-discontinuous",
# "adept_human_invisible-discontinuous",
# "adept_human_delay",
# "adept_human_block",
)
return _C
