~8 min · keras-nlp
가장 흔한 NLP task. BertClassifier.from_preset('bert_base_en', num_classes=2) — pretrained backbone + classification head 한 줄. fit(texts, labels) 하면 학습.
입력은 string list 그대로 OK — preprocessor 가 자동 tokenize + padding. label 은 0/1 (binary) 또는 0..N-1 (multi-class). compile (loss + optimizer + accuracy) → fit → evaluate. transfer learning 의 가장 빠른 패턴.
import keras_hub
# Load BERT for classification
classifier = keras_hub.models.BertClassifier.from_preset(
"bert_base_en",
num_classes=2, # Binary sentiment
)
# Compile and train
classifier.compile(
optimizer=keras.optimizers.Adam(5e-5),
loss="sparse_categorical_crossentropy",
metrics=["accuracy"],
)
classifier.fit(train_ds, validation_data=val_ds, epochs=3)아직 댓글이 없어요. 첫 댓글을 남겨보세요.