File size: 1,410 Bytes
c3e75ac
 
 
 
 
63debe3
c3e75ac
 
63debe3
 
c3e75ac
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9a4023b
3299692
9a4023b
 
 
 
3299692
54f8640
 
6ab4125
3f76519
c3e75ac
 
8b6aa34
c3e75ac
8b14234
c3e75ac
 
2f156d5
c3e75ac
 
 
 
 
 
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
import torch
from torch import nn
import torchvision.transforms as transforms
import torch.nn.functional as F
from pathlib import Path
import gradio as gr
from PIL import Image
import numpy as np


LABELS = Path('classes.txt').read_text().splitlines()
num_classes = len(LABELS)

model = nn.Sequential(
    nn.Conv2d(1, 64, 3, padding='same'),
    nn.ReLU(),
    nn.MaxPool2d(2),
    nn.Conv2d(64, 128, 3, padding='same'),
    nn.ReLU(),
    nn.MaxPool2d(2),
    nn.Conv2d(128, 256, 3, padding='same'),
    nn.ReLU(),
    nn.MaxPool2d(2),
    nn.Flatten(),
    nn.Linear(2304, 512),
    nn.ReLU(),
    nn.Linear(512, num_classes),
)

state_dict = torch.load('model.pth', map_location='cpu')
model.load_state_dict(state_dict, strict=False)
model.eval()

transform = transforms.Compose([
    transforms.Resize((28, 28)),
    transforms.ToTensor(),
    transforms.Normalize((0.5,), (0.5,))
])


def predict(image):
    image = image['composite']
    image = Image.fromarray(image).convert('L')
    input = transform(image).unsqueeze(0)

    with torch.no_grad():
        out = model(input)

    print(out.shape)
    probabilities = F.softmax(out[0], dim=0)
    values, indices = torch.topk(probabilities, 5)
    print(values, indices)

    return {LABELS[i]: v.item() for i, v in zip(indices, values)}


interface = gr.Interface(predict, inputs='sketchpad', outputs='label', live=True)
interface.launch(debug=True)