switched wrong file names for 06_1 and 06_2

Author: patrickloeber

06_1_loss_and_optimizer.py

@@ -13,49 +13,31 @@
 
 # here : f = 2 * x
 
-# 0) Training samples, watch the shape!
-X = torch.tensor([[1], [2], [3], [4]], dtype=torch.float32)
-Y = torch.tensor([[2], [4], [6], [8]], dtype=torch.float32)
-
-n_samples, n_features = X.shape
-print(f'#samples: {n_samples}, #features: {n_features}')
-# 0) create a test sample
-X_test = torch.tensor([5], dtype=torch.float32)
-
-# 1) Design Model, the model has to implement the forward pass!
-# Here we can use a built-in model from PyTorch
-input_size = n_features
-output_size = n_features
-
-# we can call this model with samples X
-model = nn.Linear(input_size, output_size)
-
-'''
-class LinearRegression(nn.Module):
-    def __init__(self, input_dim, output_dim):
-        super(LinearRegression, self).__init__()
-        # define diferent layers
-        self.lin = nn.Linear(input_dim, output_dim)
-    
-    def forward(self, x):
-        return self.lin(x)
-
-model = LinearRegression(input_size, output_size)
-'''
-
-print(f'Prediction before training: f(5) = {model(X_test).item():.3f}')
+# 0) Training samples
+X = torch.tensor([1, 2, 3, 4], dtype=torch.float32)
+Y = torch.tensor([2, 4, 6, 8], dtype=torch.float32)
+
+# 1) Design Model: Weights to optimize and forward function
+w = torch.tensor(0.0, dtype=torch.float32, requires_grad=True)
+
+def forward(x):
+    return w * x
+
+print(f'Prediction before training: f(5) = {forward(5).item():.3f}')
 
 # 2) Define loss and optimizer
 learning_rate = 0.01
 n_iters = 100
 
+# callable function
 loss = nn.MSELoss()
-optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)
+
+optimizer = torch.optim.SGD([w], lr=learning_rate)
 
 # 3) Training loop
 for epoch in range(n_iters):
-    # predict = forward pass with our model
-    y_predicted = model(X)
+    # predict = forward pass
+    y_predicted = forward(X)
 
     # loss
     l = loss(Y, y_predicted)
@@ -70,7 +52,6 @@ def forward(self, x):
     optimizer.zero_grad()
 
     if epoch % 10 == 0:
-        [w, b] = model.parameters() # unpack parameters
-        print('epoch ', epoch+1, ': w = ', w[0][0].item(), ' loss = ', l)
+        print('epoch ', epoch+1, ': w = ', w, ' loss = ', l)
 
-print(f'Prediction after training: f(5) = {model(X_test).item():.3f}')
+print(f'Prediction after training: f(5) = {forward(5).item():.3f}')

06_2_model_loss_and_ optimizer.py

@@ -13,31 +13,49 @@
 
 # here : f = 2 * x
 
-# 0) Training samples
-X = torch.tensor([1, 2, 3, 4], dtype=torch.float32)
-Y = torch.tensor([2, 4, 6, 8], dtype=torch.float32)
+# 0) Training samples, watch the shape!
+X = torch.tensor([[1], [2], [3], [4]], dtype=torch.float32)
+Y = torch.tensor([[2], [4], [6], [8]], dtype=torch.float32)
 
-# 1) Design Model: Weights to optimize and forward function
-w = torch.tensor(0.0, dtype=torch.float32, requires_grad=True)
+n_samples, n_features = X.shape
+print(f'#samples: {n_samples}, #features: {n_features}')
+# 0) create a test sample
+X_test = torch.tensor([5], dtype=torch.float32)
 
-def forward(x):
-    return w * x
+# 1) Design Model, the model has to implement the forward pass!
+# Here we can use a built-in model from PyTorch
+input_size = n_features
+output_size = n_features
 
-print(f'Prediction before training: f(5) = {forward(5).item():.3f}')
+# we can call this model with samples X
+model = nn.Linear(input_size, output_size)
+
+'''
+class LinearRegression(nn.Module):
+    def __init__(self, input_dim, output_dim):
+        super(LinearRegression, self).__init__()
+        # define diferent layers
+        self.lin = nn.Linear(input_dim, output_dim)
+
+    def forward(self, x):
+        return self.lin(x)
+
+model = LinearRegression(input_size, output_size)
+'''
+
+print(f'Prediction before training: f(5) = {model(X_test).item():.3f}')
 
 # 2) Define loss and optimizer
 learning_rate = 0.01
 n_iters = 100
 
-# callable function
 loss = nn.MSELoss()
-
-optimizer = torch.optim.SGD([w], lr=learning_rate)
+optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)
 
 # 3) Training loop
 for epoch in range(n_iters):
-    # predict = forward pass
-    y_predicted = forward(X)
+    # predict = forward pass with our model
+    y_predicted = model(X)
 
     # loss
     l = loss(Y, y_predicted)
@@ -52,6 +70,7 @@ def forward(x):
     optimizer.zero_grad()
 
     if epoch % 10 == 0:
-        print('epoch ', epoch+1, ': w = ', w, ' loss = ', l)
+        [w, b] = model.parameters() # unpack parameters
+        print('epoch ', epoch+1, ': w = ', w[0][0].item(), ' loss = ', l)
 
-print(f'Prediction after training: f(5) = {forward(5).item():.3f}')
+print(f'Prediction after training: f(5) = {model(X_test).item():.3f}')