Shift label to sample center; remove the sigmoid in FC

src/models.py

@@ -185,7 +185,7 @@ class doublePhotonNet_251001(nn.Module):
         x = torch.relu(self.conv3(x))
         # x = self.global_avg_pool(x).view(x.size(0), -1)
         x = self.global_max_pool(x).view(x.size(0), -1)
-        coords = self.fc(x)*6
+        coords = self.fc(x)
         return coords  # shape: [B, 4]
 
 class doublePhotonNet_251001_2(nn.Module):
@@ -220,7 +220,7 @@ class doublePhotonNet_251001_2(nn.Module):
             nn.ReLU(),
             nn.Dropout(0.3),
             nn.Linear(128, 4),
-            nn.Sigmoid()  # output in [0,1]
+            # nn.Sigmoid()  # output in [0,1]
         )
         
         self._init_weights()
@@ -255,55 +255,5 @@ class doublePhotonNet_251001_2(nn.Module):
         global_feat = torch.cat([g_max, g_avg], dim=1)  # [B, 256]
         
         # Regression
-        coords = self.fc(global_feat) * 6.0  # scale to [0,6)
-        return coords  # [B, 4]
-
-class doublePhotonNet_251104(nn.Module):
-    def __init__(self):
-        super().__init__()
-        # Backbone: deeper
-        self.conv1 = nn.Conv2d(3, 32, kernel_size=3) # 6x6 -> 4x4
-        self.conv2 = nn.Conv2d(32, 64, kernel_size=3) # 4x4 -> 2x2
-        self.conv3 = nn.Conv2d(64, 128, kernel_size=2) # 2x2 -> 1x1
-        
-        # Spatial Attention Module (轻量但有效)
-        self.spatial_attn = nn.Sequential(
-            nn.Conv2d(128, 1, kernel_size=1),
-            nn.Sigmoid()
-        )
-        
-        # Enhanced regression head
-        self.fc = nn.Sequential(
-            nn.Linear(128, 256),   # concat max + avg
-            nn.ReLU(),
-            nn.Dropout(0.3),
-            nn.Linear(256, 128),
-            nn.ReLU(),
-            nn.Dropout(0.3),
-            nn.Linear(128, 4),
-            nn.Sigmoid()  # output in [0,1]
-        )
-        
-        self._init_weights()
-    
-    def _init_weights(self):
-        for m in self.modules():
-            if isinstance(m, nn.Conv2d):
-                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
-            elif isinstance(m, nn.Linear):
-                nn.init.xavier_uniform_(m.weight)
-                nn.init.zeros_(m.bias)
-    
-    def forward(self, x):
-        # Feature extraction
-        c1 = F.relu(self.conv1(x))      # [B, 32, 6, 6]
-        c2 = F.relu(self.conv2(c1))     # [B, 64, 6, 6]
-        c3 = F.relu(self.conv3(c2))     # [B,128, 6, 6]
-        
-        # Spatial attention: highlight photon peaks
-        attn = self.spatial_attn(c3)    # [B, 1, 6, 6]
-        c3 = c3 * attn                  # reweight features
-        
-        # Regression
-        coords = self.fc(c3.flatten(1)) * 6.0  # scale to [0,6)
+        coords = self.fc(global_feat)
         return coords  # [B, 4]