bert_torch_dataset_creator.py

from torch.utils.data import Dataset, DataLoader
import torch

class GPTweetDataset(Dataset):

    def __init__(self, texts, targets, tokenizer, max_len):
        self.texts = texts
        self.targets = targets
        self.tokenizer = tokenizer
        self.max_len = max_len

    def __len__(self):
        return len(self.texts)

    def __getitem__(self, item):
        text = str(self.texts[item])
        target = self.targets[item]

        encoding = self.tokenizer.encode_plus(
            text,
            add_special_tokens=True,
            max_length=self.max_len,
            return_token_type_ids=False,
            pad_to_max_length=True,
            return_attention_mask=True,
            return_tensors='pt',
            #truncation=True
        )

        return {
            'tweet_text': text,
            'input_ids': encoding['input_ids'].flatten(),
            'attention_mask': encoding['attention_mask'].flatten(),
            #'labels': torch.tensor(label, dtype=torch.long)
            'targets': torch.tensor(target, dtype=torch.long)

        }