Update model.py

model.py

@@ -1,144 +1,3 @@
 import torch
 import torch.nn as nn
-import torch.nn.functional as F
-
-class Enhanced3DCNN(nn.Module):
-    def __init__(self, num_classes=3, dropout_rate=0.5):
-        super().__init__()
-        self.conv1 = nn.Conv3d(1, 32, kernel_size=3, padding=1)
-        self.bn1 = nn.BatchNorm3d(32)
-        self.pool1 = nn.MaxPool3d(2)
-
-        self.conv2 = nn.Conv3d(32, 64, kernel_size=3, padding=1)
-        self.bn2 = nn.BatchNorm3d(64)
-        self.pool2 = nn.MaxPool3d(2)
-
-        self.conv3 = nn.Conv3d(64, 128, kernel_size=3, padding=1)
-        self.bn3 = nn.BatchNorm3d(128)
-        self.pool3 = nn.MaxPool3d(2)
-
-        self.conv4 = nn.Conv3d(128, 256, kernel_size=3, padding=1)
-        self.bn4 = nn.BatchNorm3d(256)
-        self.pool4 = nn.AdaptiveAvgPool3d(1)
-
-        self.dropout = nn.Dropout(dropout_rate)
-        self.fc1 = nn.Linear(256, 128)
-        self.fc2 = nn.Linear(128, num_classes)
-
-        self._initialize_weights()
-
-    def _initialize_weights(self):
-        for m in self.modules():
-            if isinstance(m, nn.Conv3d):
-                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
-                if m.bias is not None:
-                    nn.init.constant_(m.bias, 0)
-            elif isinstance(m, nn.BatchNorm3d):
-                nn.init.constant_(m.weight, 1)
-                nn.init.constant_(m.bias, 0)
-            elif isinstance(m, nn.Linear):
-                nn.init.normal_(m.weight, 0, 0.01)
-                nn.init.constant_(m.bias, 0)
-
-    def forward(self, x):
-        x = self.pool1(F.relu(self.bn1(self.conv1(x))))
-        x = self.pool2(F.relu(self.bn2(self.conv2(x))))
-        x = self.pool3(F.relu(self.bn3(self.conv3(x))))
-        x = self.pool4(F.relu(self.bn4(self.conv4(x))))
-        x = x.view(x.size(0), -1)
-        x = F.relu(self.fc1(self.dropout(x)))
-        return self.fc2(x)
-
-class Enhanced3DCNNv7(nn.Module):
-    def __init__(self, num_classes=3, dropout_rate=0.2):
-        super().__init__()
-        self.conv1 = nn.Conv3d(1, 32, kernel_size=2, padding=1)
-        self.bn1 = nn.BatchNorm3d(32)
-        self.pool1 = nn.MaxPool3d(2)
-
-        self.conv2 = nn.Conv3d(32, 64, kernel_size=2, padding=1)
-        self.bn2 = nn.BatchNorm3d(64)
-        self.pool2 = nn.MaxPool3d(2)
-
-        self.conv3 = nn.Conv3d(64, 128, kernel_size=2, padding=1)
-        self.bn3 = nn.BatchNorm3d(128)
-        self.pool3 = nn.MaxPool3d(2)
-
-        self.conv4 = nn.Conv3d(128, 256, kernel_size=2, padding=1)
-        self.bn4 = nn.BatchNorm3d(256)
-        self.pool4 = nn.AdaptiveAvgPool3d(1)
-
-        self.dropout = nn.Dropout(dropout_rate)
-        self.fc1 = nn.Linear(256, 128)
-        self.fc2 = nn.Linear(128, num_classes)
-
-        self._initialize_weights()
-
-    def _initialize_weights(self):
-        for m in self.modules():
-            if isinstance(m, nn.Conv3d):
-                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
-                if m.bias is not None:
-                    nn.init.constant_(m.bias, 0)
-            elif isinstance(m, nn.BatchNorm3d):
-                nn.init.constant_(m.weight, 1)
-                nn.init.constant_(m.bias, 0)
-            elif isinstance(m, nn.Linear):
-                nn.init.normal_(m.weight, 0, 0.01)
-                nn.init.constant_(m.bias, 0)
-
-    def forward(self, x):
-        x = self.pool1(F.relu(self.bn1(self.conv1(x))))
-        x = self.pool2(F.relu(self.bn2(self.conv2(x))))
-        x = self.pool3(F.relu(self.bn3(self.conv3(x))))
-        x = self.pool4(F.relu(self.bn4(self.conv4(x))))
-        x = x.view(x.size(0), -1)
-        x = F.relu(self.fc1(self.dropout(x)))
-        return self.fc2(x)
-
-class Enhanced3DCNNv8(nn.Module):
-    def __init__(self, num_classes=3, dropout_rate=0.25):
-        super().__init__()
-        self.conv1 = nn.Conv3d(1, 32, kernel_size=1, padding=1)
-        self.bn1 = nn.BatchNorm3d(32)
-        self.pool1 = nn.MaxPool3d(2)
-
-        self.conv2 = nn.Conv3d(32, 64, kernel_size=1, padding=1)
-        self.bn2 = nn.BatchNorm3d(64)
-        self.pool2 = nn.MaxPool3d(2)
-
-        self.conv3 = nn.Conv3d(64, 128, kernel_size=1, padding=1)
-        self.bn3 = nn.BatchNorm3d(128)
-        self.pool3 = nn.MaxPool3d(2)
-
-        self.conv4 = nn.Conv3d(128, 256, kernel_size=1, padding=1)
-        self.bn4 = nn.BatchNorm3d(256)
-        self.pool4 = nn.AdaptiveAvgPool3d(1)
-
-        self.dropout = nn.Dropout(dropout_rate)
-        self.fc1 = nn.Linear(256, 128)
-        self.fc2 = nn.Linear(128, num_classes)
-
-        self._initialize_weights()
-
-    def _initialize_weights(self):
-        for m in self.modules():
-            if isinstance(m, nn.Conv3d):
-                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
-                if m.bias is not None:
-                    nn.init.constant_(m.bias, 0)
-            elif isinstance(m, nn.BatchNorm3d):
-                nn.init.constant_(m.weight, 1)
-                nn.init.constant_(m.bias, 0)
-            elif isinstance(m, nn.Linear):
-                nn.init.normal_(m.weight, 0, 0.01)
-                nn.init.constant_(m.bias, 0)
-
-    def forward(self, x):
-        x = self.pool1(F.relu(self.bn1(self.conv1(x))))
-        x = self.pool2(F.relu(self.bn2(self.conv2(x))))
-        x = self.pool3(F.relu(self.bn3(self.conv3(x))))
-        x = self.pool4(F.relu(self.bn4(self.conv4(x))))
-        x = x.view(x.size(0), -1)
-        x = F.relu(self.fc1(self.dropout(x)))
-        return self.fc2(x)
+import torch.nn.functional as F