OhST commited on
Commit
331b353
1 Parent(s): b39e2b2

machine learning assignment 3 만듬.

Browse files
Files changed (7) hide show
  1. app.py +111 -0
  2. ex_1.jpg +0 -0
  3. ex_2.jpg +0 -0
  4. ex_3.jpg +0 -0
  5. ex_4.jpg +0 -0
  6. ex_5.jpg +0 -0
  7. labels.txt +19 -0
app.py ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import gradio as gr
2
+
3
+ from matplotlib import gridspec
4
+ import matplotlib.pyplot as plt
5
+ import numpy as np
6
+ from PIL import Image
7
+ import tensorflow as tf
8
+ from transformers import SegformerFeatureExtractor, TFSegformerForSemanticSegmentation
9
+
10
+ feature_extractor = SegformerFeatureExtractor.from_pretrained(
11
+ "nvidia/segformer-b1-finetuned-cityscapes-1024-1024"
12
+ )
13
+ model = TFSegformerForSemanticSegmentation.from_pretrained(
14
+ "nvidia/segformer-b1-finetuned-cityscapes-1024-1024"
15
+ )
16
+
17
+ def ade_palette():
18
+ """ADE20K palette that maps each class to RGB values."""
19
+ return [
20
+ [255, 0, 0],
21
+ [255, 255, 0],
22
+ [29, 219, 22],
23
+ [0, 84, 255],
24
+ [255, 0, 221],
25
+ [189, 189, 189],
26
+ [255, 204, 151],
27
+ [255, 228, 0],
28
+ [135, 38, 0],
29
+ [0, 0, 0],
30
+ [166, 156, 255],
31
+ [1, 0, 255],
32
+ [0, 216, 255],
33
+ [87, 129, 0],
34
+ [153, 0, 133],
35
+ [172, 242, 0],
36
+ [173, 255, 166],
37
+ [45, 78, 123],
38
+ [255, 178, 217]
39
+ ]
40
+
41
+ labels_list = []
42
+
43
+ with open(r'labels.txt', 'r') as fp:
44
+ for line in fp:
45
+ labels_list.append(line[:-1])
46
+
47
+ colormap = np.asarray(ade_palette())
48
+
49
+ def label_to_color_image(label):
50
+ if label.ndim != 2:
51
+ raise ValueError("Expect 2-D input label")
52
+
53
+ if np.max(label) >= len(colormap):
54
+ raise ValueError("label value too large.")
55
+ return colormap[label]
56
+
57
+ def draw_plot(pred_img, seg):
58
+ fig = plt.figure(figsize=(20, 15))
59
+
60
+ grid_spec = gridspec.GridSpec(1, 2, width_ratios=[6, 1])
61
+
62
+ plt.subplot(grid_spec[0])
63
+ plt.imshow(pred_img)
64
+ plt.axis('off')
65
+ LABEL_NAMES = np.asarray(labels_list)
66
+ FULL_LABEL_MAP = np.arange(len(LABEL_NAMES)).reshape(len(LABEL_NAMES), 1)
67
+ FULL_COLOR_MAP = label_to_color_image(FULL_LABEL_MAP)
68
+
69
+ unique_labels = np.unique(seg.numpy().astype("uint8"))
70
+ ax = plt.subplot(grid_spec[1])
71
+ plt.imshow(FULL_COLOR_MAP[unique_labels].astype(np.uint8), interpolation="nearest")
72
+ ax.yaxis.tick_right()
73
+ plt.yticks(range(len(unique_labels)), LABEL_NAMES[unique_labels])
74
+ plt.xticks([], [])
75
+ ax.tick_params(width=0.0, labelsize=25)
76
+ return fig
77
+
78
+ def sepia(input_img):
79
+ input_img = Image.fromarray(input_img)
80
+
81
+ inputs = feature_extractor(images=input_img, return_tensors="tf")
82
+ outputs = model(**inputs)
83
+ logits = outputs.logits
84
+
85
+ logits = tf.transpose(logits, [0, 2, 3, 1])
86
+ logits = tf.image.resize(
87
+ logits, input_img.size[::-1]
88
+ ) # We reverse the shape of `image` because `image.size` returns width and height.
89
+ seg = tf.math.argmax(logits, axis=-1)[0]
90
+
91
+ color_seg = np.zeros(
92
+ (seg.shape[0], seg.shape[1], 3), dtype=np.uint8
93
+ ) # height, width, 3
94
+ for label, color in enumerate(colormap):
95
+ color_seg[seg.numpy() == label, :] = color
96
+
97
+ # Show image + mask
98
+ pred_img = np.array(input_img) * 0.5 + color_seg * 0.5
99
+ pred_img = pred_img.astype(np.uint8)
100
+
101
+ fig = draw_plot(pred_img, seg)
102
+ return fig
103
+
104
+ demo = gr.Interface(fn=sepia,
105
+ inputs=gr.Image(shape=(400, 600)),
106
+ outputs=['plot'],
107
+ examples=["ex_1.jpg","ex_2.jpg", "ex_3.jpg", "ex_4.jpg", "ex_5.jpg"],
108
+ allow_flagging='never')
109
+
110
+
111
+ demo.launch()
ex_1.jpg ADDED
ex_2.jpg ADDED
ex_3.jpg ADDED
ex_4.jpg ADDED
ex_5.jpg ADDED
labels.txt ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ road
2
+ sidewalk
3
+ building
4
+ wall
5
+ fence
6
+ pole
7
+ traffic light
8
+ traffic sign
9
+ vegetation
10
+ terrain
11
+ sky
12
+ person
13
+ rider
14
+ car
15
+ truck
16
+ bus
17
+ train
18
+ motorcycle
19
+ bicycle