File size: 3,642 Bytes
352a01b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fd85cb7
 
cc7bbe2
 
 
fd85cb7
352a01b
 
 
 
 
 
 
 
 
 
 
 
 
6c74fa8
 
 
 
 
 
fd85cb7
df4a260
 
 
 
b60307f
df4a260
 
 
3c5e90d
fd85cb7
352a01b
 
df4a260
0f56854
352a01b
 
 
df4a260
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
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-b5-finetuned-cityscapes-1024-1024"
)
model = TFSegformerForSemanticSegmentation.from_pretrained(
    "nvidia/segformer-b5-finetuned-cityscapes-1024-1024"
)

def ade_palette():
    """ADE20K palette that maps each class to RGB values."""
    return [
        [204, 87, 92],
        [112, 185, 212],
        [45, 189, 106],
        [234, 123, 67],
        [78, 56, 123],
        [210, 32, 89],
        [90, 180, 56],
        [155, 102, 200],
        [33, 147, 176],
        [255, 183, 76],
        [67, 123, 89],
        [190, 60, 45],
        [134, 112, 200],
        [56, 45, 189],
        [200, 56, 123],
        [87, 92, 204],
        [120, 56, 123],
        [45, 78, 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 segmentation_to_text(seg):
    seg = seg.numpy()
    unique_labels, counts = np.unique(seg, return_counts=True)
    labels_text = [f"{labels_list[label]}: {count}" for label, count in zip(unique_labels, counts)]
    return "\n".join(labels_text)

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

    seg_text = segmentation_to_text(seg)
    
    # 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)
    plt.text(0, -20, seg_text, fontsize=12, color='black', ha='left', va='top', backgroundcolor='gray', wrap=True)
    return fig


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


demo.launch()