File size: 5,296 Bytes
3f7fda1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
import gradio as gr

from matplotlib import gridspec
import matplotlib.pyplot as plt
import numpy as np
from PIL import Image
import tensorflow as tf
from transformers import SegformerFeatureExtractor, TFSegformerForSemanticSegmentation

feature_extractor = SegformerFeatureExtractor.from_pretrained(
    "prem-timsina/segformer-b0-finetuned-food"
)
model = TFSegformerForSemanticSegmentation.from_pretrained(
    "prem-timsina/segformer-b0-finetuned-food"
)

def ade_palette():
    """ADE20K palette that maps each class to RGB values."""
    return [
        [93, 93, 93],
        [43, 240, 132],
        [139, 136, 240],
        [158, 83, 109],
        [6, 76, 151],
        [95, 170, 87],
        [273, 236, 139],
        [21, 155, 160],
        [188, 220, 166],
        [238, 96, 247],
        [223, 180, 221],
        [29, 97, 24],
        [3, 233, 248],
        [105, 118, 44],
        [203, 237, 63],
        [234, 100, 240],
        [19, 179, 164],
        [65, 22, 115],
        [111, 128, 194],
        [232, 41, 17],
        [11, 250, 159],
        [137, 163, 129],
        [212, 223, 210],
        [51, 37, 4],
        [37, 63, 239],
        [257, 180, 163],
        [172, 53, 105],
        [104, 150, 99],
        [80, 157, 133],
        [195, 104, 202],
        [42, 187, 110],
        [133, 225, 66],
        [132, 99, 213],
        [178, 248, 209],
        [93, 147, 60],
        [105, 109, 115],
        [26, 65, 115],
        [239, 52, 182],
        [242, 19, 204],
        [157, 101, 214],
        [248, 85, 198],
        [103, 198, 171],
        [44, 129, 75],
        [159, 32, 120],
        [155, 77, 71],
        [233, 231, 155],
        [135, 196, 206],
        [81, 53, 51],
        [134, 221, 213],
        [192, 27, 152],
        [127, 127, 194],
        [82, 161, 1],
        [71, 80, 161],
        [148, 9, 159],
        [91, 110, 124],
        [127, 157, 223],
        [25, 210, 232],
        [129, 0, 114],
        [231, 187, 138],
        [23, 17, 224],
        [25, 255, 29],
        [158, 19, 53],
        [157, 190, 176],
        [114, 140, 221],
        [46, 104, 87],
        [17, 114, 122],
        [221, 12, 229],
        [54, 20, 92],
        [215, 191, 252],
        [144, 127, 146],
        [141, 116, 77],
        [100, 89, 89],
        [104, 115, 249],
        [179, 212, 38],
        [140, 248, 179],
        [177, 230, 240],
        [219, 98, 8],
        [74, 219, 53],
        [161, 28, 243],
        [64, 57, 184],
        [147, 193, 113],
        [182, 15, 30],
        [151, 204, 109],
        [187, 76, 21],
        [118, 163, 155],
        [158, 30, 220],
        [227, 170, 63],
        [199, 186, 72],
        [0, 241, 168],
        [80, 150, 225],
        [237, 250, 4],
        [29, 210, 181],
        [176, 120, 81],
        [134, 47, 123],
        [240, 141, 130],
        [250, 41, 115],
        [29, 88, 143],
        [66, 151, 87],
        [241, 231, 144],
        [238, 107, 153],
        [181, 96, 220],
        [239, 122, 133],
        [205, 120, 21],
        [168, 12, 77],

    ]

labels_list = []

with open(r'labels.txt', 'r') as fp:
    for line in fp:
        labels_list.append(line[:-1])

colormap = np.asarray(ade_palette())

def label_to_color_image(label):
    if label.ndim != 2:
        raise ValueError("Expect 2-D input label")

    if np.max(label) >= len(colormap):
        raise ValueError("label value too large.")
    return colormap[label]

def draw_plot(pred_img, seg):
    fig = plt.figure(figsize=(20, 15))

    grid_spec = gridspec.GridSpec(1, 2, width_ratios=[6, 1])

    plt.subplot(grid_spec[0])
    plt.imshow(pred_img)
    plt.axis('off')
    LABEL_NAMES = np.asarray(labels_list)
    FULL_LABEL_MAP = np.arange(len(LABEL_NAMES)).reshape(len(LABEL_NAMES), 1)
    FULL_COLOR_MAP = label_to_color_image(FULL_LABEL_MAP)

    unique_labels = np.unique(seg.numpy().astype("uint8"))
    ax = plt.subplot(grid_spec[1])
    plt.imshow(FULL_COLOR_MAP[unique_labels].astype(np.uint8), interpolation="nearest")
    ax.yaxis.tick_right()
    plt.yticks(range(len(unique_labels)), LABEL_NAMES[unique_labels])
    plt.xticks([], [])
    ax.tick_params(width=0.0, labelsize=25)
    return fig

def sepia(input_img):
    input_img = Image.fromarray(input_img)

    inputs = feature_extractor(images=input_img, return_tensors="tf")
    outputs = model(**inputs)
    logits = outputs.logits

    logits = tf.transpose(logits, [0, 2, 3, 1])
    logits = tf.image.resize(
        logits, input_img.size[::-1]
    )  # We reverse the shape of `image` because `image.size` returns width and height.
    seg = tf.math.argmax(logits, axis=-1)[0]

    color_seg = np.zeros(
        (seg.shape[0], seg.shape[1], 3), dtype=np.uint8
    )  # height, width, 3
    for label, color in enumerate(colormap):
        color_seg[seg.numpy() == label, :] = color

    # Show image + mask
    pred_img = np.array(input_img) * 0.5 + color_seg * 0.5
    pred_img = pred_img.astype(np.uint8)

    fig = draw_plot(pred_img, seg)
    return fig

demo = gr.Interface(fn=sepia,
                    inputs=gr.Image(shape=(400, 600)),
                    outputs=['plot'],
                    examples=["food-1.jpg","food-2.jpg", "food-3.jpg", "food-4.jpg", "food-5.jpg", "food-6.jpg"],
                    allow_flagging='never')


demo.launch()