mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-07 23:00:08 +06:00
41 lines
2.3 KiB
Python
41 lines
2.3 KiB
Python
import tensorflow as tf
|
|
import tensorflow_datasets
|
|
from transformers import BertTokenizer, TFBertForSequenceClassification, glue_convert_examples_to_features, BertForSequenceClassification
|
|
|
|
# Load dataset, tokenizer, model from pretrained model/vocabulary
|
|
tokenizer = BertTokenizer.from_pretrained('bert-base-cased')
|
|
model = TFBertForSequenceClassification.from_pretrained('bert-base-cased')
|
|
data = tensorflow_datasets.load('glue/mrpc')
|
|
|
|
# Prepare dataset for GLUE as a tf.data.Dataset instance
|
|
train_dataset = glue_convert_examples_to_features(data['train'], tokenizer, 128, 'mrpc')
|
|
valid_dataset = glue_convert_examples_to_features(data['validation'], tokenizer, 128, 'mrpc')
|
|
train_dataset = train_dataset.shuffle(100).batch(32).repeat(2)
|
|
valid_dataset = valid_dataset.batch(64)
|
|
|
|
# Prepare training: Compile tf.keras model with optimizer, loss and learning rate schedule
|
|
optimizer = tf.keras.optimizers.Adam(learning_rate=3e-5, epsilon=1e-08, clipnorm=1.0)
|
|
loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
|
|
metric = tf.keras.metrics.SparseCategoricalAccuracy('accuracy')
|
|
model.compile(optimizer=optimizer, loss=loss, metrics=[metric])
|
|
|
|
# Train and evaluate using tf.keras.Model.fit()
|
|
history = model.fit(train_dataset, epochs=2, steps_per_epoch=115,
|
|
validation_data=valid_dataset, validation_steps=7)
|
|
|
|
# Load the TensorFlow model in PyTorch for inspection
|
|
model.save_pretrained('./save/')
|
|
pytorch_model = BertForSequenceClassification.from_pretrained('./save/', from_tf=True)
|
|
|
|
# Quickly test a few predictions - MRPC is a paraphrasing task, let's see if our model learned the task
|
|
sentence_0 = "This research was consistent with his findings."
|
|
sentence_1 = "His findings were compatible with this research."
|
|
sentence_2 = "His findings were not compatible with this research."
|
|
inputs_1 = tokenizer.encode_plus(sentence_0, sentence_1, add_special_tokens=True, return_tensors='pt')
|
|
inputs_2 = tokenizer.encode_plus(sentence_0, sentence_2, add_special_tokens=True, return_tensors='pt')
|
|
|
|
pred_1 = pytorch_model(**inputs_1)[0].argmax().item()
|
|
pred_2 = pytorch_model(**inputs_2)[0].argmax().item()
|
|
print("sentence_1 is", "a paraphrase" if pred_1 else "not a paraphrase", "of sentence_0")
|
|
print("sentence_2 is", "a paraphrase" if pred_2 else "not a paraphrase", "of sentence_0")
|