theme

app.py

@@ -1,4 +1,6 @@
 import gradio as gr
+import random
+
 from matplotlib import gridspec
 import matplotlib.pyplot as plt
 import numpy as np
@@ -14,26 +16,28 @@ model = TFSegformerForSemanticSegmentation.from_pretrained(
 )
 
 def ade_palette():
+
     return [
-        [204, 87, 92],   # road (Reddish)
+        [204, 87, 92],  # road (Reddish)
         [112, 185, 212],  # sidewalk (Blue)
         [196, 160, 122],  # building (Brown)
         [106, 135, 242],  # wall (Light Blue)
-        [91, 192, 222],   # fence (Turquoise)
+        [91, 192, 222],  # fence (Turquoise)
         [255, 192, 203],  # pole (Pink)
         [176, 224, 230],  # traffic light (Light Blue)
-        [222, 49, 99],    # traffic sign (Red)
-        [139, 69, 19],    # vegetation (Brown)
-        [255, 0, 0],      # terrain (Red)
-        [0, 0, 255],      # sky (Blue)
+        [222, 49, 99],  # traffic sign (Red)
+        [139, 69, 19],  # vegetation (Brown)
+        [255, 0, 0],  # terrain (Red)
+        [0, 0, 255],  # sky (Blue)
         [255, 228, 181],  # person (Peach)
-        [128, 0, 0],      # rider (Maroon)
-        [0, 128, 0],      # car (Green)
-        [255, 99, 71],    # truck (Tomato)
-        [0, 255, 0],      # bus (Lime)
-        [128, 0, 128],    # train (Purple)
-        [255, 255, 0],    # motorcycle (Yellow)
-        [128, 0, 128]     # bicycle (Purple)
+        [128, 0, 0],  # rider (Maroon)
+        [0, 128, 0],  # car (Green)
+        [255, 99, 71],  # truck (Tomato)
+        [0, 255, 0],  # bus (Lime)
+        [128, 0, 128],  # train (Purple)
+        [255, 255, 0],  # motorcycle (Yellow)
+        [128, 0, 128]  # bicycle (Purple)
+
     ]
 
 labels_list = []
@@ -73,14 +77,7 @@ def draw_plot(pred_img, seg):
     ax.tick_params(width=0.0, labelsize=25)
     return fig
 
-def sepia(input_img, *label_buttons):
-    selected_color = None
-    for label, button_state in zip(labels_list, label_buttons):
-        if button_state:
-            label_index = labels_list.index(label)
-            selected_color = colormap[label_index]
-            break
-
+def sepia(input_img):
     input_img = Image.fromarray(input_img)
 
     inputs = feature_extractor(images=input_img, return_tensors="tf")
@@ -90,43 +87,129 @@ def sepia(input_img, *label_buttons):
     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]
 
     color_seg = np.zeros(
         (seg.shape[0], seg.shape[1], 3), dtype=np.uint8
-    )
-    if selected_color:
-        label = colormap.index(selected_color)
-        color_seg[seg.numpy() == label, :] = selected_color
+    )  # height, width, 3
+    for label, color in enumerate(colormap):
+        color_seg[seg.numpy() == label, :] = color
 
+    # Show image + mask
     pred_img = np.array(input_img) * 0.5 + color_seg * 0.5
     pred_img = pred_img.astype(np.uint8)
 
     fig = draw_plot(pred_img, seg)
     return fig
 
-# 라벨 버튼 생성
-label_buttons = [gr.Button(label) for label in labels_list]
-
-# Gradio 인터페이스 생성
-iface = gr.Interface(
-    fn=sepia,
-    inputs=[gr.Image(shape=(564, 846))] + label_buttons,
-    outputs="plot",
-    live=True,
-    examples=["city1.jpg", "city2.jpg", "city3.jpg"],
-    allow_flagging='never',
-    title="This is a machine learning activity project at Kyunggi University.",
-    theme="darkpeach",
-    css="""
-    body{
-        background-color: dark;
-        color: white;
-        font-family: Arial, sans-serif;
-    }
-    """
-)
 
-# Gradio 인터페이스 시작
-iface.launch()
+with gr.Blocks() as demo:
+    section_labels = [
+        "road",
+        "sidewalk",
+        "building",
+        "wall",
+        "fence",
+        "pole",
+        "traffic light",
+        "traffic sign",
+        "vegetation",
+        "terrain",
+        "sky",
+        "person",
+        "rider",
+        "car",
+        "truck",
+        "bus",
+        "train",
+        "motorcycle",
+        "bicycle"
+    ]
+
+    with gr.Row():
+        num_boxes = gr.Slider(1, 1, 1, step=0, label="Number of boxes")
+        num_segments = gr.Slider(0, 19, 1, step=1, label="Number of segments")
+
+    with gr.Row():
+        img_input = gr.Image()
+        img_output = gr.AnnotatedImage(
+            color_map={
+                "road": "#CC575C",
+                "sidewalk": "#70B9D4",
+                "building": "#C4A07A",
+                "wall": "#6A87F2",
+                "fence": "#5BC0DE",
+                "pole": "#FFC0CB",
+                "traffic light": "#B0E0E6",
+                "traffic sign": "#DE3163",
+                "vegetation": "#8B4513",
+                "terrain": "#FF0000",
+                "sky": "#0000FF",
+                "person": "#FFE4B5",
+                "rider": "#800000",
+                "car": "#008000",
+                "truck": "#FF6347",
+                "bus": "#00FF00",
+                "train": "#800080",
+                "motorcycle": "#FFFF00",
+                "bicycle": "#800080"}
+        )
+
+    section_btn = gr.Button("Identify Sections")
+    selected_section = gr.Textbox(label="Selected Section")
+
+
+    def section(img, num_boxes, num_segments):
+        sections = []
+
+        for a in range(num_boxes):
+            x = random.randint(0, img.shape[1])
+            y = random.randint(0, img.shape[0])
+            w = random.randint(0, img.shape[1] - x)
+            h = random.randint(0, img.shape[0] - y)
+            sections.append(((x, y, x + w, y + h), section_labels[a]))
+        for b in range(num_segments):
+            x = random.randint(0, img.shape[1])
+            y = random.randint(0, img.shape[0])
+            r = random.randint(0, min(x, y, img.shape[1] - x, img.shape[0] - y))
+            mask = np.zeros(img.shape[:2])
+            for i in range(img.shape[0]):
+                for j in range(img.shape[1]):
+                    dist_square = (i - y) ** 2 + (j - x) ** 2
+                    if dist_square < r ** 2:
+                        mask[i, j] = round((r ** 2 - dist_square) / r ** 2 * 4) / 4
+            sections.append((mask, section_labels[b + num_boxes]))
+        return (img, sections)
+
+
+    section_btn.click(section, [img_input, num_boxes, num_segments], img_output)
+
+
+    def select_section(evt: gr.SelectData):
+        return section_labels[evt.index]
+
+
+    img_output.select(select_section, None, selected_section)
+
+demo = gr.Interface(fn=sepia,
+                    inputs=gr.Image(shape=(564,846)),
+                    outputs=['plot'],
+                    live=True,
+                    examples=["city1.jpg","city2.jpg","city3.jpg"],
+                    allow_flagging='never',
+                    title="This is a machine learning activity project at Kyunggi University.",
+                    theme="darkpeach",
+                    css="""
+                        body {
+                            background-color: dark;
+                            color: white;  /* 폰트 색상 수정 */
+                            font-family: Arial, sans-serif;  /* 폰트 패밀리 수정 */
+                        }
+                        """
+
+                    )
+
+
+demo.launch()
+