tflite_model_maker.question_answer.MobileBertQaSpec

Creates MobileBert model spec for the question answer task. See also: tflite_model_maker.question_answer.BertQaSpec.

tflite_model_maker.question_answer.MobileBertQaSpec(
    *,
    uri='https://hub.tensorflow.google.cn/google/mobilebert/uncased_L-24_H-128_B-512_A-4_F-4_OPT/1',
    model_dir=None,
    seq_len=384,
    query_len=64,
    doc_stride=128,
    dropout_rate=0.1,
    initializer_range=0.02,
    learning_rate=4e-05,
    distribution_strategy='off',
    num_gpus=-1,
    tpu='',
    trainable=True,
    predict_batch_size=8,
    do_lower_case=True,
    is_tf2=False,
    tflite_input_name=None,
    tflite_output_name=None,
    init_from_squad_model=False,
    default_batch_size=32,
    name='MobileBert'
)

Args
`uri`	TF-Hub path/url to Bert module.
`model_dir`	The location of the model checkpoint files.
`seq_len`	Length of the sequence to feed into the model.
`query_len`	Length of the query to feed into the model.
`doc_stride`	The stride when we do a sliding window approach to take chunks of the documents.
`dropout_rate`	The rate for dropout.
`initializer_range`	The stdev of the truncated_normal_initializer for initializing all weight matrices.
`learning_rate`	The initial learning rate for Adam.
`distribution_strategy`	A string specifying which distribution strategy to use. Accepted values are 'off', 'one_device', 'mirrored', 'parameter_server', 'multi_worker_mirrored', and 'tpu' -- case insensitive. 'off' means not to use Distribution Strategy; 'tpu' means to use TPUStrategy using `tpu_address`.
`num_gpus`	How many GPUs to use at each worker with the DistributionStrategies API. The default is -1, which means utilize all available GPUs.
`tpu`	TPU address to connect to.
`trainable`	boolean, whether pretrain layer is trainable.
`predict_batch_size`	Batch size for prediction.
`do_lower_case`	boolean, whether to lower case the input text. Should be True for uncased models and False for cased models.
`is_tf2`	boolean, whether the hub module is in TensorFlow 2.x format.
`tflite_input_name`	Dict, input names for the TFLite model.
`tflite_output_name`	Dict, output names for the TFLite model.
`init_from_squad_model`	boolean, whether to initialize from the model that is already retrained on Squad 1.1.
`default_batch_size`	Default batch size for training.
`name`	Name of the object.

tflite_model_maker.question_answer.MobileBertQaSpec

Args