SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

add batch dimension in encode

Browse Source
This commit is contained in:
thomwolf
2019-09-26 01:45:55 +02:00
parent 4a21c4d88d
commit d6dde438ea
2 changed files with 8 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
examples/run_tf_glue.py
View File

@@ -20,51 +20,12 @@ loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
tf_model.compile(optimizer=optimizer, loss=loss, metrics=['sparse_categorical_accuracy']) tf_model.compile(optimizer=optimizer, loss=loss, metrics=['sparse_categorical_accuracy'])
# Train and evaluate using tf.keras.Model.fit() # Train and evaluate using tf.keras.Model.fit()
tf_model.fit(train_dataset, epochs=1, steps_per_epoch=115, validation_data=valid_dataset, validation_steps=7) tf_model.fit(train_dataset, epochs=3, steps_per_epoch=115, validation_data=valid_dataset, validation_steps=7)
# Save the model and load it in PyTorch # Save the model and load it in PyTorch
tf_model.save_pretrained('./runs/') tf_model.save_pretrained('./runs/')
pt_model = BertForSequenceClassification.from_pretrained('./runs/') pt_model = BertForSequenceClassification.from_pretrained('./runs/', from_tf=True)
# Quickly inspect a few predictions # Quickly inspect a few predictions
inputs = tokenizer.encode_plus("I said the company is doing great", "The company has good results", add_special_tokens=True) inputs = tokenizer.encode_plus("I said the company is doing great", "The company has good results", add_special_tokens=True, return_tensors='pt')
pred = pt_model(torch.tensor([tokens])) pred = pt_model(torch.tensor(tokens))
# Divers
import torch
import tensorflow as tf
import tensorflow_datasets
from pytorch_transformers import BertTokenizer, BertForSequenceClassification, TFBertForSequenceClassification, glue_convert_examples_to_features
# Load tokenizer, model, dataset
tokenizer = BertTokenizer.from_pretrained('bert-base-cased')
model = TFBertForSequenceClassification.from_pretrained('bert-base-cased')
pt_train_dataset = torch.load('../../data/glue_data//MRPC/cached_train_bert-base-cased_128_mrpc')
def gen():
for el in pt_train_dataset:
yield ((el.input_ids, el.attention_mask, el.token_type_ids), (el.label,))
dataset = tf.data.Dataset.from_generator(gen,
((tf.int32, tf.int32, tf.int32), (tf.int64,)),
((tf.TensorShape([None]), tf.TensorShape([None]), tf.TensorShape([None])),
(tf.TensorShape([]),)))
dataset = dataset.shuffle(100).batch(32)
next(iter(dataset))
learning_rate = tf.keras.optimizers.schedules.PolynomialDecay(2e-5, 345, 0)
loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
model.compile(optimizer=tf.keras.optimizers.Adam(
learning_rate=learning_rate,
epsilon=1e-08,
clipnorm=1.0),
loss=loss,
metrics=[['sparse_categorical_accuracy']])
tensorboard_cbk = tf.keras.callbacks.TensorBoard(log_dir='./runs/', update_freq=10, histogram_freq=1)
# Train model
model.fit(dataset, epochs=3, callbacks=[tensorboard_cbk])

8
pytorch_transformers/tokenization_utils.py
View File

@@ -849,11 +849,11 @@ class PreTrainedTokenizer(object):
token_type_ids = [0] * len(ids) + ([1] * len(pair_ids) if pair else []) token_type_ids = [0] * len(ids) + ([1] * len(pair_ids) if pair else [])
if return_tensors == 'tf' and is_tf_available(): if return_tensors == 'tf' and is_tf_available():
sequence = tf.constant(sequence) sequence = tf.constant([sequence])
token_type_ids = tf.constant(token_type_ids) token_type_ids = tf.constant([token_type_ids])
elif return_tensors == 'pt' and is_torch_available(): elif return_tensors == 'pt' and is_torch_available():
sequence = torch.tensor(sequence) sequence = torch.tensor([sequence])
token_type_ids = torch.tensor(token_type_ids) token_type_ids = torch.tensor([token_type_ids])
elif return_tensors is not None: elif return_tensors is not None:
logger.warning("Unable to convert output to tensors format {}, PyTorch or TensorFlow is not available.".format(return_tensors)) logger.warning("Unable to convert output to tensors format {}, PyTorch or TensorFlow is not available.".format(return_tensors))