mediapipe_model_maker.text_classifier.AverageWordEmbeddingModelOptions

Configurable model options for an Average Word Embedding classifier.

mediapipe_model_maker.text_classifier.AverageWordEmbeddingModelOptions(
    seq_len: int = 256,
    wordvec_dim: int = 16,
    do_lower_case: bool = True,
    vocab_size: int = 10000,
    dropout_rate: float = 0.2
)

seq_len Length of the sequence to feed into the model.
wordvec_dim Dimension of the word embedding.
do_lower_case Whether to convert all uppercase characters to lowercase during preprocessing.
vocab_size Number of words to generate the vocabulary from data.
dropout_rate The rate for dropout.

Methods

__eq__

__eq__(
    other
)

do_lower_case True
dropout_rate 0.2
seq_len 256
vocab_size 10000
wordvec_dim 16