File size: 1,433 Bytes
16e5bdb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8e72497
16e5bdb
 
 
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
import json
import time
from PIL import Image
import torch
from torchvision.transforms import transforms
import gradio as gr


model = torch.load('model.pth', map_location=torch.device('cpu'))
model.eval()
transform = transforms.Compose([
    transforms.Resize((448, 448)),
    transforms.ToTensor(),
    transforms.Normalize(mean=[
        0.48145466,
        0.4578275,
        0.40821073
    ], std=[
        0.26862954,
        0.26130258,
        0.27577711
    ])
])


with open("tags_8041.json", "r") as file:
    tags = json.load(file)
allowed_tags = sorted(tags)
allowed_tags.insert(0, "placeholder0")
allowed_tags.append("placeholder1")
allowed_tags.append("explicit")
allowed_tags.append("questionable")
allowed_tags.append("safe")

def create_tags(image):
  img = image.convert('RGB')
  tensor = transform(img).unsqueeze(0)

  with torch.no_grad():
      out = model(tensor)
      probabilities = torch.nn.functional.sigmoid(out[0])
      indices = torch.where(probabilities > 0.3)[0]
      values = probabilities[indices]

  temp = []
  for i in range(indices.size(0)):
      temp.append([allowed_tags[indices[i]], values[i].item()])
  temp = sorted(temp, key=lambda x: x[1], reverse=True)
  text = ""
  for i in range(len(temp)):
    text += temp[i][0] + (' ,' if i < len(temp) - 1 else '')
  return text

demo = gr.Interface(
    fn=create_tags,
    inputs=[gr.Image(type="pil")],
    outputs=["text"],
)
demo.launch()