Adding comments and updates to pytorch :)

01_basics.py

@@ -15,22 +15,29 @@ def loss(x, y):
     y_pred = forward(x)
     return (y_pred - y) * (y_pred - y)
 
-
+# List of weights/Mean square Error (Mse) for each input
 w_list = []
 mse_list = []
 
 for w in np.arange(0.0, 4.1, 0.1):
+    # Print the weights and initialize the lost
     print("w=", w)
     l_sum = 0
+
     for x_val, y_val in zip(x_data, y_data):
+        # For each input and output, calculate y_hat
+        # Compute the total loss and add to the total error
         y_pred_val = forward(x_val)
         l = loss(x_val, y_val)
         l_sum += l
         print("\t", x_val, y_val, y_pred_val, l)
+    # Now compute the Mean squared error (mse) of each
+    # Aggregate the weight/mse from this run
     print("MSE=", l_sum / 3)
     w_list.append(w)
     mse_list.append(l_sum / 3)
 
+# Plot it all
 plt.plot(w_list, mse_list)
 plt.ylabel('Loss')
 plt.xlabel('w')

02_manual_gradient.py

@@ -1,11 +1,11 @@
+# Training Data
 x_data = [1.0, 2.0, 3.0]
 y_data = [2.0, 4.0, 6.0]
 
 w = 1.0  # a random guess: random value
 
-# our model forward pass
-
 
+# our model forward pass
 def forward(x):
     return x * w
 
@@ -20,18 +20,21 @@ def loss(x, y):
 def gradient(x, y):  # d_loss/d_w
     return 2 * x * (x * w - y)
 
+
 # Before training
-print("predict (before training)",  4, forward(4))
+print("Prediction (before training)",  4, forward(4))
 
 # Training loop
 for epoch in range(10):
     for x_val, y_val in zip(x_data, y_data):
+        # Compute derivative w.r.t to the learned weights
+        # Update the weights
+        # Compute the loss and print progress
         grad = gradient(x_val, y_val)
         w = w - 0.01 * grad
         print("\tgrad: ", x_val, y_val, round(grad, 2))
         l = loss(x_val, y_val)
-
     print("progress:", epoch, "w=", round(w, 2), "loss=", round(l, 2))
 
 # After training
-print("predict (after training)",  "4 hours", forward(4))
+print("Predicted score (after training)",  "4 hours of studying: ", forward(4))

03_auto_gradient.py

@@ -1,39 +1,34 @@
 import torch
-from torch.autograd import Variable
+import pdb
 
 x_data = [1.0, 2.0, 3.0]
 y_data = [2.0, 4.0, 6.0]
-
-w = Variable(torch.Tensor([1.0]),  requires_grad=True)  # Any random value
+w = torch.tensor([1.0], requires_grad=True)
 
 # our model forward pass
-
-
 def forward(x):
     return x * w
 
 # Loss function
-
-
-def loss(x, y):
-    y_pred = forward(x)
-    return (y_pred - y) * (y_pred - y)
+def loss(y_pred, y_val):
+    return (y_pred - y_val) ** 2
 
 # Before training
-print("predict (before training)",  4, forward(4).data[0])
+print("Prediction (before training)",  4, forward(4).item())
 
 # Training loop
 for epoch in range(10):
     for x_val, y_val in zip(x_data, y_data):
-        l = loss(x_val, y_val)
-        l.backward()
-        print("\tgrad: ", x_val, y_val, w.grad.data[0])
-        w.data = w.data - 0.01 * w.grad.data
+        y_pred = forward(x_val) # 1) Forward pass
+        l = loss(y_pred, y_val) # 2) Compute loss
+        l.backward() # 3) Back propagation to update weights
+        print("\tgrad: ", x_val, y_val, w.grad.item())
+        w.data = w.data - 0.01 * w.grad.item()
 
         # Manually zero the gradients after updating weights
         w.grad.data.zero_()
 
-    print("progress:", epoch, l.data[0])
+    print(f"Epoch: {epoch} | Loss: {l.item()}")
 
 # After training
-print("predict (after training)",  4, forward(4).data[0])
+print("Prediction (after training)",  4, forward(4).item())