def pad_batch_BERT(self, batch, bert_layers, bert_dims):
num_sentences = [len(x) for x in batch]
max_num_sentences = max(num_sentences)
batch, no_padding_num_sentences = hF.pad_batch_with_sentences_BERT(
batch, max_num_sentences, bert_layers, bert_dims)
##########################################
return batch, max_num_sentences, None, no_padding_num_sentences, None
def encode_and_pad_BERT(self, data_batches, Bert_model_Path, device,
bert_layers, bert_dims):
from pytorch_pretrained_bert import BertTokenizer, BertModel
tokenizer = BertTokenizer.from_pretrained(
Bert_model_Path
) # '../../pytorch-pretrained-BERT/bert_models/uncased_L-12_H-768_A-12/')
model = BertModel.from_pretrained(
Bert_model_Path
) # '../../pytorch-pretrained-BERT/bert_models/uncased_L-12_H-768_A-12/')
model.eval()
model.to(device)
#################### Prepare Training data################
print('Encoding Data using BERT...')
max_sentences = []
no_padding_sentences = []
for index, batch in tqdm(enumerate(data_batches)):
batch = hF.encode_batch_BERT(batch, model, tokenizer, device,
bert_layers)
# data_batches[index] = batch
num_sentences = [len(x) for x in batch]
max_num_sentences = max(num_sentences)
batch, no_padding_num_sentences = hF.pad_batch_with_sentences_BERT(
batch, max_num_sentences, bert_layers, bert_dims)
max_sentences.append(max_num_sentences)
no_padding_sentences.append(no_padding_num_sentences)
data_batches[index] = batch
##########################################
return data_batches, max_sentences, None, no_padding_sentences, None
def pad_BERT(self, data_batches, bert_layers, bert_dims):
print('Padding Data using BERT...')
max_sentences = []
no_padding_sentences = []
for index, batch in tqdm(enumerate(data_batches)):
num_sentences = [len(x) for x in batch]
max_num_sentences = max(num_sentences)
batch, no_padding_num_sentences = hF.pad_batch_with_sentences_BERT(
batch, max_num_sentences, bert_layers, bert_dims)
max_sentences.append(max_num_sentences)
no_padding_sentences.append(no_padding_num_sentences)
data_batches[index] = batch
##########################################
return data_batches, max_sentences, None, no_padding_sentences, None