Spaces:
Sleeping
Sleeping
File size: 1,985 Bytes
a65b2d6 |
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 |
import torch
from transformers import BertTokenizer, BertModel
from torch.nn import Embedding
import numpy as np
# BERT 모델 및 토크나이저 로드
tokenizer = BertTokenizer.from_pretrained("klue/bert-base")
bert_model = BertModel.from_pretrained("klue/bert-base")
# 상품 데이터 임베딩
def embed_product_data(product_data):
text = product_data.get("title", "") + " " + product_data.get("description", "")
inputs = tokenizer(
text, return_tensors="pt", truncation=True, padding=True, max_length=128
)
outputs = bert_model(**inputs)
text_embedding = outputs.last_hidden_state.mean(dim=1)
category_embedding_layer = Embedding(num_embeddings=50, embedding_dim=16)
color_embedding_layer = Embedding(num_embeddings=20, embedding_dim=8)
category_id = product_data.get("category_id", 0)
color_id = product_data.get("color_id", 0)
category_embedding = category_embedding_layer(torch.tensor([category_id]))
color_embedding = color_embedding_layer(torch.tensor([color_id]))
combined_embedding = torch.cat((text_embedding, category_embedding, color_embedding), dim=1)
return combined_embedding.detach().numpy()
# 사용자 데이터 임베딩
def embed_user_data(user_data):
embedding_layer = Embedding(num_embeddings=100, embedding_dim=128)
gender_id = 0 if user_data['gender'] == 'M' else 1
scaled_height = int((user_data['height'] - 50) * 99 // 200)
scaled_weight = int((user_data['weight'] - 30) * 99 // 170)
age_embedding = embedding_layer(torch.tensor([user_data['age']])).view(1, -1)
gender_embedding = embedding_layer(torch.tensor([gender_id])).view(1, -1)
height_embedding = embedding_layer(torch.tensor([scaled_height])).view(1, -1)
weight_embedding = embedding_layer(torch.tensor([scaled_weight])).view(1, -1)
combined_embedding = torch.cat((age_embedding, gender_embedding, height_embedding, weight_embedding), dim=1)
return combined_embedding.detach().numpy()
|