tfr.extension.premade.TFRBertConfig

The tf-ranking BERT task config.

Inherits From: RankingTaskConfig

tfr.extension.premade.TFRBertConfig(
    default_params: dataclasses.InitVar[Optional[Mapping[str, Any]]] = None,
    restrictions: dataclasses.InitVar[Optional[List[str]]] = None,
    init_checkpoint: str = '',
    model: tfr.extension.premade.TFRBertModelConfig = TFRBertModelConfig(),
    train_data: tfr.extension.task.RankingDataConfig = None,
    validation_data: tfr.extension.task.RankingDataConfig = None,
    name: Optional[str] = None,
    differential_privacy_config: Optional[dp_configs.DifferentialPrivacyConfig] = None,
    allow_image_summary: bool = False,
    loss: str = 'softmax_loss',
    loss_reduction: str = tf.keras.losses.Reduction.NONE,
    aggregated_metrics: bool = False,
    output_preds: bool = False
)

BUILDER

default_params Dataclass field
restrictions Dataclass field
init_checkpoint Dataclass field
model Dataclass field
train_data Dataclass field
validation_data Dataclass field
name Dataclass field
differential_privacy_config Dataclass field
allow_image_summary Dataclass field
loss Dataclass field
loss_reduction Dataclass field
aggregated_metrics Dataclass field
output_preds Dataclass field

Methods

as_dict

as_dict()

Returns a dict representation of params_dict.ParamsDict.

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

from_args

@classmethod
from_args(
    *args, **kwargs
)

Builds a config from the given list of arguments.

from_json

@classmethod
from_json(
    file_path: str
)

Wrapper for from_yaml.

from_yaml

@classmethod
from_yaml(
    file_path: str
)

get

get(
    key, value=None
)

Accesses through built-in dictionary get method.

lock

lock()

Makes the ParamsDict immutable.

override

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

replace(
    **kwargs
)

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

validate

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__

__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'>)
aggregated_metrics False
allow_image_summary False
default_params None
differential_privacy_config None
init_checkpoint ''
loss 'softmax_loss'
loss_reduction 'none'
model Instance of tfr.extension.premade.TFRBertModelConfig
name None
output_preds False
restrictions None
train_data None
validation_data None