File size: 3,450 Bytes
0de2ebf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29f78a0
 
78e1acc
 
0de2ebf
 
 
 
 
 
 
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
import gradio as gr
from matplotlib import gridspec
import matplotlib.pyplot as plt
import numpy as np
from PIL import Image
import torch
from transformers import AutoImageProcessor, AutoModelForSemanticSegmentation

MODEL_ID = "nvidia/segformer-b0-finetuned-cityscapes-768-768"
processor = AutoImageProcessor.from_pretrained(MODEL_ID)
model = AutoModelForSemanticSegmentation.from_pretrained(MODEL_ID)

def ade_palette():
    return [
        [255,228,0],   #road
        [255,94,0],     #sidewalk
        [1,1,1],        #building
        [255,0,0],      #wall
        [255,255,255],  #fence
        [0,0,255],      #pole
        [196,183,59],      #traffic light
        [103,0,0],      #traffic sign
        [0,255,0],      #vegetation
        [0,216,255],    #terrain
        [255,0,127],    #sky
        [165,102,255],  #person
        [255,0,221],    #rider
        [241,95,95],    #car
        [107,102,255],  #truck
        [102,92,0],     #bus
        [171,242,0],    #train
        [67,116,127],   #motorcycle
        [71,200,62],    #bicycle
    ]

labels_list = []
with open("labels.txt", "r", encoding="utf-8") as fp:
    for line in fp:
        labels_list.append(line.rstrip("\n"))

colormap = np.asarray(ade_palette(), dtype=np.uint8)

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_np):
    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_np.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 run_inference(input_img):
    # input: numpy array from gradio -> PIL
    img = Image.fromarray(input_img.astype(np.uint8)) if isinstance(input_img, np.ndarray) else input_img
    if img.mode != "RGB":
        img = img.convert("RGB")

    inputs = processor(images=img, return_tensors="pt")
    with torch.no_grad():
        outputs = model(**inputs)
        logits = outputs.logits  # (1, C, h/4, w/4)

    # resize to original
    upsampled = torch.nn.functional.interpolate(
        logits, size=img.size[::-1], mode="bilinear", align_corners=False
    )
    seg = upsampled.argmax(dim=1)[0].cpu().numpy().astype(np.uint8)  # (H,W)

    # colorize & overlay
    color_seg = colormap[seg]                                # (H,W,3)
    pred_img = (np.array(img) * 0.5 + color_seg * 0.5).astype(np.uint8)

    fig = draw_plot(pred_img, seg)
    return fig

demo = gr.Interface(
    fn=run_inference,
    inputs=gr.Image(type="numpy", label="Input Image"),
    outputs=gr.Plot(label="Overlay + Legend"),
    examples=[
        "street-1.jpg",
        "street-2.jpg",
        "street-3.jpg",
        "street-4.jpg",
    ],
    flagging_mode="never",
    cache_examples=False,
)

if __name__ == "__main__":
    demo.launch()