No success with adjusting CNN, set up VGG-16

.~lock.2024 - ECE new poster presentation template - landscape.pptx#

@@ -0,0 +1 @@
+,sharpe,dhcp-150-250-221-61,25.04.2024 11:36,file:///home/sharpe/.var/app/org.libreoffice.LibreOffice/config/libreoffice/4;

Filter_Analysis/cifar10.py

@@ -11,46 +11,62 @@ import torch.nn as nn
 import torch.nn.functional as F
 
 #import dla
+import vgg
 
 
 
-EPOCHS = 200
+EPOCHS = 40
+
+class CnnBlock(nn.Module):
+    def __init__(self, in_channels=3, out_channels=16):
+        super(CnnBlock, self).__init__()
+        self.conv1 = nn.Conv2d(in_channels, 2*in_channels, 3, 1)
+        self.conv2 = nn.Conv2d(2*in_channels, out_channels, 3, 1)
+        self.bn1 = nn.BatchNorm2d(2*in_channels)
+        self.bn2 = nn.BatchNorm2d(out_channels)
+
+    def forward(self, x):
+        x = self.conv1(x)
+        x = self.bn1(x)
+        x = F.relu(x)
+        x = self.conv2(x)
+        x = self.bn2(x)
+        x = F.relu(x)
+        return x
 
 class CifarCNN(nn.Module):
     def __init__(self):
         super(CifarCNN, self).__init__()
-        self.conv1 = nn.Conv2d(3, 96, 3, 1)
-        self.conv2 = nn.Conv2d(96, 192, 3, 1)
+        self.block1 = CnnBlock(3, 16)
+        self.block2 = CnnBlock(16, 64)
+        self.block3 = CnnBlock(64, 128)
         self.dropout1 = nn.Dropout(0.25)
         self.dropout2 = nn.Dropout(0.5)
-        self.fc1 = nn.Linear(37632, 128)
-        self.fc2 = nn.Linear(128, 10)
+        self.fc1 = nn.Linear(128, 10)
 
     def forward(self, x):
-        x = self.conv1(x)
-        x = F.relu(x)
-        x = self.conv2(x)
-        x = F.relu(x)
-        x = F.max_pool2d(x,2)
+        x = self.block1(x)
         x = self.dropout1(x)
+        x = F.max_pool2d(x,2)
+        x = self.block2(x)
+        x = F.max_pool2d(x,2)
+        x = self.dropout2(x)
+        x = self.block3(x)
         x = torch.flatten(x,1)
         x = self.fc1(x)
-        x = F.relu(x)
-        x = self.dropout2(x)
-        x = self.fc2(x)
         output = F.log_softmax(x, dim=1)
         return output
 
-def train(model, trainloader, optimizer, epoch):
+def train(model, trainloader, device, optimizer, criterion, epoch):
         running_loss = 0.0
         for i, [data, target] in enumerate(trainloader, 0):
-
+            data, target = data.to(device), target.to(device)
             # zero the parameter gradients
             optimizer.zero_grad()
 
             # forward + backward + optimize
             output = model(data)
-            loss = F.nll_loss(output, target)
+            loss = criterion(output, target)
             loss.backward()
             optimizer.step()
 
@@ -61,13 +77,14 @@ def train(model, trainloader, optimizer, epoch):
                 running_loss = 0.0
 
 
-def test(model, testloader, classes):
+def test(model, testloader, device, classes):
     correct = 0
     total = 0
 
     # since we're not training, we don't need to calculate the gradients for our outputs
     with torch.no_grad():
         for data, target in testloader:
+            data, target = data.to(device), target.to(device)
             # calculate outputs by running images through the network
             output = model(data)
             # the class with the highest energy is what we choose as prediction
@@ -85,6 +102,7 @@ def test(model, testloader, classes):
     # again no gradients needed
     with torch.no_grad():
         for data, target in testloader:
+            data, target = data.to(device), target.to(device)
             output = model(data)
             _, predictions = torch.max(output, 1)
             # collect the correct predictions for each class
@@ -121,15 +139,16 @@ def main():
                'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
 
     device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
-    model = CifarCNN().to(device)
+    model = vgg.VGG('VGG16').to(device)
 
-    optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9)
+    optimizer = optim.SGD(model.parameters(), lr=0.0001, momentum=0.9)
+    criterion = nn.CrossEntropyLoss()
 
     for epoch in range(EPOCHS):
-        train(model, trainloader, optimizer, epoch)
-        test(model, testloader, classes)
+        train(model, trainloader, device, optimizer, criterion, epoch)
+        test(model, testloader, device, classes)
 
-    PATH = './cifar_cnn.pth'
+    PATH = './cifar_vgg.pth'
     torch.save(model.state_dict(), PATH)
 
 

Filter_Analysis/vgg.py

@@ -0,0 +1,47 @@
+'''VGG11/13/16/19 in Pytorch.'''
+import torch
+import torch.nn as nn
+
+
+cfg = {
+    'VGG11': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
+    'VGG13': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
+    'VGG16': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
+    'VGG19': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'M'],
+}
+
+
+class VGG(nn.Module):
+    def __init__(self, vgg_name):
+        super(VGG, self).__init__()
+        self.features = self._make_layers(cfg[vgg_name])
+        self.classifier = nn.Linear(512, 10)
+
+    def forward(self, x):
+        out = self.features(x)
+        out = out.view(out.size(0), -1)
+        out = self.classifier(out)
+        return out
+
+    def _make_layers(self, cfg):
+        layers = []
+        in_channels = 3
+        for x in cfg:
+            if x == 'M':
+                layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
+            else:
+                layers += [nn.Conv2d(in_channels, x, kernel_size=3, padding=1),
+                           nn.BatchNorm2d(x),
+                           nn.ReLU(inplace=True)]
+                in_channels = x
+        layers += [nn.AvgPool2d(kernel_size=1, stride=1)]
+        return nn.Sequential(*layers)
+
+
+def test():
+    net = VGG('VGG11')
+    x = torch.randn(2,3,32,32)
+    y = net(x)
+    print(y.size())
+
+# test()