-
Notifications
You must be signed in to change notification settings - Fork 0
/
model.py
39 lines (25 loc) · 1.06 KB
/
model.py
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
import torch
import torch.nn as nn
from torchvision import models
from transformers import AutoTokenizer, AutoModel
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.image_encoder = models.resnet18()
self.image_encoder.fc = nn.Identity()
self.image_out = nn.Sequential(
nn.Linear(512, 256), nn.ReLU(), nn.Linear(256, 256)
)
self.text_encoder = AutoModel.from_pretrained("dbmdz/distilbert-base-turkish-cased")
self.target_token_idx = 0
self.text_out = nn.Sequential(
nn.Linear(768, 256), nn.ReLU(), nn.Linear(256, 256)
)
def forward(self, image, text, mask):
image_vec = self.image_encoder(image)
image_vec = self.image_out(image_vec.view(-1,512))
text_out = self.text_encoder(text, mask)
last_hidden_states = text_out.last_hidden_state
last_hidden_states = last_hidden_states[:,self.target_token_idx,:]
text_vec = self.text_out(last_hidden_states.view(-1,768))
return image_vec, text_vec