tfm.vision.configs.maskrcnn.Losses

Inherits From: Config, ParamsDict

tfm.vision.configs.maskrcnn.Losses(
    default_params: dataclasses.InitVar[Optional[Mapping[str, Any]]] = None,
    restrictions: dataclasses.InitVar[Optional[List[str]]] = None,
    loss_weight: float = 1.0,
    rpn_huber_loss_delta: float = (1.0 / 9.0),
    frcnn_huber_loss_delta: float = 1.0,
    frcnn_class_use_binary_cross_entropy: bool = False,
    frcnn_class_loss_top_k_percent: float = 1.0,
    l2_weight_decay: float = 0.0,
    rpn_score_weight: float = 1.0,
    rpn_box_weight: float = 1.0,
    frcnn_class_weight: float = 1.0,
    frcnn_box_weight: float = 1.0,
    mask_weight: float = 1.0,
    class_weights: Optional[List[float]] = None
)

BUILDER

default_params Dataclass field
restrictions Dataclass field
loss_weight Dataclass field
rpn_huber_loss_delta Dataclass field
frcnn_huber_loss_delta Dataclass field
frcnn_class_use_binary_cross_entropy Dataclass field
frcnn_class_loss_top_k_percent Dataclass field
l2_weight_decay Dataclass field
rpn_score_weight Dataclass field
rpn_box_weight Dataclass field
frcnn_class_weight Dataclass field
frcnn_box_weight Dataclass field
mask_weight Dataclass field
class_weights Dataclass field

Methods

as_dict

View source

as_dict()

Returns a dict representation of params_dict.ParamsDict.

For the nested params_dict.ParamsDict, a nested dict will be returned.

from_args

View source

@classmethod
from_args(
    *args, **kwargs
)

Builds a config from the given list of arguments.

from_json

View source

@classmethod
from_json(
    file_path: str
)

Wrapper for from_yaml.

from_yaml

View source

@classmethod
from_yaml(
    file_path: str
)

get

View source

get(
    key, value=None
)

Accesses through built-in dictionary get method.

lock

View source

lock()

Makes the ParamsDict immutable.

override

View source

override(
    override_params, is_strict=True
)

Override the ParamsDict with a set of given params.

Args
override_params a dict or a ParamsDict specifying the parameters to be overridden.
is_strict a boolean specifying whether override is strict or not. If True, keys in override_params must be present in the ParamsDict. If False, keys in override_params can be different from what is currently defined in the ParamsDict. In this case, the ParamsDict will be extended to include the new keys.

replace

View source

replace(
    **kwargs
)

Overrides/returns a unlocked copy with the current config unchanged.

validate

View source

validate()

Validate the parameters consistency based on the restrictions.

This method validates the internal consistency using the pre-defined list of restrictions. A restriction is defined as a string which specifies a binary operation. The supported binary operations are {'==', '!=', '<', '<=', '>', '>='}. Note that the meaning of these operators are consistent with the underlying Python immplementation. Users should make sure the define restrictions on their type make sense.

For example, for a ParamsDict like the following

a:
  a1: 1
  a2: 2
b:
  bb:
    bb1: 10
    bb2: 20
  ccc:
    a1: 1
    a3: 3

one can define two restrictions like this ['a.a1 == b.ccc.a1', 'a.a2 <= b.bb.bb2']

What it enforces are

  • a.a1 = 1 == b.ccc.a1 = 1
  • a.a2 = 2 <= b.bb.bb2 = 20

Raises
KeyError if any of the following happens (1) any of parameters in any of restrictions is not defined in ParamsDict, (2) any inconsistency violating the restriction is found.
ValueError if the restriction defined in the string is not supported.

__contains__

View source

__contains__(
    key
)

Implements the membership test operator.

__eq__

__eq__(
    other
)

IMMUTABLE_TYPES (<class 'str'>, <class 'int'>, <class 'float'>, <class 'bool'>, <class 'NoneType'>)
RESERVED_ATTR ['_locked', '_restrictions']
SEQUENCE_TYPES (<class 'list'>, <class 'tuple'>)
class_weights None
default_params None
frcnn_box_weight 1.0
frcnn_class_loss_top_k_percent 1.0
frcnn_class_use_binary_cross_entropy False
frcnn_class_weight 1.0
frcnn_huber_loss_delta 1.0
l2_weight_decay 0.0
loss_weight 1.0
mask_weight 1.0
restrictions None
rpn_box_weight 1.0
rpn_huber_loss_delta 0.1111111111111111
rpn_score_weight 1.0