Albert分类器模型
AlbertClassifier class
keras_nlp.models.AlbertClassifier(
backbone, num_classes, preprocessor=None, activation=None, dropout=0.1, **kwargs
)
An end-to-end ALBERT model for classification tasks
This model attaches a classification head to a keras_nlp.model.AlbertBackbone
backbone, mapping from the backbone outputs to logit output suitable for
a classification task. For usage of this model with pre-trained weights, see
the from_preset() method.
This model can optionally be configured with a preprocessor layer, in
which case it will automatically apply preprocessing to raw inputs during
fit(), predict(), and evaluate(). This is done by default when
creating the model with from_preset().
Disclaimer: Pre-trained models are provided on an "as is" basis, without warranties or conditions of any kind.
Arguments
- backbone: A
keras_nlp.models.AlertBackboneinstance. - num_classes: int. Number of classes to predict.
- preprocessor: A
keras_nlp.models.AlbertPreprocessororNone. IfNone, this model will not apply preprocessing, and inputs should be preprocessed before calling the model. - activation: Optional
stror callable. The activation function to use on the model outputs. Setactivation="softmax"to return output probabilities. Defaults toNone. - dropout: float. The dropout probability value, applied after the dense layer.
Examples
Raw string data.
features = ["The quick brown fox jumped.", "I forgot my homework."]
labels = [0, 3]
# Pretrained classifier.
classifier = keras_nlp.models.AlbertClassifier.from_preset(
"albert_base_en_uncased",
num_classes=4,
)
classifier.fit(x=features, y=labels, batch_size=2)
classifier.predict(x=features, batch_size=2)
# Re-compile (e.g., with a new learning rate).
classifier.compile(
loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
optimizer=keras.optimizers.Adam(5e-5),
jit_compile=True,
)
# Access backbone programmatically (e.g., to change `trainable`).
classifier.backbone.trainable = False
# Fit again.
classifier.fit(x=features, y=labels, batch_size=2)
Preprocessed integer data.
features = {
"token_ids": np.ones(shape=(2, 12), dtype="int32"),
"segment_ids": np.array([[0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0]] * 2),
"padding_mask": np.array([[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0]] * 2),
}
labels = [0, 3]
# Pretrained classifier without preprocessing.
classifier = keras_nlp.models.AlbertClassifier.from_preset(
"albert_base_en_uncased",
num_classes=4,
preprocessor=None,
)
classifier.fit(x=features, y=labels, batch_size=2)
Custom backbone and vocabulary.
features = ["The quick brown fox jumped.", "I forgot my homework."]
labels = [0, 3]
bytes_io = io.BytesIO()
ds = tf.data.Dataset.from_tensor_slices(features)
sentencepiece.SentencePieceTrainer.train(
sentence_iterator=ds.as_numpy_iterator(),
model_writer=bytes_io,
vocab_size=10,
model_type="WORD",
pad_id=0,
unk_id=1,
bos_id=2,
eos_id=3,
pad_piece="<pad>",
unk_piece="<unk>",
bos_piece="[CLS]",
eos_piece="[SEP]",
user_defined_symbols="[MASK]",
)
tokenizer = keras_nlp.models.AlbertTokenizer(
proto=bytes_io.getvalue(),
)
preprocessor = keras_nlp.models.AlbertPreprocessor(
tokenizer=tokenizer,
sequence_length=128,
)
backbone = keras_nlp.models.AlbertBackbone(
vocabulary_size=tokenizer.vocabulary_size(),
num_layers=4,
num_heads=4,
hidden_dim=256,
embedding_dim=128,
intermediate_dim=512,
max_sequence_length=128,
)
classifier = keras_nlp.models.AlbertClassifier(
backbone=backbone,
preprocessor=preprocessor,
num_classes=4,
)
classifier.fit(x=features, y=labels, batch_size=2)
from_preset method
AlbertClassifier.from_preset(preset, load_weights=True, **kwargs)
Instantiate a keras_nlp.models.Task from a model preset.
A preset is a directory of configs, weights and other file assets used
to save and load a pre-trained model. The preset can be passed as a
one of:
- a built in preset identifier like
'bert_base_en' - a Kaggle Models handle like
'kaggle://user/bert/keras/bert_base_en' - a Hugging Face handle like
'hf://user/bert_base_en' - a path to a local preset directory like
'./bert_base_en'
For any Task subclass, you can run cls.presets.keys() to list all
built-in presets available on the class.
This constructor can be called in one of two ways. Either from a task
specific base class like keras_nlp.models.CausalLM.from_preset(), or
from a model class like keras_nlp.models.BertClassifier.from_preset().
If calling from the a base class, the subclass of the returning object
will be inferred from the config in the preset directory.
Arguments
- preset: string. A built in preset identifier, a Kaggle Models handle, a Hugging Face handle, or a path to a local directory.
- load_weights: bool. If
True, the weights will be loaded into the model architecture. IfFalse, the weights will be randomly initialized.
Examples
# Load a Gemma generative task.
causal_lm = keras_nlp.models.CausalLM.from_preset(
"gemma_2b_en",
)
# Load a Bert classification task.
model = keras_nlp.models.Classifier.from_preset(
"bert_base_en",
num_classes=2,
)
| Preset name | Parameters | Description |
|---|---|---|
| albert_base_en_uncased | 11.68M | 12-layer ALBERT model where all input is lowercased. Trained on English Wikipedia + BooksCorpus. |
| albert_large_en_uncased | 17.68M | 24-layer ALBERT model where all input is lowercased. Trained on English Wikipedia + BooksCorpus. |
| albert_extra_large_en_uncased | 58.72M | 24-layer ALBERT model where all input is lowercased. Trained on English Wikipedia + BooksCorpus. |
| albert_extra_extra_large_en_uncased | 222.60M | 12-layer ALBERT model where all input is lowercased. Trained on English Wikipedia + BooksCorpus. |
backbone property
keras_nlp.models.AlbertClassifier.backbone
A keras_nlp.models.Backbone model with the core architecture.
preprocessor property
keras_nlp.models.AlbertClassifier.preprocessor
A keras_nlp.models.Preprocessor layer used to preprocess input.