AI417 A5 AlexNet model

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,3 @@
+---
+license: apache-2.0
+---

alexnet_weights.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac4b336b945369337fa90a3ddb7999979aad01e91ce51480c887ce9286231c5b
+size 24202694

hubconf.py

@@ -0,0 +1,11 @@
+import torch
+from model import CNNModel
+
+def AlexNet(pretrained=True):
+    model = CNNModel()
+
+    if pretrained:
+        state_dict = torch.load("alexnet_weights.pth", map_location="cpu")
+        model.load_state_dict(state_dict)
+
+    return model

model.py

@@ -0,0 +1,51 @@
+import torch
+import torch.nn as nn
+import torch.optim as optim
+
+class CNNModel(nn.Module):
+
+    def __init__(self):
+        super(CNNModel, self).__init__()
+        self.conv1 = nn.Conv2d(3, 64, kernel_size=5, padding=2)
+        self.relu1 = nn.ReLU()
+        self.pool1 = nn.MaxPool2d(kernel_size=2, stride=2)
+        self.conv2 = nn.Conv2d(64, 128, kernel_size=5, padding=2)
+        self.relu2 = nn.ReLU()
+        self.pool2 = nn.MaxPool2d(kernel_size=2, stride=2)
+        self.conv3 = nn.Conv2d(128, 256, kernel_size=3, padding=1)
+        self.relu3 = nn.ReLU()
+        self.pool3 = nn.MaxPool2d(kernel_size=2, stride=2)
+        self.conv4 = nn.Conv2d(256, 384, kernel_size=5, padding=1)
+        self.relu4 = nn.ReLU()
+        self.conv5 = nn.Conv2d(384, 256, kernel_size=1, padding=0)
+        self.relu5 = nn.ReLU()
+        self.avgpool = nn.AdaptiveAvgPool2d((3, 3))
+        self.flatten = nn.Flatten()
+        self.dropout1 = nn.Dropout(p=0.1)
+        self.fc1 = nn.Linear(256 * 3 * 3, 1024)
+        self.relu6 = nn.ReLU()
+        self.dropout2 = nn.Dropout(p=0.1)
+        self.fc2 = nn.Linear(1024, 512)
+        self.relu7 = nn.ReLU()
+        self.fc3 = nn.Linear(512, 200)
+        self.softmax = nn.Softmax(dim=1)
+
+    def forward(self, x):
+        x = self.pool1(self.relu1(self.conv1(x)))
+        x = self.pool2(self.relu2(self.conv2(x)))
+        x = self.pool3(self.relu3(self.conv3(x)))
+        x = self.relu4(self.conv4(x))
+        x = self.relu5(self.conv5(x))
+        x = self.avgpool(x)
+        x = self.flatten(x)
+        x = self.dropout1(x)
+        x = self.relu6(self.fc1(x))
+        x = self.dropout2(x)
+        x = self.relu7(self.fc2(x))
+        x = self.fc3(x)
+        x = self.softmax(x)
+        return x
+        
+model = CNNModel()
+loss_fn = nn.NLLLoss()
+optimizer = optim.Adam(model.parameters(), lr=0.0003)

train.py

@@ -0,0 +1,74 @@
+import time
+import torch as tr
+import torchvision as tv
+import torchvision.transforms as transforms
+from model import model, loss_fn, optimizer
+
+def main():
+    batch_size = 128
+    epochs = 10
+    transform = transforms.Compose([
+        transforms.Resize((64, 64)),
+        transforms.ToTensor()])
+    
+    trn_dataset = tv.datasets.ImageFolder(
+        root='data/tiny-imagenet-200/train',
+        transform=transform)
+    
+    evl_dataset = tv.datasets.ImageFolder(
+        root='data/tiny-imagenet-200/val',
+        transform=transform)
+    
+    trn_loader = tr.utils.data.DataLoader(
+        trn_dataset,
+        batch_size=batch_size,
+        shuffle=True,
+        num_workers=8,
+        pin_memory=True)
+    
+    evl_loader = tr.utils.data.DataLoader(
+        evl_dataset,
+        batch_size=batch_size,
+        shuffle=False,
+        num_workers=8,
+        pin_memory=True)
+    
+    device = tr.device("cuda" if tr.cuda.is_available() else "cpu")
+    model.to(device)
+    print("Running on:", device)
+    start_time = time.time()
+    for epoch in range(1, epochs + 1):
+        model.train()
+        for images, labels in trn_loader:
+            images = images.to(device)
+            labels = labels.to(device)
+            optimizer.zero_grad()
+            output = model(images)
+            loss = loss_fn(tr.log(tr.clamp(output, min=1e-9)), labels)
+            loss.backward()
+            optimizer.step()
+        model.eval()
+        correct = 0
+        total = 0
+
+        with tr.no_grad():
+            for images, labels in evl_loader:
+                images = images.to(device)
+                labels = labels.to(device)
+                output = model(images)
+                preds = tr.argmax(output, dim=1)
+                correct += tr.sum(preds == labels).item()
+                total += labels.size(0)
+        accuracy = correct / total
+        print(f"Epoch {epoch}/{epochs} - Loss: {loss.item():.4f} - Accuracy: {accuracy*100:.2f}%")
+
+    end_time = time.time()
+
+    print("Training finished")
+    print(f"Final Loss: {loss.item():.4f}")
+    print(f"Final Accuracy: {accuracy*100:.2f}%")
+    print(f"Total Time: {end_time - start_time:.2f} seconds")
+
+
+if __name__ == "__main__":
+    main()