example radio

app.py

@@ -1,129 +1,61 @@
 import gradio as gr
-import random
-
-from matplotlib import gridspec
-import matplotlib.pyplot as plt
-import numpy as np
-from PIL import Image
 import tensorflow as tf
-from transformers import SegformerFeatureExtractor, TFSegformerForSemanticSegmentation
-
-feature_extractor = SegformerFeatureExtractor.from_pretrained(
-    "nvidia/segformer-b5-finetuned-cityscapes-1024-1024"
-)
-model = TFSegformerForSemanticSegmentation.from_pretrained(
-    "nvidia/segformer-b5-finetuned-cityscapes-1024-1024"
+from PIL import Image
+import requests
+
+# 모델 로드
+model = tf.saved_model.load("nvidia_segformer_b5_finetuned_cityscapes_1024")
+
+# 레이블 및 색상 정의
+label_colors = {
+    "road": [204, 87, 92],
+    "sidewalk": [112, 185, 212],
+    "building": [196, 160, 122],
+    "wall": [106, 135, 242],
+    "fence": [91, 192, 222],
+    "pole": [255, 192, 203],
+    "traffic_light": [176, 224, 230],
+    "traffic_sign": [222, 49, 99],
+    "vegetation": [139, 69, 19],
+    "terrain": [255, 0, 0],
+    "sky": [0, 0, 255],
+    "person": [255, 228, 181],
+    "rider": [128, 0, 0],
+    "car": [0, 128, 0],
+    "truck": [255, 99, 71],
+    "bus": [0, 255, 0],
+    "train": [128, 0, 128],
+    "motorcycle": [255, 255, 0],
+    "bicycle": [128, 0, 128]
+}
+
+# Gradio 인터페이스 정의
+iface = gr.Interface(
+    fn=lambda image: predict_segmentation(image, model),
+    inputs="image",
+    outputs="image"
 )
-
-def ade_palette():
-
-    return [
-        [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)
-        [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)
-        [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)
-
-    ]
-
-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_left()
-    plt.yticks(range(len(unique_labels)), LABEL_NAMES[unique_labels])
-    plt.xticks([], [])
-    ax.tick_params(width=0.0, labelsize=27)
-    return fig
-
-def sepia(input_img):
-    input_img = Image.fromarray(input_img)
-
-    inputs = feature_extractor(images=input_img, return_tensors="tf")
-    outputs = model(**inputs)
-    logits = outputs.logits
-
-    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
-    )  # 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
-
-
-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()
-
+iface.launch()
+
+# 이미지 세그멘테이션 함수 정의
+def predict_segmentation(image, model):
+    # 이미지 변환
+    image = Image.fromarray(image.astype('uint8'), 'RGB')
+    image = image.resize((1024, 1024))  # 모델의 입력 크기에 맞게 조절
+    image_array = tf.keras.preprocessing.image.img_to_array(image)
+    image_array = tf.expand_dims(image_array, 0)
+
+    # 모델 추론
+    predictions = model(image_array)["output_0"]
+
+    # 레이블별 색상 매핑
+    segmented_image = tf.zeros_like(predictions)
+    for label, color in label_colors.items():
+        mask = tf.reduce_all(tf.equal(predictions, color), axis=-1, keepdims=True)
+        for i in range(3):
+            segmented_image += tf.cast(mask, tf.float32) * tf.constant(color[i], dtype=tf.float32)
+
+    # 이미지 리턴
+    segmented_image = tf.cast(segmented_image, tf.uint8)
+    segmented_image = tf.image.resize(segmented_image, [image.height, image.width])
+    return segmented_image.numpy()