feat: Add missing BEGIN/END SOLUTION markers to NBGrader modules

- Add solution markers to 01_tensor module properties (data, shape, size, dtype)
- Add solution markers to 04_networks Sequential.forward method
- Add solution markers to 05_cnn module (conv2d_naive, Conv2D.__init__, Conv2D.forward, flatten)
- Add solution markers to 06_dataloader Dataset class methods (__getitem__, __len__, get_sample_shape)
- Verify existing solution markers in 02_activations (4 pairs), 03_layers (3 pairs), 07_autograd (4 pairs), 00_setup (2 pairs)

Critical for NBGrader functionality:
- BEGIN/END SOLUTION markers identify instructor solutions to hide from students
- Enables proper assignment generation and solution hiding
- Ensures seamless integration with NBGrader grading system
- Maintains pedagogical separation between student TODOs and instructor solutions

modules/source/01_tensor/tensor_dev.py

@@ -317,7 +317,9 @@ print(t.dtype)  # int32 - data type
         - Users can access the numpy array directly via this property
         - This is how PyTorch's .data property works
         """
+        ### BEGIN SOLUTION
         return self._data
+        ### END SOLUTION
 
     @property
     def shape(self) -> Tuple[int, ...]:
@@ -346,7 +348,9 @@ print(t.dtype)  # int32 - data type
         - Shape is a tuple of integers
         - Essential for checking tensor compatibility
         """
+        ### BEGIN SOLUTION
         return self._data.shape
+        ### END SOLUTION
 
     @property
     def size(self) -> int:
@@ -375,7 +379,9 @@ print(t.dtype)  # int32 - data type
         - Size is the product of all dimensions
         - Important for memory calculations
         """
+        ### BEGIN SOLUTION
         return self._data.size
+        ### END SOLUTION
 
     @property
     def dtype(self) -> np.dtype:
@@ -405,7 +411,9 @@ print(t.dtype)  # int32 - data type
         - Important for precision and memory usage
         - Affects computation speed and accuracy
         """
+        ### BEGIN SOLUTION
         return self._data.dtype
+        ### END SOLUTION
 
     def __repr__(self) -> str:
         """

modules/source/04_networks/networks_dev.py

@@ -251,10 +251,12 @@ class Sequential:
         - The output of one layer becomes input to the next
         - Return the final result
         """
+        ### BEGIN SOLUTION
         # Apply each layer in sequence
         for layer in self.layers:
             x = layer(x)
         return x
+        ### END SOLUTION
     
     def __call__(self, x: Tensor) -> Tensor:
         """Make network callable: network(x) same as network.forward(x)"""

modules/source/05_cnn/cnn_dev.py

@@ -184,6 +184,7 @@ def conv2d_naive(input: np.ndarray, kernel: np.ndarray) -> np.ndarray:
     - Use four nested loops: for i in range(out_H): for j in range(out_W): for di in range(kH): for dj in range(kW):
     - Accumulate the sum: output[i,j] += input[i+di, j+dj] * kernel[di, dj]
     """
+    ### BEGIN SOLUTION
     # Get input and kernel dimensions
     H, W = input.shape
     kH, kW = kernel.shape
@@ -202,6 +203,7 @@ def conv2d_naive(input: np.ndarray, kernel: np.ndarray) -> np.ndarray:
                     output[i, j] += input[i + di, j + dj] * kernel[di, dj]
     
     return output
+    ### END SOLUTION
 
 # %% [markdown]
 """
@@ -334,12 +336,14 @@ class Conv2D:
         - Initialize kernel: np.random.randn(kH, kW) * 0.1 (small values)
         - Convert to float32 for consistency
         """
+        ### BEGIN SOLUTION
         # Store kernel size
         self.kernel_size = kernel_size
         kH, kW = kernel_size
         
         # Initialize random kernel with small values
         self.kernel = np.random.randn(kH, kW).astype(np.float32) * 0.1
+        ### END SOLUTION
     
     def forward(self, x: Tensor) -> Tensor:
         """
@@ -368,9 +372,11 @@ class Conv2D:
         - Use conv2d_naive(x.data, self.kernel)
         - Return Tensor(result) to wrap the result
         """
+        ### BEGIN SOLUTION
         # Apply convolution using naive implementation
         result = conv2d_naive(x.data, self.kernel)
         return Tensor(result)
+        ### END SOLUTION
     
     def __call__(self, x: Tensor) -> Tensor:
         """Make layer callable: layer(x) same as layer.forward(x)"""
@@ -490,10 +496,12 @@ def flatten(x: Tensor) -> Tensor:
     - Add batch dimension: result[None, :]
     - Return Tensor(result)
     """
+    ### BEGIN SOLUTION
     # Flatten the tensor and add batch dimension
     flattened = x.data.flatten()
     result = flattened[None, :]  # Add batch dimension
     return Tensor(result)
+    ### END SOLUTION
 
 # %% [markdown]
 """

modules/source/06_dataloader/dataloader_dev.py

@@ -209,8 +209,10 @@ class Dataset:
         - Always return a tuple of (data, label) tensors
         - Data contains the input features, label contains the target
         """
+        ### BEGIN SOLUTION
         # This is an abstract method - subclasses must implement it
         raise NotImplementedError("Subclasses must implement __getitem__")
+        ### END SOLUTION
     
     def __len__(self) -> int:
         """
@@ -229,8 +231,10 @@ class Dataset:
         - This is an abstract method that subclasses must override
         - Return an integer representing the total number of samples
         """
+        ### BEGIN SOLUTION
         # This is an abstract method - subclasses must implement it
         raise NotImplementedError("Subclasses must implement __len__")
+        ### END SOLUTION
     
     def get_sample_shape(self) -> Tuple[int, ...]:
         """
@@ -251,9 +255,11 @@ class Dataset:
         - Extract data from the (data, label) tuple
         - Return data.shape
         """
+        ### BEGIN SOLUTION
         # Get the first sample to determine shape
         data, _ = self[0]
         return data.shape
+        ### END SOLUTION
     
     def get_num_classes(self) -> int:
         """