Have a question? Connect with the community at the TensorFlow Forum Visit Forum

tflite_model_maker.text_classifier.BertClassifierSpec

A specification of BERT model for text classification.

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.
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.
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.
name The name of the object.
tflite_input_name Dict, input names for the TFLite model.
default_batch_size Default batch size for training.

Methods

build

Builds the class. Used for lazy initialization.

convert_examples_to_features

Converts examples to features and write them into TFRecord file.

create_model

Creates the keras model.

get_config

Gets the configuration.

get_default_quantization_config

Gets the default quantization configuration.

get_name_to_features

Gets the dictionary describing the features.

reorder_input_details

Reorders the tflite input details to map the order of keras model.

run_classifier

Creates classifier and runs the classifier training.

save_vocab

Prints the file path to the vocabulary.

select_data_from_record

Dispatches records to features and labels.

compat_tf_versions [2]
convert_from_saved_model_tf2 True
need_gen_vocab False