MARI-posa commited on
Commit
fb540e3
1 Parent(s): 1fcea40

Update stri.py

Browse files
Files changed (1) hide show
  1. stri.py +3 -3
stri.py CHANGED
@@ -16,10 +16,10 @@ model = AutoModel.from_pretrained(model_name, output_hidden_states=True)
16
  books = pd.read_csv('book_6000.csv')
17
  books.dropna(inplace=True)
18
 
19
- books = books.reset_index(drop=True)
20
  books = books[books['annotation'].apply(lambda x: len(x.split()) >= 10)]
21
  books.drop_duplicates(subset='title', keep='first', inplace=True)
22
- books.reset_index(drop=True)
23
 
24
 
25
  def data_preprocessing(text: str) -> str:
@@ -50,7 +50,7 @@ book_embeddings = []
50
  for inputs, attention_masks in zip(input_ids, attention_mask):
51
  with torch.no_grad():
52
  book_embedding = model(inputs.unsqueeze(0), attention_mask=attention_masks.unsqueeze(0))
53
- book_embedding = book_embedding[0][:, 0, :].detach().cpu().numpy()
54
  book_embeddings.append(np.squeeze(book_embedding))
55
 
56
  # Определение запроса пользователя
 
16
  books = pd.read_csv('book_6000.csv')
17
  books.dropna(inplace=True)
18
 
19
+
20
  books = books[books['annotation'].apply(lambda x: len(x.split()) >= 10)]
21
  books.drop_duplicates(subset='title', keep='first', inplace=True)
22
+ books = books.reset_index(drop=True)
23
 
24
 
25
  def data_preprocessing(text: str) -> str:
 
50
  for inputs, attention_masks in zip(input_ids, attention_mask):
51
  with torch.no_grad():
52
  book_embedding = model(inputs.unsqueeze(0), attention_mask=attention_masks.unsqueeze(0))
53
+ book_embedding = book_embedding[0][:, 0, :]#.detach().cpu().numpy()
54
  book_embeddings.append(np.squeeze(book_embedding))
55
 
56
  # Определение запроса пользователя