File size: 4,297 Bytes
93f1f28
 
931b10a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2c8378d
 
 
 
 
877d93d
 
 
 
 
b63e59c
0c96891
f65e7b6
2c8378d
 
f65e7b6
 
 
 
2c8378d
931b10a
 
877d93d
931b10a
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
#-*- encoding: utf-8 -*-

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(
    "nvidia/segformer-b4-finetuned-cityscapes-1024-1024"
)
model = TFSegformerForSemanticSegmentation.from_pretrained(
    "nvidia/segformer-b4-finetuned-cityscapes-1024-1024"
)

def ade_palette():
    """ADE20K palette that maps each class to RGB values."""
    return [
        [0, 0, 0],          # black
        [140, 140, 140],    # gray
        [95, 0, 255],       # purple
        [221, 126, 255],    # light purple
        [1, 0, 255],        # blue
        [0, 216, 255],      # light blue
        [35, 164, 26],      # green
        [29, 219, 22],      # light green
        [255, 228, 0],      # yellow
        [255, 187, 0],      # light orange
        [255, 94, 0],       # orange
        [255, 0, 0],        # red
        [255, 167, 167],    # pink
        [153, 56, 0],       # brown
        [207, 166, 54],
        [180, 40, 180],
        [120, 56, 123],
        [45, 56, 28],
        [67, 56, 123],
    ]

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


with gr.Blocks(theme=gr.themes.Monochrome()) as demo:
    with gr.Tab("Semantic Segmentation with Cityscape Image"):
        with gr.Row():
            with gr.Column(scale=1):
                cities = [
                    "city_1.jpg", "city_2.jpg", "city_3.jpg",
                    "city_4.jpg", "city_5.jpg", "city_6.jpg",
                    "city_7.jpg", "city_8.jpg",
                ]
                input_gallery = gr.Gallery(label="Select Image", value=cities, columns=4)
                input_image = gr.Image(label="Uploaded Image", interactive=True, type="numpy")
                input_gallery.change(fn=lambda x: x, inputs=input_gallery, outputs=input_image)
                process_button = gr.Button("Process Image")
            with gr.Column(scale=2):
                output_image = gr.Plot(label="Segmented Image")
                process_button.click(sepia, inputs=input_image, outputs=output_image)

    with gr.Accordion("Information"):
        gr.Markdown("A Gradio-based page which performs Semantic Segmentation into 19 classes for an example image")



demo.launch()