Hugging Face's logo

Spaces:
OmAlve
/
Swin-Transformer-Foods101
Sleeping

App Files Community
1
Swin-Transformer-Foods101
File size: 2,778 Bytes 
d012df7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
 
import timm
from PIL import Image
from torchvision import transforms as T
import gradio as gr
import torch

model = timm.create_model("hf_hub:OmAlve/swin_s3_base_224-Foods-101", pretrained=True)
image_size = (224,224)

test_tf = T.Compose([
    T.Resize(image_size),
    T.ToTensor(),
    T.Normalize(
        mean = (0.5,0.5,0.5),
        std = (0.5,0.5,0.5)
    )
])

labels = [
    "apple_pie",
    "baby_back_ribs",
    "baklava",
    "beef_carpaccio",
    "beef_tartare",
    "beet_salad",
    "beignets",
    "bibimbap",
    "bread_pudding",
    "breakfast_burrito",
    "bruschetta",
    "caesar_salad",
    "cannoli",
    "caprese_salad",
    "carrot_cake",
    "ceviche",
    "cheesecake",
    "cheese_plate",
    "chicken_curry",
    "chicken_quesadilla",
    "chicken_wings",
    "chocolate_cake",
    "chocolate_mousse",
    "churros",
    "clam_chowder",
    "club_sandwich",
    "crab_cakes",
    "creme_brulee",
    "croque_madame",
    "cup_cakes",
    "deviled_eggs",
    "donuts",
    "dumplings",
    "edamame",
    "eggs_benedict",
    "escargots",
    "falafel",
    "filet_mignon",
    "fish_and_chips",
    "foie_gras",
    "french_fries",
    "french_onion_soup",
    "french_toast",
    "fried_calamari",
    "fried_rice",
    "frozen_yogurt",
    "garlic_bread",
    "gnocchi",
    "greek_salad",
    "grilled_cheese_sandwich",
    "grilled_salmon",
    "guacamole",
    "gyoza",
    "hamburger",
    "hot_and_sour_soup",
    "hot_dog",
    "huevos_rancheros",
    "hummus",
    "ice_cream",
    "lasagna",
    "lobster_bisque",
    "lobster_roll_sandwich",
    "macaroni_and_cheese",
    "macarons",
    "miso_soup",
    "mussels",
    "nachos",
    "omelette",
    "onion_rings",
    "oysters",
    "pad_thai",
    "paella",
    "pancakes",
    "panna_cotta",
    "peking_duck",
    "pho",
    "pizza",
    "pork_chop",
    "poutine",
    "prime_rib",
    "pulled_pork_sandwich",
    "ramen",
    "ravioli",
    "red_velvet_cake",
    "risotto",
    "samosa",
    "sashimi",
    "scallops",
    "seaweed_salad",
    "shrimp_and_grits",
    "spaghetti_bolognese",
    "spaghetti_carbonara",
    "spring_rolls",
    "steak",
    "strawberry_shortcake",
    "sushi",
    "tacos",
    "takoyaki",
    "tiramisu",
    "tuna_tartare",
    "waffles"
  ]

def predict(img):
  inp = test_tf(img).unsqueeze(0)
  with torch.no_grad():
    predictions = torch.nn.functional.softmax(model(inp)[0], dim=0)
    toplabels = predictions.argsort(descending=True)[:5]
  results = {labels[label] : float(predictions[label]) for label in toplabels}
  return results

gr.Interface(fn=predict,
             inputs=gr.Image(type="pil"),
             outputs="label",
             examples=['./miso soup.jpg','./cupcake.jpg','./pasta.jpg'],
             live=True).launch()