File size: 2,215 Bytes
bbfebbe |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 |
import transformers
import torch
from torch.utils.data import Dataset, DataLoader, RandomSampler, SequentialSampler
from transformers import DistilBertTokenizer, DistilBertModel
import logging
logging.basicConfig(level=logging.ERROR)
import torch.nn as nn
from torch.nn import functional as F
import torch.optim as optim
import pandas as pd
import numpy as np
# Điều chỉnh các tham số
MAX_LEN = 100
TRAIN_BATCH_SIZE = 4
VALID_BATCH_SIZE = 4
EPOCHS = 1
LEARNING_RATE = 1e-05
tokenizer_DB = DistilBertTokenizer.from_pretrained('distilbert-base-uncased', truncation=True, do_lower_case=True)
# Tạo dataframe
# Tạo class
class BinaryLabel(Dataset):
def __init__(self, dataframe, tokenizer, max_len):
self.tokenizer = tokenizer_DB
self.data = dataframe
self.text = dataframe.text
self.targets = self.data.label
self.max_len = max_len
def __len__(self):
return len(self.text)
def __getitem__(self, index):
text = str(self.text[index])
text = " ".join(text.split())
inputs = self.tokenizer.encode_plus(
text,
None,
add_special_tokens=True,
max_length=self.max_len,
pad_to_max_length=True,
return_token_type_ids=True
)
ids = inputs['input_ids']
mask = inputs['attention_mask']
token_type_ids = inputs["token_type_ids"]
return {
'ids': torch.tensor(ids, dtype=torch.long),
'mask': torch.tensor(mask, dtype=torch.long),
'token_type_ids': torch.tensor(token_type_ids, dtype=torch.long),
'targets': torch.tensor(self.targets[index], dtype=torch.float)
}
train_params = {'batch_size': TRAIN_BATCH_SIZE,
'shuffle': True,
'num_workers': 0
}
test_params = {'batch_size': VALID_BATCH_SIZE,
'shuffle': True,
'num_workers': 0
}
training_set = BinaryLabel(train_df_DB, tokenizer, MAX_LEN)
testing_set = BinaryLabel(test_df_DB, tokenizer, MAX_LEN)
training_loader = DataLoader(training_set, **train_params)
testing_loader = DataLoader(testing_set, **test_params) |