Upload 6 files

.gitattributes

@@ -38,3 +38,4 @@ city-2.jpg filter=lfs diff=lfs merge=lfs -text
 city-3.jpg filter=lfs diff=lfs merge=lfs -text
 city-4.jpg filter=lfs diff=lfs merge=lfs -text
 city-5.jpg filter=lfs diff=lfs merge=lfs -text
+city-3.jpeg filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,105 @@
+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 = "nvidia/segformer-b0-finetuned-cityscapes-512-1024"
+processor = AutoImageProcessor.from_pretrained("nvidia/segformer-b0-finetuned-cityscapes-512-1024")
+model = AutoModelForSemanticSegmentation.from_pretrained("nvidia/segformer-b0-finetuned-cityscapes-512-1024")
+
+def ade_palette():
+    """ADE20K palette that maps each class to RGB values."""
+    return [
+        [204, 87, 92],[112, 185, 212],[45, 189, 106],[234, 123, 67],[78, 56, 123],[210, 32, 89],
+        [90, 180, 56],[155, 102, 200],[33, 147, 176],[255, 183, 76],[67, 123, 89],[190, 60, 45],
+        [134, 112, 200],[56, 45, 189],[200, 56, 123],[87, 92, 204],[120, 56, 123],[45, 78, 123],
+    ]
+
+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
+
+with gr.Blocks(title="City Segmentation Demo") as demo:
+    gr.Markdown("# 🏙️ 도시 이미지 시맨틱 세그멘테이션")
+    gr.Markdown("이미지를 업로드하면 SegFormer가 도로, 건물, 하늘 등을 색상으로 구분합니다.")
+
+    with gr.Row():
+        with gr.Column(scale=1):
+            input_image = gr.Image(type="numpy", label="입력 이미지")
+            run_button = gr.Button("🔍 분석 실행")
+            gr.Examples(
+                examples=[
+                    ["city-1.jpg"],
+                    ["city-2.jpg"],
+                    ["city-3.jpeg"],
+                    ["city-4.jpg"],
+                    ["city-5.jpg"],
+                ],
+                inputs=input_image
+            )
+
+        with gr.Column(scale=2):
+            output_plot = gr.Plot(label="결과 (Segmentation Overlay + Legend)")
+
+    run_button.click(fn=run_inference, inputs=input_image, outputs=output_plot)
+
+if __name__ == "__main__":
+    demo.launch()