initial commit

README.md

@@ -4,7 +4,7 @@ emoji: 🏆
 colorFrom: green
 colorTo: gray
 sdk: gradio
-sdk_version: 4.2.0
+sdk_version: 3.44.4
 app_file: app.py
 pinned: false
 ---

app.py

@@ -0,0 +1,111 @@
+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-b0-finetuned-cityscapes-1024-1024"
+)
+model = TFSegformerForSemanticSegmentation.from_pretrained(
+    "nvidia/segformer-b0-finetuned-cityscapes-1024-1024"
+)
+
+def ade_palette():
+    """ADE20K palette that maps each class to RGB values."""
+    return [
+        [204, 87, 92],
+        [67, 123, 89],
+        [32, 90, 210],
+        [56, 156, 200],
+        [45, 56, 123],
+        [67, 123, 56],
+        [45, 123, 67],
+        [184, 20, 100],
+        [107, 86, 176],
+        [168, 200, 52],
+        [206, 40, 143],
+        [204, 52, 114],
+        [112, 30, 83],
+        [145, 48, 83],
+        [123, 89, 189],
+        [106, 120, 210],
+        [156, 112, 78],
+        [57, 78, 145],
+        [89, 156, 78],
+    ]
+
+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=["city-1.jpg", "city-2.jpg", "city-3.jpg", "city-4.jpg", "city-5.jpg"],
+                    allow_flagging='never')
+
+
+demo.launch()

labels.txt

@@ -0,0 +1,19 @@
+road
+sidewalk
+building
+wall
+fence
+pole
+traffic light
+traffic sign
+vegetation
+terrain
+sky
+person
+rider
+car
+truck
+bus
+train
+motorcycle
+bicycle

requirements.txt

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