Upload 8 files

.gitattributes

@@ -33,3 +33,6 @@ 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
+test-1.jpg filter=lfs diff=lfs merge=lfs -text
+test-2.jpg filter=lfs diff=lfs merge=lfs -text
+test-3.jpg filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,147 @@
+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 = "jonathandinu/face-parsing"
+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 [
+        [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], [200, 32, 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
+
+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="🎨 머신러닝 6차 과제", theme=gr.themes.Base(
+    primary_hue="blue",      # GitHub 파란색 계열 버튼
+    secondary_hue="slate",   # 회색 포인트
+    neutral_hue="gray",      # 배경 톤
+    text_size=gr.themes.sizes.text_md,
+    font=["JetBrains Mono", "sans-serif"],  # GitHub 느낌 폰트
+    radius_size=gr.themes.sizes.radius_sm
+)) as demo:
+    theme=gr.themes.Glass() 
+    gr.Markdown("""
+    # ⭐ Face Parsing Demo
+    얼굴 각 부위를 자동으로 구분하는 Image Segmentation 모델입니다.
+
+    **활용 모델:** `jonathandinu/face-parsing`  
+    **컴퓨터공학전공 202111570 조항준** 
+
+    ---
+
+    👍 업로드한 얼굴 이미지를 분석하여, 머리카락·피부·눈·입 등의 얼굴 영역을 각각 다른 색상으로 표시합니다.\n
+    👍 본 모델은 유명인사들의 얼굴로 이루어진 CelebAMask-HQ dataset 을 활용하여 학습된 모델입니다.\n
+    """)
+    
+    gr.Markdown("""
+        👍 탐지할 수 있는 영역은 아래와 같습니다. \n
+    	background / skin / nose / eye_g / l_eye / r_eye / l_brow / r_brow / l_ear / r_ear / mouth / u_lip / l_lip / hair / hat	/ ear_r / neck_l / neck	/ cloth
+    """)
+    
+    gr.Interface(
+        fn=run_inference,
+        inputs=gr.Image(type="numpy", label="Input Image"),
+        outputs=gr.Plot(label="Overlay + Legend"),
+        examples=[
+            "test-1.jpg",
+            "test-2.jpg",
+            "test-3.jpg",
+            "test-4.jpg",
+            "test-5.jpg"
+        ],
+        flagging_mode="never",
+        cache_examples=False,
+    )
+
+if __name__ == "__main__":
+    demo.launch()

labels.txt

@@ -0,0 +1,19 @@
+background
+skin
+nose
+eye_g
+l_eye
+r_eye
+l_brow
+r_brow
+l_ear
+r_ear
+mouth
+u_lip
+l_lip
+hair
+hat
+ear_r
+neck_l
+neck
+cloth

requirements.txt

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