p-31 까지의 내용

app.py

@@ -0,0 +1,99 @@
+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 SegformerFeatureExtractor, AutoModelForSemanticSegmentation
+
+feature_extractor = SegformerFeatureExtractor.from_pretrained(
+    "mattmdjaga/segformer_b2_clothes"
+)
+model = AutoModelForSemanticSegmentation.from_pretrained(
+    "mattmdjaga/segformer_b2_clothes"
+)
+
+def ade_palette():
+    """ADE20K palette that maps each class to RGB values."""
+    return [
+        [120, 120, 120], [180, 120, 120], [6, 230, 230], [80, 50, 50], [4, 200, 3], [120, 120, 80],
+        [140, 140, 140], [204, 5, 255], [230, 230, 230], [4, 250, 7], [224, 5, 255], [235, 255, 7],
+        [150, 5, 61], [120, 120, 70], [8, 255, 51], [255, 5, 153], [6, 51, 255], [255, 153, 5]
+    ]
+
+labels_list = []
+with open("../Segmentation/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 = feature_extractor(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=[
+        "person-1.jpg",
+        "person-2.jpg",
+        "person-3.jpg",
+        "person-4.jpg",
+        "person-5.jpg"
+    ],
+    flagging_mode="never",
+    cache_examples=False,
+)
+
+if __name__ == "__main__":
+    demo.launch()

label.txt

@@ -0,0 +1,18 @@
+background
+hat
+hair
+sunglasses
+upper-clothes
+skirt
+pants
+dress
+belt
+left-shoe
+right-shoe
+face
+left-leg
+right-leg
+left-arm
+right-arm
+bag
+scarf

requirements.txt

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