Upload 8 files

app.py

@@ -0,0 +1,244 @@
+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-ade-640-640"
+    "nvidia/segformer-b0-finetuned-ade-512-512"
+)
+model = TFSegformerForSemanticSegmentation.from_pretrained(
+    # "nvidia/segformer-b5-finetuned-ade-640-640"
+    "nvidia/segformer-b0-finetuned-ade-512-512"
+)
+
+def ade_palette():
+    """ADE20K palette that maps each class to RGB values."""
+    return [
+        [78, 145, 57],
+        [200, 78, 112],
+        [99, 89, 145],
+        [200, 156, 78],
+        [57, 78, 145],
+        [78, 57, 99],
+        [145, 112, 78],
+        [78, 89, 145],
+        [210, 99, 28],
+        [145, 78, 189],
+        [57, 200, 136],
+        [89, 156, 78],
+        [99, 28, 210],
+        [189, 78, 47],
+        [28, 210, 99],
+        [200, 78, 112],
+        [210, 99, 28],
+        [78, 145, 57],
+        [145, 78, 99],
+        [78, 57, 99],
+        [78, 145, 57],
+        [99, 28, 210],
+        [99, 89, 145],
+        [145, 78, 99],
+        [145, 112, 78],
+        [78, 89, 145],
+        [57, 78, 145],
+        [57, 200, 136],
+        [57, 78, 145],
+        [99, 28, 210],
+        [89, 156, 78],
+        [57, 78, 145],
+        [78, 89, 145],
+        [145, 112, 78],
+        [200, 156, 78],
+        [57, 200, 136],
+        [28, 210, 99],
+        [78, 57, 99],
+        [78, 145, 57],
+        [57, 200, 136],
+        [57, 78, 145],
+        [210, 99, 28],
+        [145, 78, 189],
+        [200, 78, 112],
+        [78, 89, 145],
+        [99, 28, 210],
+        [189, 78, 47],
+        [99, 89, 145],
+        [78, 145, 57],
+        [200, 156, 78],
+        [57, 78, 145],
+        [210, 99, 28],
+        [145, 78, 189],
+        [78, 89, 145],
+        [200, 78, 112],
+        [57, 78, 145],
+        [145, 112, 78],
+        [99, 28, 210],
+        [57, 200, 136],
+        [78, 57, 99],
+        [28, 210, 99],
+        [189, 78, 47],
+        [145, 78, 189],
+        [78, 57, 99],
+        [99, 28, 210],
+        [57, 200, 136],
+        [145, 112, 78],
+        [78, 89, 145],
+        [200, 78, 112],
+        [78, 57, 99],
+        [99, 28, 210],
+        [145, 78, 99],
+        [28, 210, 99],
+        [145, 112, 78],
+        [78, 89, 145],
+        [57, 200, 136],
+        [57, 78, 145],
+        [189, 78, 47],
+        [200, 156, 78],
+        [99, 28, 210],
+        [78, 89, 145],
+        [145, 78, 189],
+        [57, 78, 145],
+        [200, 78, 112],
+        [78, 57, 99],
+        [99, 89, 145],
+        [210, 99, 28],
+        [145, 78, 189],
+        [28, 210, 99],
+        [145, 112, 78],
+        [57, 200, 136],
+        [78, 57, 99],
+        [78, 145, 57],
+        [99, 28, 210],
+        [200, 156, 78],
+        [57, 78, 145],
+        [145, 78, 99],
+        [78, 89, 145],
+        [57, 200, 136],
+        [28, 210, 99],
+        [99, 89, 145],
+        [78, 145, 57],
+        [145, 78, 99],
+        [200, 78, 112],
+        [78, 57, 99],
+        [210, 99, 28],
+        [57, 78, 145],
+        [200, 156, 78],
+        [99, 28, 210],
+        [189, 78, 47],
+        [78, 89, 145],
+        [57, 200, 136],
+        [145, 112, 78],
+        [145, 78, 189],
+        [28, 210, 99],
+        [99, 89, 145],
+        [78, 57, 99],
+        [57, 200, 136],
+        [210, 99, 28],
+        [145, 112, 78],
+        [78, 145, 57],
+        [78, 89, 145],
+        [57, 78, 145],
+        [200, 78, 112],
+        [189, 78, 47],
+        [200, 156, 78],
+        [57, 200, 136],
+        [99, 89, 145],
+        [99, 28, 210],
+        [145, 112, 78],
+        [145, 78, 99],
+        [57, 78, 145],
+        [28, 210, 99],
+        [78, 57, 99],
+        [78, 145, 57],
+        [57, 200, 136],
+        [78, 89, 145],
+        [99, 28, 210],
+        [200, 156, 78],
+        [145, 78, 189],
+        [78, 57, 99],
+        [57, 78, 145],
+        [210, 99, 28],
+        [99, 89, 145],
+        [28, 210, 99],
+        [145, 112, 78],
+        [200, 78, 112],
+        [78, 57, 99],
+        [57, 78, 145],
+        [99, 28, 210],
+    ]
+
+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=["sample-1.jpg", "sample-2.jpg", "sample-3.png", ],
+                    allow_flagging='never')
+
+
+demo.launch()

labels.txt

@@ -0,0 +1,150 @@
+wall
+building
+sky
+floor
+tree
+ceiling
+road
+bed
+windowpane
+grass
+cabinet
+sidewalk
+person
+earth
+door
+table
+mountain
+plant
+curtain
+chair
+car
+water
+painting
+sofa
+shelf
+house
+sea
+mirror
+rug
+field
+armchair
+seat
+fence
+desk
+rock
+wardrobe
+lamp
+bathtub
+railing
+cushion
+base
+box
+column
+signboard
+chest of drawers
+counter
+sand
+sink
+skyscraper
+fireplace
+refrigerator
+grandstand
+path
+stairs
+runway
+case
+pool table
+pillow
+screen door
+stairway
+river
+bridge
+bookcase
+blind
+coffee table
+toilet
+flower
+book
+hill
+bench
+countertop
+stove
+palm
+kitchen island
+computer
+swivel chair
+boat
+bar
+arcade machine
+hovel
+bus
+towel
+light
+truck
+tower
+chandelier
+awning
+streetlight
+booth
+television receiver
+airplane
+dirt track
+apparel
+pole
+land
+bannister
+escalator
+ottoman
+bottle
+buffet
+poster
+stage
+van
+ship
+fountain
+conveyer belt
+canopy
+washer
+plaything
+swimming pool
+stool
+barrel
+basket
+waterfall
+tent
+bag
+minibike
+cradle
+oven
+ball
+food
+step
+tank
+trade name
+microwave
+pot
+animal
+bicycle
+lake
+dishwasher
+screen
+blanket
+sculpture
+hood
+sconce
+vase
+traffic light
+tray
+ashcan
+fan
+pier
+crt screen
+plate
+monitor
+bulletin board
+shower
+radiator
+glass
+clock
+flag

requirements.txt

@@ -0,0 +1,6 @@
+torch
+transformers
+tensorflow
+numpy
+Image
+matplotlib