def setup(args, config):
"""
Create configs and perform basic setups.
"""
from detectron2.config import CfgNode
# detectron2 default cfg
# cfg = get_cfg()
cfg = CfgNode()
cfg.OUTPUT_DIR = "./output"
cfg.SEED = -1
cfg.CUDNN_BENCHMARK = False
cfg.DATASETS = CfgNode()
cfg.SOLVER = CfgNode()
cfg.DATALOADER = CfgNode()
cfg.DATALOADER.FILTER_EMPTY_ANNOTATIONS = True
cfg.DATALOADER.SAMPLER_TRAIN = "TrainingSampler"
cfg.MODEL = CfgNode()
cfg.MODEL.KEYPOINT_ON = False
cfg.MODEL.LOAD_PROPOSALS = False
cfg.MODEL.WEIGHTS = ""
# cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg = detection2_utils.D2Utils.cfg_merge_from_easydict(cfg, config)
cfg.freeze()
default_setup(
cfg, args
) # if you don't like any of the default setup, write your own setup code
return cfg
def create_cfg():
"""
Create configs and perform basic setups.
"""
from detectron2.config import CfgNode
# detectron2 default cfg
# cfg = get_cfg()
cfg = CfgNode()
cfg.OUTPUT_DIR = "./output"
cfg.SEED = -1
cfg.CUDNN_BENCHMARK = False
cfg.DATASETS = CfgNode()
cfg.SOLVER = CfgNode()
cfg.DATALOADER = CfgNode()
cfg.DATALOADER.FILTER_EMPTY_ANNOTATIONS = True
cfg.DATALOADER.SAMPLER_TRAIN = "TrainingSampler"
cfg.MODEL = CfgNode()
cfg.MODEL.KEYPOINT_ON = False
cfg.MODEL.LOAD_PROPOSALS = False
cfg.MODEL.WEIGHTS = ""
cfg.freeze()
return cfg
# with datasets listed in DATASETS.TRAIN. _C.DATASETS.PROPOSAL_FILES_TRAIN = () # Number of top scoring precomputed proposals to keep for training _C.DATASETS.PRECOMPUTED_PROPOSAL_TOPK_TRAIN = 2000 # List of the dataset names for testing. Must be registered in DatasetCatalog _C.DATASETS.TEST = () # List of the pre-computed proposal files for test, which must be consistent # with datasets listed in DATASETS.TEST. _C.DATASETS.PROPOSAL_FILES_TEST = () # Number of top scoring precomputed proposals to keep for test _C.DATASETS.PRECOMPUTED_PROPOSAL_TOPK_TEST = 1000 # ----------------------------------------------------------------------------- # DataLoader # ----------------------------------------------------------------------------- _C.DATALOADER = CN() # Number of data loading threads _C.DATALOADER.NUM_WORKERS = 4 # If True, each batch should contain only images for which the aspect ratio # is compatible. This groups portrait images together, and landscape images # are not batched with portrait images. _C.DATALOADER.ASPECT_RATIO_GROUPING = True # Options: TrainingSampler, RepeatFactorTrainingSampler _C.DATALOADER.SAMPLER_TRAIN = "TrainingSampler" # Repeat threshold for RepeatFactorTrainingSampler _C.DATALOADER.REPEAT_THRESHOLD = 0.0 # if True, the dataloader will filter out images that have no associated # annotations at train time. _C.DATALOADER.FILTER_EMPTY_ANNOTATIONS = True # ---------------------------------------------------------------------------- #
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_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
