Add images with Git LFS

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.jpg filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,128 @@
+import gradio as gr
+from matplotlib import gridspec
+import matplotlib.pyplot as plt
+import numpy as np
+from PIL import Image
+import torch
+from transformers import AutoImageProcessor, AutoModelForSemanticSegmentation
+
+MODEL_ID = "tobiasc/segformer-b0-finetuned-segments-sidewalk"
+processor = AutoImageProcessor.from_pretrained(MODEL_ID)
+model = AutoModelForSemanticSegmentation.from_pretrained(MODEL_ID)
+
+def ade_palette():
+    """ADE20K palette that maps each class to RGB values."""
+    return [
+        [0, 0, 0],  # 0: unlabeled
+        [120, 120, 120],  # 1: flat-road (회색)
+        [244, 35, 232],  # 2: flat-sidewalk (분홍)
+        [107, 142, 35],  # 3: flat-crosswalk (녹색)
+        [70, 130, 180],  # 4: flat-cyclinglane (하늘색)
+        [255, 0, 0],  # 5: flat-parkingdriveway (빨강)
+        [0, 0, 142],  # 6: flat-railtrack (진청)
+        [220, 20, 60],  # 7: flat-curb (진홍)
+        [220, 220, 0],  # 8: human-person (노랑)
+        [119, 11, 32],  # 9: human-rider (적갈)
+        [0, 0, 230],  # 10: vehicle-car (파랑)
+        [0, 0, 70],  # 11: vehicle-truck (남색)
+        [0, 60, 100],  # 12: vehicle-bus (청록)
+        [0, 80, 100],  # 13: vehicle-tramtrain
+        [0, 0, 110],  # 14: vehicle-motorcycle
+        [111, 74, 0],  # 15: vehicle-bicycle
+        [51, 51, 0],  # 16: vehicle-caravan
+        [81, 0, 81],  # 17: vehicle-cartrailer
+        [70, 70, 70],  # 18: construction-building (진회색)
+        [150, 100, 100],  # 19: construction-door
+        [190, 153, 153],  # 20: construction-wall
+        [153, 153, 153],  # 21: construction-fenceguardrail
+        [102, 102, 156],  # 22: construction-bridge
+        [128, 64, 128],  # 23: construction-tunnel (보라)
+        [64, 170, 64],  # 24: construction-stairs
+        [250, 170, 30],  # 25: object-pole (주황)
+        [255, 255, 0],  # 26: object-trafficsign
+        [152, 251, 152],  # 27: object-trafficlight
+        [31, 119, 180],  # 28: nature-vegetation (초록)
+        [174, 199, 232],  # 29: nature-terrain (연청)
+        [255, 127, 14],  # 30: sky (연주황)
+        [140, 86, 75],  # 31: void-ground
+        [148, 103, 189],  # 32: void-dynamic
+        [227, 119, 194],  # 33: void-static
+        [188, 189, 34]  # 34: void-unclear
+    ]
+
+labels_list = []
+with open("labels.txt", "r", encoding="utf-8") as fp:
+    for line in fp:
+        labels_list.append(line.rstrip("\n"))
+
+colormap = np.asarray(ade_palette(), dtype=np.uint8)
+
+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_np):
+    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_np.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 run_inference(input_img):
+    # input: numpy array from gradio -> PIL
+    img = Image.fromarray(input_img.astype(np.uint8)) if isinstance(input_img, np.ndarray) else input_img
+    if img.mode != "RGB":
+        img = img.convert("RGB")
+
+    inputs = processor(images=img, return_tensors="pt")
+    with torch.no_grad():
+        outputs = model(**inputs)
+        logits = outputs.logits  # (1, C, h/4, w/4)
+
+    # resize to original
+    upsampled = torch.nn.functional.interpolate(
+        logits, size=img.size[::-1], mode="bilinear", align_corners=False
+    )
+    seg = upsampled.argmax(dim=1)[0].cpu().numpy().astype(np.uint8)  # (H,W)
+
+    # colorize & overlay
+    color_seg = colormap[seg]                                # (H,W,3)
+    pred_img = (np.array(img) * 0.5 + color_seg * 0.5).astype(np.uint8)
+
+    fig = draw_plot(pred_img, seg)
+    return fig
+
+demo = gr.Interface(
+    fn=run_inference,
+    inputs=gr.Image(type="numpy", label="Input Image"),
+    outputs=gr.Plot(label="Overlay + Legend"),
+    examples=[
+        "image1.jpg",
+        "image2.jpg",
+        "image3.jpg",
+        "image4.jpg",
+        "image5.jpg"
+    ],
+    flagging_mode="never",
+    cache_examples=False,
+)
+
+if __name__ == "__main__":
+    demo.launch()

labels.txt

@@ -0,0 +1,35 @@
+unlabeled
+flat-road
+flat-sidewalk
+flat-crosswalk
+flat-cyclinglane
+flat-parkingdriveway
+flat-railtrack
+flat-curb
+human-person
+human-rider
+vehicle-car
+vehicle-truck
+vehicle-bus
+vehicle-tramtrain
+vehicle-motorcycle
+vehicle-bicycle
+vehicle-caravan
+vehicle-cartrailer
+construction-building
+construction-door
+construction-wall
+construction-fenceguardrail
+construction-bridge
+construction-tunnel
+construction-stairs
+object-pole
+object-trafficsign
+object-trafficlight
+nature-vegetation
+nature-terrain
+sky
+void-ground
+void-dynamic
+void-static
+void-unclear

requirements.txt

@@ -0,0 +1,6 @@
+torch
+transformers>=4.41.0
+gradio>=4.0.0
+Pillow
+numpy
+matplotlib