做了一个向量相乘的APP,避免embedding_mobile递归循环.

net/resnet_embedding.py

@@ -97,21 +97,31 @@ class ResNet50EmbeddingNet(nn.Module):
     def mobile_preprocess(self, x: torch.Tensor) -> torch.Tensor:
         """
         移动端预处理（TorchScript兼容）
-        
+
         Args:
             x: 输入tensor，形状为 [batch, 3, height, width]，值范围 0-1
-            
+
         Returns:
             torch.Tensor: 预处理后的tensor，形状为 [batch, 3, 224, 224]
         """
+        # # 通过 scale_factor 避免对 size 的整数检查（规避 RecursionError）
+        # h, w = x.shape[2], x.shape[3]
+        # # 防御：避免除零
+        # if h == 0 or w == 0:
+        #     raise ValueError(f"Invalid input size: height={h}, width={w}")
+        # scale_h = 224.0 / float(h)
+        # scale_w = 224.0 / float(w)
+        #
+        # x = F.interpolate(x, scale_factor=(scale_h, scale_w),
+        #                   mode='bilinear', align_corners=False)
         # 缩放到 224x224
         x = F.interpolate(x, size=(224, 224), mode='bilinear', align_corners=False)
-        
+
         # ImageNet标准化
         mean = torch.tensor([0.485, 0.456, 0.406], device=x.device).view(1, 3, 1, 1)
         std = torch.tensor([0.229, 0.224, 0.225], device=x.device).view(1, 3, 1, 1)
         x = (x - mean) / std
-        
+
         return x
     
     def _forward_backbone(self, x: torch.Tensor) -> torch.Tensor:
@@ -180,8 +190,8 @@ class ResNet50EmbeddingNet(nn.Module):
         # 移动端预处理
         x = self.mobile_preprocess(x)
         
-        # 执行前向传播
-        return self.forward(x, normalize=normalize)
+        # 显式调用基类 forward，避免子类重写的 forward 形成递归
+        return ResNet50EmbeddingNet.forward(self, x, normalize=normalize)
     
     def extract_embedding(self, image: Union[Image.Image, np.ndarray, torch.Tensor], 
                          normalize: bool = True) -> np.ndarray:
@@ -210,7 +220,8 @@ class ResNet50EmbeddingNet(nn.Module):
             
             # 提取特征
             embedding = self.forward(x, normalize=normalize)
-            
+            # embedding = self.forward(x, normalize=False)
+
             return embedding.cpu().numpy().flatten()
     
     def extract_batch_embeddings(self, images: List[Union[Image.Image, np.ndarray]], 
@@ -365,7 +376,7 @@ def create_resnet50_embedding(embedding_dim: int = 512,
     )
 
 
-def create_mobile_resnet50_embedding(embedding_dim: int = 512) -> ResNet50EmbeddingNet:
+def create_mobile_resnet50_embedding(embedding_dim: int = 512,pretrained: bool = True) -> ResNet50EmbeddingNet:
     """
     创建移动端ResNet50 Embedding模型
     
@@ -387,15 +398,10 @@ def create_mobile_resnet50_embedding(embedding_dim: int = 512) -> ResNet50Embedd
         def forward(self, x: torch.Tensor, normalize: bool = True) -> torch.Tensor:
             """
             移动端前向传播（自动包含预处理）
-            
-            Args:
-                x: 输入tensor，形状为 [batch, 3, height, width]，值范围 0-1
-                normalize: 是否对输出进行L2归一化
-                
-            Returns:
-                torch.Tensor: embedding向量
             """
-            return self.forward_mobile(x, normalize=normalize)
+            # 在子类里做预处理，然后显式调用基类 forward
+            x = self.mobile_preprocess(x)
+            return ResNet50EmbeddingNet.forward(self, x, normalize=normalize)
     
     return MobileResNet50Embedding(embedding_dim=embedding_dim)
 

toAndroid/toAndroidEmbedding.py

@@ -15,7 +15,8 @@ def main():
     print("开始转换ResNet50 Embedding模型为移动端格式...")
     
     # 1. 加载训练好的embedding模型权重
-    base_model = create_resnet50_embedding(embedding_dim=512, pretrained=True)
+    # base_model = create_resnet50_embedding(embedding_dim=512, pretrained=True)
+    base_model = create_mobile_resnet50_embedding(embedding_dim=512, pretrained=True)
     model_path = "../model/embedding_20250917_145342/best_embedding_model.pth"
     
     if not os.path.exists(model_path):

toAndroid/toAndroidSearch.py

@@ -127,11 +127,11 @@ class TwoLayerSimilarityNet(nn.Module):
             raise ValueError("输入张量形状必须为 [batch, 512]")
 
         # 输入归一化
-        # x_norm = F.normalize(x, p=2, dim=1)  # [B, 512]
+        x_norm = F.normalize(x, p=2, dim=1)  # [B, 512]
 
         # 单层线性变换
-        # sims = self.layer2(x_norm)          # [B, N]
-        sims = self.layer2(x)          # [B, N]
+        sims = self.layer2(x_norm)          # [B, N]
+        # sims = self.layer2(x)          # [B, N]
 
         return sims