Update app.py

app.py

@@ -9,12 +9,10 @@ from PIL import Image
 import matplotlib.pyplot as plt
 from model.CyueNet_models import MMS
 from utils1.data import transform_image
-import plotly.graph_objects as go
-import plotly.express as px
-import pandas as pd
 
-# 设置GPU/CPU
-device = torch.device('cuda:0' if torch.cuda.cuda.is_available() else 'cpu')
+# 设置GPU/CPU - 修复了torch.cuda.is_available()的调用
+device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
+
 custom_css = """
     :root {
         --primary-color: #2196F3;
@@ -140,6 +138,7 @@ custom_css = """
         margin: 15px 0;
     }
 """
+
 class ImageProcessor:
     def __init__(self):
         self.model = None
@@ -186,25 +185,31 @@ class ImageProcessor:
         return image
 
     def generate_analysis_plots(self, saliency_map):
-        """生成分析图表"""
-        # 直方图数据
-        hist_data = saliency_map.flatten()
-        fig_hist = px.histogram(hist_data, nbins=50,
-                              title="显著性分布直方图",
-                              labels={'value': '显著性值', 'count': '频率'})
+        """生成分析图表 - 使用matplotlib替代plotly"""
+        # 创建直方图
+        plt.figure(figsize=(8, 4))
+        plt.hist(saliency_map.flatten(), bins=50, color='skyblue', edgecolor='black')
+        plt.title('显著性分布直方图')
+        plt.xlabel('显著性值')
+        plt.ylabel('频率')
+        plt.grid(axis='y', alpha=0.75)
         
-        # 计算显著性统计
-        regions = np.zeros_like(saliency_map)
-        regions[saliency_map > np.mean(saliency_map)] = 1
+        # 保存到缓冲区
+        plt.tight_layout()
+        plt.savefig('temp_hist.png')
+        plt.close()
         
-        return fig_hist
+        # 读取并返回图像
+        hist_img = cv2.imread('temp_hist.png')
+        hist_img = cv2.cvtColor(hist_img, cv2.COLOR_BGR2RGB)
+        return hist_img
 
     def process_image(self, image, threshold=0.5, testsize=256, 
                      enhance_contrast=False, denoise=False, 
                      brightness=0, contrast=0, filter_type="无"):
         """增强的图像处理函数"""
         if image is None:
-            return [None] * 7 + ["请提供有效的图像"]
+            return [None] * 8 + ["请提供有效的图像"]
 
         # 图像预处理
         if denoise:
@@ -270,9 +275,10 @@ class ImageProcessor:
         analysis_plot = self.generate_analysis_plots(res_resized)
         
         # 计算统计信息
+        contours = cv2.findContours(binary_mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)[0]
         stats = {
             "处理分辨率": f"{w}x{h}",
-            "检测目标数量": str(len(cv2.findContours(binary_mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)[0])),
+            "检测目标数量": str(len(contours)),
             "平均置信度": f"{np.mean(res_resized):.2%}",
             "最大置信度": f"{np.max(res_resized):.2%}",
             "处理时间": f"{inference_time:.3f}秒"
@@ -440,8 +446,9 @@ with gr.Blocks(title="高级显著性目标检测系统", css=custom_css) as dem
                                 stats_output = gr.HTML(
                                     label="统计信息"
                                 )
-                                analysis_plot = gr.Plot(
-                                    label="显著性分布分析"
+                                analysis_plot = gr.Image(
+                                    label="显著性分布分析",
+                                    elem_classes="output-image"
                                 )
 
         with gr.TabItem("📖 使用指南"):
@@ -540,4 +547,4 @@ with gr.Blocks(title="高级显著性目标检测系统", css=custom_css) as dem
 
 # 启动应用
 if __name__ == "__main__":
-    demo.launch(share=True)
+    demo.launch(share=True)