need to do test then we done

dogs_cats_ds.py

@@ -1,6 +1,6 @@
 from torch.utils.data import Dataset
 class DogCatDataset(Dataset):
-    def __init__(self, ds, dog=[5], cat = [3]):
+    def __init__(self, ds:Dataset, dog=[5], cat = [3]):
         self.ds = ds
         self.idx = []
         for i in range(len(ds)):

model.py

@@ -5,50 +5,36 @@ class DogCatClassifier(nn.Module):
         super().__init__()
 
         # 3 color (RGB) image, so tensor is of shape (B x 3 x H X W)
-        self.conv1 = nn.Sequential(
+        # if we take a look, we can see that the images are of size 32 * 32 if we look at them in a file explorer, so our H and W are 32 in this case
-            nn.Conv2d(3, 32, 3, padding = 1), # passes conv kernel over batch and increases num channels from 3 (for RBG) to 32
+        self.conv1 = nn.Conv2d(3, 32, 3, padding = 1) # passes conv kernel over batch and increases num channels from 3 (for RBG) to 32
-            nn.ReLU(inplace = True), # relu to add nonlinearity
+        self.relu = nn.ReLU(inplace = True) # relu to add nonlinearity
-            nn.MaxPool2d(2), # reduces h and w of img by a factor of 2
+        self.mp = nn.MaxPool2d(2) # reduces h and w of img by a factor of 2
-            nn.BatchNorm2d(32) #normalizes over z distribution https://arxiv.org/abs/1502.03167
+        self.bn1 = nn.BatchNorm2d(32) #normalizes over z distribution https://arxiv.org/abs/1502.03167
-        )
         
-         # tensor size is now (B x 32 x h/2 x w/2)
+         # tensor size is now (B x 32 x 32/2 = 16 x 32/2 = 16)
 
-        self.conv2 = nn.Sequential(
+        self.conv2 = nn.Conv2d(32, 64, 3, padding = 1) # 32 channels to 64 ch with 3x3 kernel
-            nn.Conv2d(32, 64, 3, padding = 1), # 32 channels to 64 ch with 3x3 kernel
+        self.bn2 = nn.BatchNorm2d(64) #normalizes over z distribution https://arxiv.org/abs/1502.03167
-            nn.ReLU(inplace = True),
-            nn.MaxPool2d(2), # reduces # reduces h and w of img by a factor of 2
-            nn.BatchNorm2d(64) #normalizes over z distribution https://arxiv.org/abs/1502.03167
-        )
 
-         # tensor size is now (B x 64 x h/4 x w/4)
+         # tensor size is now (B x 64 x 32/4 = 8 x 32/4 = 8)
 
-        self.conv3 = nn.Sequential(
+        self.conv3 = nn.Conv2d(64, 128, 3, padding = 1)  # 64 channels to 128 ch with 3x3 kernelnn
-            nn.Conv2d(64, 128, 3, padding = 1),  # 64 channels to 128 ch with 3x3 kernel
+        self.bn3= nn.BatchNorm2d(128)  # normalizes over z distribution https://arxiv.org/abs/1502.03167
-            nn.ReLU(inplace = True),
-            nn.MaxPool2d(2),  # reduces # reduces h and w of img by a factor of 2
-            nn.BatchNorm2d(128)  # normalizes over z distribution https://arxiv.org/abs/1502.03167
-        )
          
-        # tensor size is now (B x 128 x h/8 x w/8)
+        # tensor size is now (B x 128 x 32/8 = 4 x 32/8 = 4)
-
+        # basically, we have B batches, 128 channels, and a 4x4 pixel representation of our initial image
-        self.fc1 = nn.Linear(128 * 4 * 4 , 512)# 2048, lowkey had to calculator it lol
+        self.fc1 = nn.Linear(128 * 4 * 4 , 512)# 2048 feats (ch x h x w), lowkey had to calculator it lol
         self.dropout = 0.5 # tunable, removes half of the values and replaces them with 0s
-        self.fc2 = nn.Linear(512, 1) # 512 ch to 1 ch output
+        self.fc2 = nn.Linear(512, 1) # 512 feats  to 1 scalar output
   
     def forward(self, x):
-        x = self.conv1(x)
+        x = self.bn1(self.mp(self.relu(self.conv1(x))))
-        x = self.conv2(x)
+        x = self.bn2(self.mp(self.relu(self.conv2(x))))
-        x = self.conv3(x)
+        x = self.bn3(self.mp(self.relu(self.conv3(x))))
-        x = x.view(x.size(0), -1)
+        x = x.view(x.size(0), -1) # see model_ez for why we do this before linear layers
         # reformats for use in linear layer
         x = self.fc1(x)
         x = nn.functional.relu(x) # relu to add nonlinearity
         x = self.fc2(x)
         x = nn.functional.sigmoid(x) # 1 / 1 + e ^(-x)
         return x
-
-
-
-
-

test.py

@@ -5,11 +5,31 @@ from dogs_cats_ds import DogCatDataset
 from model import DogCatClassifier
 from consts import TEST_DATA
 
