tfm.vision.configs.video_classification.DataConfig

The base configuration for building datasets.

Inherits From: DataConfig, Config, ParamsDict

tfm.vision.configs.video_classification.DataConfig(
    default_params: dataclasses.InitVar[Optional[Mapping[str, Any]]] = None,
    restrictions: dataclasses.InitVar[Optional[List[str]]] = None,
    input_path: Union[str, tfm.hyperparams.Config] = '',
    tfds_name: Union[str, tfm.hyperparams.Config] = '',
    tfds_split: str = '',
    global_batch_size: int = 128,
    is_training: bool = True,
    drop_remainder: bool = True,
    shuffle_buffer_size: int = 64,
    cache: bool = False,
    cycle_length: int = 10,
    block_length: int = 1,
    deterministic: Optional[bool] = None,
    sharding: bool = True,
    enable_tf_data_service: bool = False,
    tf_data_service_address: Optional[str] = None,
    tf_data_service_job_name: Optional[str] = None,
    tfds_data_dir: str = '',
    tfds_as_supervised: bool = False,
    tfds_skip_decoding_feature: str = '',
    enable_shared_tf_data_service_between_parallel_trainers: bool = False,
    apply_tf_data_service_before_batching: bool = False,
    trainer_id: Optional[str] = None,
    seed: Optional[int] = None,
    prefetch_buffer_size: Optional[int] = None,
    autotune_algorithm: Optional[str] = None,
    name: Optional[str] = None,
    file_type: Optional[str] = 'tfrecord',
    compressed_input: bool = False,
    split: str = 'train',
    variant_name: Optional[str] = None,
    feature_shape: Tuple[int, ...] = tfm.vision.configs.video_classification.DataConfig.feature_shape,
    temporal_stride: int = 1,
    random_stride_range: int = 0,
    num_test_clips: int = 1,
    num_test_crops: int = 1,
    num_classes: int = -1,
    num_examples: int = -1,
    data_format: str = 'channels_last',
    dtype: str = 'float32',
    label_dtype: str = 'int32',
    one_hot: bool = True,
    min_image_size: int = 256,
    zero_centering_image: bool = False,
    is_multilabel: bool = False,
    output_audio: bool = False,
    audio_feature: str = '',
    audio_feature_shape: Tuple[int, ...] = tfm.vision.configs.video_classification.DataConfig.audio_feature_shape,
    aug_min_aspect_ratio: float = 0.5,
    aug_max_aspect_ratio: float = 2.0,
    aug_min_area_ratio: float = 0.49,
    aug_max_area_ratio: float = 1.0,
    aug_type: Optional[tfm.vision.configs.common.Augmentation] = None,
    mixup_and_cutmix: Optional[tfm.vision.configs.common.MixupAndCutmix] = None,
    image_field_key: str = 'image/encoded',
    label_field_key: str = 'clip/label/index',
    input_image_format: str = 'jpeg'
)

BUILDER

default_params Dataclass field
restrictions Dataclass field
input_path Dataclass field
tfds_name Dataclass field
tfds_split Dataclass field
global_batch_size Dataclass field
is_training Dataclass field
drop_remainder Dataclass field
shuffle_buffer_size Dataclass field
cache Dataclass field
cycle_length Dataclass field
block_length Dataclass field
deterministic Dataclass field
sharding Dataclass field
enable_tf_data_service Dataclass field
tf_data_service_address Dataclass field
tf_data_service_job_name Dataclass field
tfds_data_dir Dataclass field
tfds_as_supervised Dataclass field
tfds_skip_decoding_feature Dataclass field
enable_shared_tf_data_service_between_parallel_trainers Dataclass field
apply_tf_data_service_before_batching Dataclass field
trainer_id Dataclass field
seed Dataclass field
prefetch_buffer_size Dataclass field
autotune_algorithm Dataclass field
name Dataclass field
file_type Dataclass field
compressed_input Dataclass field
split Dataclass field
variant_name Dataclass field
feature_shape Dataclass field
temporal_stride Dataclass field
random_stride_range Dataclass field
num_test_clips Dataclass field
num_test_crops Dataclass field
num_classes Dataclass field
num_examples Dataclass field
data_format Dataclass field
dtype Dataclass field
label_dtype Dataclass field
one_hot Dataclass field
min_image_size Dataclass field
zero_centering_image Dataclass field
is_multilabel Dataclass field
output_audio Dataclass field
audio_feature Dataclass field
audio_feature_shape Dataclass field
aug_min_aspect_ratio Dataclass field
aug_max_aspect_ratio Dataclass field
aug_min_area_ratio Dataclass field
aug_max_area_ratio Dataclass field
aug_type Dataclass field
mixup_and_cutmix Dataclass field
image_field_key Dataclass field
label_field_key Dataclass field
input_image_format 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'>)
apply_tf_data_service_before_batching False
audio_feature ''
audio_feature_shape (-1,)
aug_max_area_ratio 1.0
aug_max_aspect_ratio 2.0
aug_min_area_ratio 0.49
aug_min_aspect_ratio 0.5
aug_type None
autotune_algorithm None
block_length 1
cache False
compressed_input False
cycle_length 10
data_format 'channels_last'
default_params None
deterministic None
drop_remainder True
dtype 'float32'
enable_shared_tf_data_service_between_parallel_trainers False
enable_tf_data_service False
feature_shape (64, 224, 224, 3)
file_type 'tfrecord'
global_batch_size 128
image_field_key 'image/encoded'
input_image_format 'jpeg'
input_path ''
is_multilabel False
is_training True
label_dtype 'int32'
label_field_key 'clip/label/index'
min_image_size 256
mixup_and_cutmix None
name None
num_classes -1
num_examples -1
num_test_clips 1
num_test_crops 1
one_hot True
output_audio False
prefetch_buffer_size None
random_stride_range 0
restrictions None
seed None
sharding True
shuffle_buffer_size 64
split 'train'
temporal_stride 1
tf_data_service_address None
tf_data_service_job_name None
tfds_as_supervised False
tfds_data_dir ''
tfds_name ''
tfds_skip_decoding_feature ''
tfds_split ''
trainer_id None
variant_name None
zero_centering_image False