File size: 6,708 Bytes
872f59a
 
538bf82
 
 
872f59a
 
 
 
 
 
 
 
 
78f1305
872f59a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
538bf82
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
872f59a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
538bf82
 
 
 
872f59a
 
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
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
import gradio as gr

import pandas as pd
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(
    "nvidia/segformer-b5-finetuned-ade-640-640"
)
model = TFSegformerForSemanticSegmentation.from_pretrained(
    "nvidia/segformer-b5-finetuned-ade-640-640"
)

def ade_palette():
    """ADE20K palette that maps each class to RGB values."""
    return [
        [120, 120, 120],
        [180, 120, 120],
        [6, 230, 230],
        [80, 50, 50],
        [4, 200, 3],
        [120, 120, 80],
        [140, 140, 140],
        [204, 5, 255],
        [230, 230, 230],
        [4, 250, 7],
        [224, 5, 255],
        [235, 255, 7],
        [150, 5, 61],
        [120, 120, 70],
        [8, 255, 51],
        [255, 6, 82],
        [143, 255, 140],
        [204, 255, 4],
        [255, 51, 7],
        [204, 70, 3],
        [0, 102, 200],
        [61, 230, 250],
        [255, 6, 51],
        [11, 102, 255],
        [255, 7, 71],
        [255, 9, 224],
        [9, 7, 230],
        [220, 220, 220],
        [255, 9, 92],
        [112, 9, 255],
        [8, 255, 214],
        [7, 255, 224],
        [255, 184, 6],
        [10, 255, 71],
        [255, 41, 10],
        [7, 255, 255],
        [224, 255, 8],
        [102, 8, 255],
        [255, 61, 6],
        [255, 194, 7],
        [255, 122, 8],
        [0, 255, 20],
        [255, 8, 41],
        [255, 5, 153],
        [6, 51, 255],
        [235, 12, 255],
        [160, 150, 20],
        [0, 163, 255],
        [140, 140, 140],
        [250, 10, 15],
        [20, 255, 0],
        [31, 255, 0],
        [255, 31, 0],
        [255, 224, 0],
        [153, 255, 0],
        [0, 0, 255],
        [255, 71, 0],
        [0, 235, 255],
        [0, 173, 255],
        [31, 0, 255],
        [11, 200, 200],
        [255, 82, 0],
        [0, 255, 245],
        [0, 61, 255],
        [0, 255, 112],
        [0, 255, 133],
        [255, 0, 0],
        [255, 163, 0],
        [255, 102, 0],
        [194, 255, 0],
        [0, 143, 255],
        [51, 255, 0],
        [0, 82, 255],
        [0, 255, 41],
        [0, 255, 173],
        [10, 0, 255],
        [173, 255, 0],
        [0, 255, 153],
        [255, 92, 0],
        [255, 0, 255],
        [255, 0, 245],
        [255, 0, 102],
        [255, 173, 0],
        [255, 0, 20],
        [255, 184, 184],
        [0, 31, 255],
        [0, 255, 61],
        [0, 71, 255],
        [255, 0, 204],
        [0, 255, 194],
        [0, 255, 82],
        [0, 10, 255],
        [0, 112, 255],
        [51, 0, 255],
        [0, 194, 255],
        [0, 122, 255],
        [0, 255, 163],
        [255, 153, 0],
        [0, 255, 10],
        [255, 112, 0],
        [143, 255, 0],
        [82, 0, 255],
        [163, 255, 0],
        [255, 235, 0],
        [8, 184, 170],
        [133, 0, 255],
        [0, 255, 92],
        [184, 0, 255],
        [255, 0, 31],
        [0, 184, 255],
        [0, 214, 255],
        [255, 0, 112],
        [92, 255, 0],
        [0, 224, 255],
        [112, 224, 255],
        [70, 184, 160],
        [163, 0, 255],
        [153, 0, 255],
        [71, 255, 0],
        [255, 0, 163],
        [255, 204, 0],
        [255, 0, 143],
        [0, 255, 235],
        [133, 255, 0],
        [255, 0, 235],
        [245, 0, 255],
        [255, 0, 122],
        [255, 245, 0],
        [10, 190, 212],
        [214, 255, 0],
        [0, 204, 255],
        [20, 0, 255],
        [255, 255, 0],
        [0, 153, 255],
        [0, 41, 255],
        [0, 255, 204],
        [41, 0, 255],
        [41, 255, 0],
        [173, 0, 255],
        [0, 245, 255],
        [71, 0, 255],
        [122, 0, 255],
        [0, 255, 184],
        [0, 92, 255],
        [184, 255, 0],
        [0, 133, 255],
        [255, 214, 0],
        [25, 194, 194],
        [102, 255, 0],
        [92, 0, 255],
    ]

def label_to_color_image(label):
    """Adds color defined by the dataset colormap to the label.

  Args:
    label: A 2D array with integer type, storing the segmentation label.

  Returns:
    result: A 2D array with floating type. The element of the array
      is the color indexed by the corresponding element in the input label
      to the PASCAL color map.

  Raises:
    ValueError: If label is not of rank 2 or its value is larger than color
      map maximum entry.
  """
    if label.ndim != 2:
        raise ValueError("Expect 2-D input label")

    colormap = np.asarray(ade_palette())

    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')

    ade20k_labels_info = pd.read_csv(
        "https://raw.githubusercontent.com/CSAILVision/sceneparsing/master/objectInfo150.csv"
    )
    labels_list = list(ade20k_labels_info["Name"])    

    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
    palette = np.array(ade_palette())

    for label, color in enumerate(palette):
        color_seg[seg == label, :] = color

    # Convert to BGR
    color_seg = color_seg[..., ::-1]

    # 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(sepia, gr.Image(shape=(200, 200)), outputs=['plot'], examples=["ADE_val_00000001.jpeg"])

demo.launch()