Update app.py

app.py

@@ -1,37 +1,108 @@
 import gradio as gr
+
+from matplotlib import gridspec
+import matplotlib.pyplot as plt
 import numpy as np
 from PIL import Image
-from transformers import SegformerFeatureExtractor, TFSegformerForSemanticSegmentation
 import tensorflow as tf
+from transformers import SegformerFeatureExtractor, TFSegformerForSemanticSegmentation
 
-# Segformer 모델 및 feature extractor 불러오기
 feature_extractor = SegformerFeatureExtractor.from_pretrained(
-    "nvidia/segformer-b1-finetuned-cityscapes-1024-1024")
+    "nvidia/segformer-b1-finetuned-cityscapes-1024-1024"
+)
 model = TFSegformerForSemanticSegmentation.from_pretrained(
-    "nvidia/segformer-b1-finetuned-cityscapes-1024-1024")
+    "nvidia/segformer-b1-finetuned-cityscapes-1024-1024"
+)
+
+def ade_palette():
+    """ADE20K palette that maps each class to RGB values."""
+    return [
+        [204, 166, 62],
+        [188, 229, 92],
+        [47, 157,39],
+        [178, 235, 244],
+        [0, 51, 153],
+        [181, 178, 255],
+        [128, 65, 217],
+        [255, 178, 245],
+        [153, 0, 76],
+        [25, 186, 52],
+        [81, 162, 235],
+        [255, 255, 0],
+        [62, 57, 159],
+        [91, 189, 203],
+        [0, 0, 255],
+        [0, 255, 255],
+        [12, 168, 0],
+        [255, 0, 0],
+        [231, 32, 65]
+    ]
+
+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)
 
-# 모델 예측 함수를 정의합니다.
-def classify_image(img):
-    try:
-        # 이미지를 전처리합니다.
-        inputs = feature_extractor(images=img, return_tensors="tf")
+    inputs = feature_extractor(images=input_img, return_tensors="tf")
+    outputs = model(**inputs)
+    logits = outputs.logits
 
-        # 모델로 예측을 수행합니다.
-        predictions = model(**inputs)
+    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]
 
-        # 예측 결과 중에서 가장 높은 확률을 가진 클래스를 선택합니다.
-        predicted_label = tf.argmax(predictions.logits[0], axis=-1).numpy()
+    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
 
-        # 라벨을 반환합니다.
-        return predicted_label
-    except Exception as e:
-        # 예외가 발생하면 예외 메시지를 반환합니다.
-        return str(e)
+    # Show image + mask
+    pred_img = np.array(input_img) * 0.5 + color_seg * 0.5
+    pred_img = pred_img.astype(np.uint8)
 
-# Gradio UI를 생성합니다.
-iface = gr.Interface(fn=classify_image,
-                     inputs="image",
-                     outputs="label", live=True)
+    fig = draw_plot(pred_img, seg)
+    return fig
 
-# Gradio UI를 시작합니다.
-iface.launch()
+demo = gr.Interface(fn=sepia,
+                    inputs=gr.Image(shape=(800, 600)),
+                    outputs=['plot'],
+                    examples=["cityoutdoor-1.jpg", "cityoutdoor-2.jpg", "cityoutdoor-3.jpg"],
+                    allow_flagging='never')