hanneshapke

{
    'input_mask': array(
        [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]),
    'input_type_ids': array(
        [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]),
    'input_word_ids': array(
        [  101,  2023,  3319,  3397, 27594,  2545,  2005,  2216,  2040, ..., 2014,   102]),
    'label': array([0])
}

hanneshapke

mirrored_strategy = tf.distribute.MirroredStrategy()
with mirrored_strategy.scope():
    model = get_model(tf_transform_output=tf_transform_output)

hanneshapke

def run_fn(fn_args: TrainerFnArgs):
    tf_transform_output = tft.TFTransformOutput(fn_args.transform_output)
    train_dataset = _input_fn(
        fn_args.train_files, tf_transform_output, 32)
    eval_dataset = _input_fn(
        fn_args.eval_files, tf_transform_output, 32)
 
    mirrored_strategy = tf.distribute.MirroredStrategy()
    with mirrored_strategy.scope():
        model = get_model(tf_transform_output=tf_transform_output)

hanneshapke

input_word_ids = tf.cast(inputs["input_word_ids"], dtype=tf.int32)
input_mask = tf.cast(inputs["input_mask"], dtype=tf.int32)
input_type_ids = tf.cast(inputs["input_type_ids"], dtype=tf.int32)

hanneshapke

    feature_spec = tf_transform_output.transformed_feature_spec() 
    feature_spec.pop(_LABEL_KEY)

    inputs = {key: tf.keras.layers.Input(shape=(max_seq_length), 
                                         name=key, dtype=tf.int32)
              for key in feature_spec.keys()}
  
    input_word_ids = tf.cast(inputs["input_word_ids"], dtype=tf.int32)
    input_mask = tf.cast(inputs["input_mask"], dtype=tf.int32)
    input_type_ids = tf.cast(inputs["input_type_ids"], dtype=tf.int32)

hanneshapke

input_type_ids = tf.zeros_like(input_mask)

hanneshapke

def preprocessing_fn(inputs):
    
    def tokenize_text(text, sequence_length=MAX_SEQ_LEN):
	  ...
        return tf.reshape(tokens, [-1, sequence_length])
 
    def preprocess_bert_input(text, segment_id=0):
        input_word_ids = tokenize_text(text)
        ...        
        return (

hanneshapke

CLS_ID = tf.constant(101, dtype=tf.int64)
SEP_ID = tf.constant(102, dtype=tf.int64)

start_tokens = tf.fill([tf.shape(text)[0], 1], CLS_ID)
end_tokens = tf.fill([tf.shape(text)[0], 1], SEP_ID)

tokens = tokens[:, :sequence_length - 2]
tokens = tf.concat([start_tokens, tokens, end_tokens], axis=1)

hanneshapke

tokens = bert_tokenizer.tokenize(text)

hanneshapke

bert_tokenizer = text.BertTokenizer(
    vocab_lookup_table=vocab_file_path, 
    token_out_type=tf.int64, 
    lower_case=do_lower_case
)