File size: 1,700 Bytes
b3aa083 |
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 |
import torch
import transformers
from transformers import BertModel, BertTokenizer, AutoTokenizer
from torch import nn, optim
from torch.utils.data import Dataset, DataLoader
import torch.nn.functional as F
###########################################################
review_text = "I love you"
###########################################################
PRE_TRAINED_MODEL_NAME = 'nreimers/BERT-Tiny_L-2_H-128_A-2'
class_names = ["Normal", "Abusive"]
MAX_LEN = "max_length"
class CyberbullyingClassifier(nn.Module):
def __init__(self, n_classes):
super(CyberbullyingClassifier, self).__init__()
self.bert = BertModel.from_pretrained(PRE_TRAINED_MODEL_NAME).to("cpu")
# self.drop = nn.Dropout(p=0.3)
self.out = nn.Linear(self.bert.config.hidden_size, n_classes)
def forward(self, input_ids, attention_mask):
bert_out = self.bert(
input_ids=input_ids,
attention_mask=attention_mask
)
pooled_output = bert_out[1]
# output = self.drop(pooled_output)
return self.out(pooled_output)
tokenizer = AutoTokenizer.from_pretrained(PRE_TRAINED_MODEL_NAME)
model = CyberbullyingClassifier(2)
model.load_state_dict(torch.load('./best_model_state.bin', map_location=torch.device('cpu')))
def classify(review_text):
encoded_review = tokenizer(review_text, padding=MAX_LEN, truncation=True, return_tensors="pt")
input_ids = encoded_review['input_ids'].to('cpu')
attention_mask = encoded_review['attention_mask'].to('cpu')
output = model(input_ids, attention_mask)
_, prediction = torch.max(output, dim=1)
print(f'Review text: {review_text}')
print(f'Sentiment : {class_names[prediction]}')
return class_names[prediction] |