block test

app.py

@@ -15,8 +15,8 @@ model = TFSegformerForSemanticSegmentation.from_pretrained(
     "nvidia/segformer-b5-finetuned-cityscapes-1024-1024"
 )
 
-
 def ade_palette():
+
     return [
         [204, 87, 92],  # road (Reddish)
         [112, 185, 212],  # sidewalk (Blue)
@@ -37,8 +37,8 @@ def ade_palette():
         [128, 0, 128],  # train (Purple)
         [255, 255, 0],  # motorcycle (Yellow)
         [128, 0, 128]  # bicycle (Purple)
-    ]
 
+    ]
 
 labels_list = []
 
@@ -48,7 +48,6 @@ with open(r'labels.txt', 'r') as fp:
 
 colormap = np.asarray(ade_palette())
 
-
 def label_to_color_image(label):
     if label.ndim != 2:
         raise ValueError("Expect 2-D input label")
@@ -57,15 +56,14 @@ def label_to_color_image(label):
         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)
@@ -79,7 +77,6 @@ def draw_plot(pred_img, seg):
     ax.tick_params(width=0.0, labelsize=25)
     return fig
 
-
 def sepia(input_img):
     input_img = Image.fromarray(input_img)
 
@@ -88,7 +85,9 @@ def sepia(input_img):
     logits = outputs.logits
 
     logits = tf.transpose(logits, [0, 2, 3, 1])
-    logits = tf.image.resize(logits, input_img.size[::-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(
@@ -97,23 +96,44 @@ def sepia(input_img):
     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
-
-
-# Gradio Blocks로 변환
+"""
+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 */
+                        }
+                        """
+
+                    )
+"""
 with gr.Blocks() as demo:
-    img_input = gr.Image(shape=(564, 846))
-    img_output = gr.Image()
 
-    # 사용자 입력을 받는 부분 추가
-    input_img = gr.Image(shape=(564, 846), source=img_input)
-    input_img.click(sepia, img_input, img_output)
 
-    # 사용자 입력에 대한 결과를 출력
-    img_output.source(sepia, img_input)
 
-demo.launch()
+    gr.MarkDown("This is a machine learning activity project at Kyunggi University.")
+    with gr.Row():
+        with gr.Column():
+            inputs = gr.Image(shape=(564, 846))
+        with gr.Column():
+            outputs = ['plot']
+    btn=gr.Button("Activate")
+    btn.click(sepia,inputs=[inputs],outputs=[outputs])
+    gr.Examples(["city1.jpg", "city2.jpg", "city3.jpg"],inputs=[inputs])
+if __name__ == "__main__":
+    demo.launch()
+