File size: 3,042 Bytes
3a298ab 1f52e1d 3a298ab 1f52e1d ca2787d 3a298ab 1f52e1d 3a298ab |
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 |
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-b1-finetuned-cityscapes-1024-1024"
)
model = TFSegformerForSemanticSegmentation.from_pretrained(
"nvidia/segformer-b1-finetuned-cityscapes-1024-1024"
)
def ade_palette():
"""ADE20K palette that maps each class to RGB values."""
return [
[204, 166, 62],
[188, 229, 92],
[47, 157,39],
[178, 235, 244],
[0, 51, 153],
[181, 178, 255],
[128, 65, 217],
[255, 178, 245],
[153, 0, 76],
[25, 186, 52],
[81, 162, 235],
[255, 255, 0],
[62, 57, 159],
[91, 189, 203],
[0, 0, 255],
[0, 255, 255],
[12, 168, 0],
[255, 0, 0],
[231, 32, 65]
]
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]
# Assuming each label corresponds to a class
class_labels = seg.numpy().flatten().tolist()
return class_labels
demo = gr.Interface(fn=sepia,
inputs=gr.Image(shape=(400, 600)),
outputs=gr.outputs.Label(), # Use Label output type for class labels
examples=["cityoutdoor-1.jpg", "cityoutdoor-2.jpg", "cityoutdoor-3.jpg"],
allow_flagging='never')
demo.launch() |