Spaces:
Running
Running
File size: 2,387 Bytes
2205ed4 5f2b86f 2205ed4 0879cff e6c86bb e5fcabb 2205ed4 0879cff 2205ed4 e5fcabb 2205ed4 924cabe 2205ed4 4707c41 9d6299e 2205ed4 9d6299e |
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 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 |
import torch
from transformers import AutoModel, AutoTokenizer
from underthesea import word_tokenize
import __main__
#phobert = AutoModel.from_pretrained("vinai/phobert-base")
tokenizer = AutoTokenizer.from_pretrained("./bert/bert_tokenizer")
class PhoBertModel(torch.nn.Module):
def __init__(self):
super(PhoBertModel, self).__init__()
self.bert = phobert
self.pre_classifier = torch.nn.Linear(self.bert.config.hidden_size, self.bert.config.hidden_size)
self.dropout = torch.nn.Dropout(0.1)
self.classifier = torch.nn.Linear(self.bert.config.hidden_size, 6)
def forward(self, input_ids, attention_mask, token_type_ids):
hidden_state, output_1 = self.bert(
input_ids = input_ids,
attention_mask=attention_mask,
return_dict = False
)
pooler = self.pre_classifier(output_1)
activation_1 = torch.nn.Tanh()(pooler)
drop = self.dropout(activation_1)
output_2 = self.classifier(drop)
# activation_2 = torch.nn.Tanh()(output_2)
output = torch.nn.Sigmoid()(output_2)
return output
setattr(__main__, "PhoBertModel", PhoBertModel)
def getModel():
model = torch.load('./bert/phoBertModel.pth', map_location=torch.device('cpu'))
model.eval()
return model
model = getModel()
def tokenize(data):
max_length = 200
for line in data:
token = tokenizer.encode_plus(
line,
max_length=200,
add_special_tokens=False,
pad_to_max_length=True
)
ids = torch.tensor([token['input_ids']])
mask = torch.tensor([token['attention_mask']])
token_type_ids = torch.tensor([token['token_type_ids']])
output = {
'ids': ids,
'mask': mask,
'token_type_ids': token_type_ids,
}
#outputs.append(output)
return output
def BERT_predict(text):
text = [text]
token = tokenize(text)
ids = token['ids']
mask = token['mask']
token_type_ids = token['token_type_ids']
result = model(ids, mask, token_type_ids)
print(result)
# print(result)
return result.tolist()[0]
print(BERT_predict("xin chaof"))
print(BERT_predict("con chó"))
print(BERT_predict("đồ chó"))
print(BERT_predict("đồ ngu"))
print(BERT_predict("cái lồn"))
print(BERT_predict("óc chó"))
print(BERT_predict("đồ chó đẻ"))
print(BERT_predict("con đĩ")) |