Update model.py

model.py

@@ -1,47 +1,60 @@
-from huggingface_hub import hf_hub_download
 import torch
 import torch.nn as nn
+from huggingface_hub import hf_hub_download
 
 class SimpleCNN(nn.Module):
-    def __init__(self, num_classes=6):
+    def __init__(self, model_type='f', num_classes=6):
         super(SimpleCNN, self).__init__()
-        self.conv1 = nn.Conv2d(3, 32, kernel_size=3, padding=1)
-        self.conv2 = nn.Conv2d(32, 64, kernel_size=3, padding=1)
-        self.conv3 = nn.Conv2d(64, 128, kernel_size=3, padding=1)
-        self.pool = nn.MaxPool2d(kernel_size=2, stride=2)
+        self.num_classes = num_classes
+        if model_type == 'f':
+            self.conv1 = nn.Conv2d(3, 16, kernel_size=3, stride=1, padding=1)
+            self.conv2 = nn.Conv2d(16, 32, kernel_size=3, stride=1, padding=1)
+            self.conv3 = nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1)
+            self.fc1 = nn.Linear(64 * 28 * 28, 256)
+            self.dropout = nn.Dropout(0.5)
+        elif model_type == 'c':
+            self.conv1 = nn.Conv2d(3, 32, kernel_size=3, stride=1, padding=1)
+            self.conv2 = nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1)
+            self.conv3 = nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1)
+            self.fc1 = nn.Linear(128 * 28 * 28, 512)
+            self.dropout = nn.Dropout(0.5)
+        elif model_type == 'q':
+            self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1)
+            self.conv2 = nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1)
+            self.conv3 = nn.Conv2d(128, 256, kernel_size=3, stride=1, padding=1)
+            self.conv4 = nn.Conv2d(256, 512, kernel_size=3, stride=1, padding=1)
+            self.fc1 = nn.Linear(512 * 14 * 14, 1024)
+            self.dropout = nn.Dropout(0.3)
+        self.fc2 = nn.Linear(self.fc1.out_features, num_classes)
         self.relu = nn.ReLU()
-        self.dropout = nn.Dropout(0.5)
-        self._initialize_fc(num_classes)
-
-    def _initialize_fc(self, num_classes):
-        dummy_input = torch.zeros(1, 3, 448, 448)
-        x = self.pool(self.relu(self.conv1(dummy_input)))
-        x = self.pool(self.relu(self.conv2(x)))
-        x = self.pool(self.relu(self.conv3(x)))
-        flattened_size = x.view(x.size(0), -1).shape[1]
-        self.fc1 = nn.Linear(flattened_size, 512)
-        self.fc2 = nn.Linear(512, num_classes)
+        self.pool = nn.MaxPool2d(kernel_size=2, stride=2, padding=0)
 
     def forward(self, x):
         x = self.pool(self.relu(self.conv1(x)))
         x = self.pool(self.relu(self.conv2(x)))
         x = self.pool(self.relu(self.conv3(x)))
+        if hasattr(self, 'conv4'):
+            x = self.pool(self.relu(self.conv4(x)))
         x = x.view(x.size(0), -1)
-        x = self.dropout(self.relu(self.fc1(x)))
+        x = self.relu(self.fc1(x))
+        x = self.dropout(x)
         x = self.fc2(x)
         return x
 
-def load_model(model_name: str, device: str = 'cpu'):
-    version = model_name.split()[-1].lower()
-    filename = f"Vbai-DPA-{version}.pt"
-    
+
+def load_model(version='c', device='cpu'):
+    """
+    Loads the correct model based on version: 'f', 'c', or 'q'
+    """
+    filename = f"Vbai-2.1{version}.pt"
+
     weights_path = hf_hub_download(
         repo_id="Neurazum/Vbai-DPA-2.1",
         filename=filename,
         repo_type="model"
     )
 
-    model = SimpleCNN(num_classes=6).to(device)
+    model = SimpleCNN(model_type=version, num_classes=6).to(device)
     state = torch.load(weights_path, map_location=device)
     model.load_state_dict(state)
     model.eval()