Spaces:
Sleeping
Sleeping
File size: 5,107 Bytes
bb988cc |
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 |
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-b3-finetuned-cityscapes-1024-1024"
)
model = TFSegformerForSemanticSegmentation.from_pretrained(
"nvidia/segformer-b3-finetuned-cityscapes-1024-1024"
)
def ade_palette():
"""ADE20K palette that maps each class to RGB values."""
return [
[255, 0, 0],
[255, 94, 0],
[255, 187, 0],
[255, 228, 0],
[171, 242, 0],
[29, 219, 22],
[0, 216, 255],
[0, 84, 255],
[1, 0, 255],
[95, 0, 255],
[255, 0, 221],
[255, 0, 127],
[0, 0, 0],
[255, 255, 255],
[255, 216, 216],
[250, 224, 212],
[250, 236, 197],
[250, 244, 192],
[228, 247, 186],
[206, 251, 201],
[212, 244, 250],
[217, 229, 255],
[218, 217, 255],
[232, 217, 255],
[255, 217, 250],
[255, 217, 236],
[246, 246, 246],
[234, 234, 234],
[255, 167, 167],
[255, 193, 158],
[255, 224, 140],
[250, 237, 125],
[206, 242, 121],
[183, 240, 177],
[178, 235, 244],
[178, 204, 255],
[181, 178, 255],
[209, 178, 255],
[255, 178, 245],
[255, 178, 217],
[213, 213, 213],
[189, 189, 189],
[241, 95, 95],
[242, 150, 97],
[242, 203, 97],
[229, 216, 92],
[188, 229, 92],
[134, 229, 127],
[92, 209, 229],
[103, 153, 255],
[107, 102, 255],
[165, 102, 255],
[243, 97, 220],
[243, 97, 166],
[166, 166, 166],
[140, 140, 140],
[93, 93, 93],
[116, 116, 116],
[217, 65, 140],
[217, 65, 197],
[128, 65, 217],
[70, 65, 217],
[67, 116, 217],
[61, 183, 204],
[71, 200, 62],
[159, 201, 60],
[196, 183, 59],
[204, 166, 61],
[204, 114, 61],
[204, 61, 61],
[152, 0, 0],
[153, 56, 0],
[153, 112, 0],
[153, 138, 0],
[107, 153, 0],
[47, 157, 39],
[0, 130, 153],
[0, 51, 153],
[5, 0, 153],
[63, 0, 153],
[153, 0, 133],
[153, 0, 76],
[76, 76, 76],
[53, 53, 53],
[25, 25, 25],
[33, 33, 33],
[102, 0, 51],
[102, 0, 88],
[42, 0, 102],
[3, 0, 102],
[0, 34, 102],
[0, 87, 102],
[34, 116, 28],
[71, 102, 0],
[102, 92, 0],
[102, 75, 0],
[102, 37, 0],
[103, 0, 0]
]
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
demo = gr.Interface(fn=sepia,
inputs=gr.Image(shape=(400, 600)),
outputs=['plot'],
examples=["cityscape-1.jpg", "cityscape-2.jpg", "cityscape-3.jpg"],
allow_flagging='never')
demo.launch()
|