-def test(model: nn.Module, test_loader: DataLoader, criterion, device):
+
+def test(model: nn.Module, test_images: torch.Tensor, test_labels: torch.Tensor, criterion):
     model.eval()
     test_loss = 0
     correct = 0
     total = 0
+    with torch.no_grad():
+        for img in test_images:
+            for label in test_labels:
+                out = model(img)
+                loss = criterion(label)
+                test_loss += loss.item()
+                pred = (out <= 0.5).float()
+                total += label.size(0)
+                correct += (pred == lab).sum().item()
+
+
+
+
+
+def test(model: nn.Module, test_loader: DataLoader, criterion, device):
+    model.eval() # this mode will disable the backward funcitonality for all tensors, and only perform the fwd pass
+    test_loss = 0
+    correct = 0
+    total = 0
     with torch.no_grad(): # do not update gradients
         for img, lab in test_loader:
             img, lab = img.to(device), lab.to(device).float().view(-1, 1) # similar to how we did it in train, offset both to a gpu for better perf
@@ -32,5 +52,6 @@ if __name__ == "__main__":
     model = DogCatClassifier()
     criterion = nn.BCELoss()
     model.load_state_dict(torch.load('dog_cat_classifier.pth', map_location = device, weights_only = True)) # loads what we trained in train.py
+    print(model)
     test(model, dog_test_loader, criterion, device)
 

train.py

@@ -2,11 +2,37 @@ import torch
 import torch.nn as nn
 import torch.optim as optim
 from torch.utils.data import DataLoader
+from torch.utils.data.dataset import Dataset
 from consts import TRAIN_DATA
 from tqdm import tqdm
 from model import DogCatClassifier
 from dogs_cats_ds import DogCatDataset
 
+
+
+# def train_sgd(model: nn.Module,
+#               imgs: torch.Tensor,
+#               labels: torch.Tensor,
+#               batch_size: int,
+#               criterion: nn.Module,
+#               optimizer: optim.Optimizer):
+#     losses: list = []
+#     shuffle: torch.Tensor = torch.randperm(imgs.size(0))
+#     images_shuffled: torch.Tensor = imgs[shuffle]
+#     labels_shuffled: torch.Tensor = labels[shuffle]
+#     for i in range(0, imgs.size(0), batch_size):
+#         batched_images: torch.Tensor = images_shuffled[i:i+batch_size]
+#         batched_labels: torch.Tensor = labels_shuffled[i:i+batch_size]
+#         outputs = model(batched_images)
+#         loss = criterion(outputs, batched_labels)
+#         loss.backward()
+#         optimizer.step()
+#
+#         losses.append(loss.item())
+#     return losses
+
+
+
 def train(model: nn.Module, train_loader: DataLoader, criterion, optimizer, device, epochs):
     model.to(device) # send to gpu if there is one, otherwise toss it over to cpu 
     model.train() #train mode means that all gradients are active and modifiable
@@ -19,18 +45,27 @@ def train(model: nn.Module, train_loader: DataLoader, criterion, optimizer, devi
             img, lab = img.to(device), lab.to(device).float().view(-1, 1) # send the image and label to the gpu if there is one else send to cpu, .view(-1, 1) returns the same tensor data but with the shape of the last dimension
             optimizer.zero_grad() # resets gradients to zero when we initialize.
 
-            out = model(img) # outputs are the results of our model on the image (sigmoid)
+            # get a prediction here
-            loss = criterion(out, lab) # loss is difference between expected and real label from prediction
+                    #
-            loss.backward() # backprop using autograd
+            # calculate the loss here
+                    
+            # perform backpropogation here
+            
+                  
+            #
             optimizer.step() # update optimizer 
 
             running_loss += loss.item() # loss in epoch updated with loss
-            pred = (out > 0.5).float() # prediction is 0 if less than 0.5 else 1
+            #calculate accuracy
-            total += lab.size(0) #total samples is increased by the 0th dim of the tensor(batch size)
-            correct += (pred == lab).sum().item() # only add 1 to the correct count if the actual label (dog) = the predicted label(dog)
 
-            if (i + 1) % 50:
+
-                print(f'yo its epoch {epoch + 1} out of {epochs} and we on minibatch {i + 1} / {len(train_loader)}. Loss lookin like: {running_loss/100:.4f}, acc lookin like {100 * correct / total :.2f}%')
+            #hint: what kind of values is the accuracy outputing? What kind of values do we want?
+            
+            total += lab.size(0) #total samples is increased by the 0th dim of the tensor(batch size)
+            # only add 1 to the correct count if the actual label (dog) = the predicted label(dog)
+
+            if (i + 1) % 50 == 0:
+                print(f'yo its epoch {epoch + 1} out of {epochs} and we on minibatch {i + 1} / {len(train_loader)}. Loss lookin like: {running_loss/(i+1):.4f}, acc lookin like {100 * correct / total :.2f}%')
                 running_loss = 0.0
                 total = 0
                 correct = 0
@@ -39,14 +74,16 @@ def train(model: nn.Module, train_loader: DataLoader, criterion, optimizer, devi
 if __name__ == "__main__":
     device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
     print(f'Using device: {device}')
+
     dog_train_dataset = DogCatDataset(TRAIN_DATA)
     dog_train_loader = DataLoader(dog_train_dataset, batch_size = 32, shuffle = True) # since its train, ok to shuffle
-    model = DogCatClassifier()
+
-    criterion = nn.BCELoss()
+    model = DogCatClassifier() # black box for now
-    optimizer = optim.Adam(model.parameters(), lr = 0.001)
+    criterion = nn.BCELoss() # cross entropy loss, feel free to experiment with others
-    print(model)
+    optimizer = optim.Adam(model.parameters(), lr = 0.001) # feel free to mess around with other optimizers as well
 
     train(model = model, train_loader = dog_train_loader, criterion = criterion, optimizer = optimizer, device = device, epochs = 10)
-    torch.save(model.state_dict(), 'dog_cat_classifier.pth') # saves model to pth file
+    torch.save(model.state_dict(), 'dog_cat_classifier.pth') # saves model to pth file, which can be read by pytorch
     print('done w train, model saved')
 
+