diff --git a/model.py b/model.py
index ef7e257..153508f 100644
--- a/model.py
+++ b/model.py
@@ -4,40 +4,48 @@ class DogCatClassifier(nn.Module):
     def __init__ (self):
         super().__init__()
 
+        # 3 color (RGB) image, so tensor is of shape (B x 3 x H X W)
         self.conv1 = nn.Sequential(
-            nn.Conv2d(3, 32, 3, padding = 1),
-            nn.ReLU(inplace = True),
-            nn.MaxPool2d(2),
-            nn.BatchNorm2d(32)
+            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
+            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
         )
+        
+         # tensor size is now (B x 32 x h/2 x w/2)
 
         self.conv2 = nn.Sequential(
-            nn.Conv2d(32, 64, 3, padding = 1),
+            nn.Conv2d(32, 64, 3, padding = 1), # 32 channels to 64 ch with 3x3 kernel
             nn.ReLU(inplace = True),
-            nn.MaxPool2d(2),
-            nn.BatchNorm2d(64)
+            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)
+
         self.conv3 = nn.Sequential(
-            nn.Conv2d(64, 128, 3, padding = 1),
+            nn.Conv2d(64, 128, 3, padding = 1),  # 64 channels to 128 ch with 3x3 kernel
             nn.ReLU(inplace = True),
-            nn.MaxPool2d(2),
-            nn.BatchNorm2d(128)
+            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)
 
         self.fc1 = nn.Linear(128 * 4 * 4 , 512)# 2048, lowkey had to calculator it lol
-        self.dropout = 0.5 # tunable
-        self.fc2 = nn.Linear(512, 1)
+        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
     
     def forward(self, x):
         x = self.conv1(x)
         x = self.conv2(x)
         x = self.conv3(x)
         x = x.view(x.size(0), -1)
+        # reformats for use in linear layer
         x = self.fc1(x)
-        x = nn.functional.relu(x)
+        x = nn.functional.relu(x) # relu to add nonlinearity
         x = self.fc2(x)
-        x = nn.functional.sigmoid(x)
+        x = nn.functional.sigmoid(x) # 1 / 1 + e ^(-x)
         return x
 
 
diff --git a/test.py b/test.py
index 908c00d..4225af0 100644
--- a/test.py
+++ b/test.py
@@ -4,23 +4,21 @@ from torch.utils.data import DataLoader
 from dogs_cats_ds import DogCatDataset
 from model import DogCatClassifier
 from consts import TEST_DATA
-import torch.optim as optim
 
 def test(model: nn.Module, test_loader: DataLoader, criterion, device):
     model.eval()
     test_loss = 0
     correct = 0
     total = 0
-    with torch.no_grad():
+    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)
+            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
             out = model(img)
-            loss = criterion(out, lab)
+            loss = criterion(out, lab) # evaluate loss
             test_loss += loss.item()
-            pred = (out > 0.5).float()
-            total += lab.size(0)
-            correct += (pred == lab).sum().item()
-
+            pred = (out > 0.5).float() #same as with train, if its < 0.5 return 0 else 1 
+            total += lab.size(0) # total is increased by batch size
+            correct += (pred == lab).sum().item() # correct only += 1 if the prediction matches the label
         print(f'test loss: {test_loss / len(test_loader):.4f}, test_acc: {100*correct/total:.2f}%')
         model.train()
 
@@ -33,6 +31,6 @@ if __name__ == "__main__":
     dog_test_loader = DataLoader(dog_test_dataset, batch_size = 32, shuffle = False) # since its test, bad to shuffle
     model = DogCatClassifier()
     criterion = nn.BCELoss()
-    model.load_state_dict(torch.load('dog_cat_classifier.pth', map_location = device, weights_only = True))
+    model.load_state_dict(torch.load('dog_cat_classifier.pth', map_location = device, weights_only = True)) # loads what we trained in train.py
     test(model, dog_test_loader, criterion, device)
 
diff --git a/train.py b/train.py
index 1f0cd29..e710f50 100644
--- a/train.py
+++ b/train.py
@@ -1,33 +1,33 @@
 import torch
 import torch.nn as nn
 import torch.optim as optim
-from torch.utils.data import DataLoader, Dataset
+from torch.utils.data import DataLoader
 from consts import TRAIN_DATA
 from tqdm import tqdm
 from model import DogCatClassifier
 from dogs_cats_ds import DogCatDataset
 
 def train(model: nn.Module, train_loader: DataLoader, criterion, optimizer, device, epochs):
-    model.to(device)
-    model.train()
+    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
 
-    for epoch in tqdm(range(epochs)):
-        running_loss = 0.0
+    for epoch in tqdm(range(epochs)): # wrapper around for loop to add a nice progress bar
+        running_loss = 0.0 # start the loss, amount of cats and dogs we guess correctly, and complete samples at 0 (float 0 in case of loss since it can be a float)
         correct = 0
         total = 0
-        for i, (img, lab) in enumerate(train_loader):
-            img, lab = img.to(device), lab.to(device).float().view(-1, 1)
-            optimizer.zero_grad()
+        for i, (img, lab) in enumerate(train_loader): # for each image, label pair in the dataset 
+            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)
-            loss = criterion(out, lab)
-            loss.backward()
-            optimizer.step()
+            out = model(img) # outputs are the results of our model on the image (sigmoid)
+            loss = criterion(out, lab) # loss is difference between expected and real label from prediction
+            loss.backward() # backprop using autograd
+            optimizer.step() # update optimizer 
 
-            running_loss += loss.item()
-            pred = (out > 0.5).float()
-            total += lab.size(0)
-            correct += (pred == lab).sum().item()
+            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
+            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}%')
@@ -47,6 +47,6 @@ if __name__ == "__main__":
     print(model)
 
     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')
+    torch.save(model.state_dict(), 'dog_cat_classifier.pth') # saves model to pth file
     print('done w train, model saved')