From 34b6999e398da24a802de5176f57b067494edfd5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Joseph=20Hopfm=C3=BCller?= <hopfmuel@hm.edu>
Date: Mon, 17 Oct 2022 00:21:56 +0200
Subject: [PATCH] finished chapter 5

---
 04_backpropagation.py              | 19 ++++++++++++
 05_01_gradient.py                  | 48 ++++++++++++++++++++++++++++++
 05_02_gradient_autograd.py         | 46 ++++++++++++++++++++++++++++
 06_01_gradient_torch_loss_optim.py |  0
 06_02_gradient_torch_model.py      |  0
 5 files changed, 113 insertions(+)
 create mode 100644 05_01_gradient.py
 create mode 100644 05_02_gradient_autograd.py
 create mode 100644 06_01_gradient_torch_loss_optim.py
 create mode 100644 06_02_gradient_torch_model.py

diff --git a/04_backpropagation.py b/04_backpropagation.py
index e69de29..075b7f4 100644
--- a/04_backpropagation.py
+++ b/04_backpropagation.py
@@ -0,0 +1,19 @@
+import torch
+
+x = torch.tensor(1.0)
+y = torch.tensor(2.0)
+
+w = torch.tensor(1.0, requires_grad=True)
+
+#forward path and compute loss
+y_hat = w*x
+loss = (y_hat-y)**2
+
+print(loss)
+
+#backward path
+loss.backward()
+print(w.grad)
+
+### update weights
+### next forward and backwards
\ No newline at end of file
diff --git a/05_01_gradient.py b/05_01_gradient.py
new file mode 100644
index 0000000..cd722be
--- /dev/null
+++ b/05_01_gradient.py
@@ -0,0 +1,48 @@
+import numpy as np
+
+# linear regression, no bias
+# f = w*x
+# f = 2*x
+
+X = np.array([1, 2, 3, 4], dtype=np.float32)
+Y = np.array([2, 4, 6, 8], dtype=np.float32)
+
+w = 0.0
+
+# model prediction
+def forward(x):
+    return w*x
+
+# loss = MSE
+def loss(y, y_pred):
+    return ((y_pred - y)**2).mean()
+
+# gradient
+# mse = 1/N * (w*x - y)**2
+# dJ/dw = 1/N * 2x * (w*x - y)
+def gradient(x, y, y_pred):
+    return np.dot(2*x, y_pred-y).mean()
+
+print(f'Prediction before training: f(5) = {forward(5):.3f}')
+
+#Training
+learning_rate = .01
+n_iters = 20
+
+for epoch in range(n_iters):
+    # prediction = forward pass
+    y_pred = forward(X)
+
+    # loss
+    l = loss(Y, y_pred)
+
+    # gradients
+    dw = gradient(X, Y, y_pred)
+
+    #update weights
+    w -= learning_rate*dw
+
+    if epoch % 2 == 0: #every nth epoch
+        print(f'epoch {epoch+1}: w = {w:.3f}, loss = {l:.8f}')
+
+print(f'Prediction after training: f(5) = {forward(5):.3f}')
diff --git a/05_02_gradient_autograd.py b/05_02_gradient_autograd.py
new file mode 100644
index 0000000..7cde354
--- /dev/null
+++ b/05_02_gradient_autograd.py
@@ -0,0 +1,46 @@
+import torch
+
+# linear regression, no bias
+# f = w*x
+# f = 2*x
+
+X = torch.tensor([1, 2, 3, 4], dtype=torch.float32)
+Y = torch.tensor([2, 4, 6, 8], dtype=torch.float32)
+
+w = torch.tensor(0.0, dtype=torch.float32, requires_grad=True) #requires grad for gradient
+
+# model prediction
+def forward(x):
+    return w*x
+
+# loss = MSE
+def loss(y, y_pred):
+    return ((y_pred - y)**2).mean()
+
+
+print(f'Prediction before training: f(5) = {forward(5):.3f}')
+
+#Training
+learning_rate = .01
+n_iters = 100
+
+for epoch in range(n_iters):
+    # prediction = forward pass
+    y_pred = forward(X)
+
+    # loss
+    l = loss(Y, y_pred)
+
+    # gradients = backward pass
+    l.backward()
+
+    #update weights
+    with torch.no_grad():
+        w -= learning_rate*w.grad
+
+    w.grad.zero_()
+
+    if epoch % 10 == 0: #every nth epoch
+        print(f'epoch {epoch+1}: w = {w:.3f}, loss = {l:.8f}')
+
+print(f'Prediction after training: f(5) = {forward(5):.3f}')
diff --git a/06_01_gradient_torch_loss_optim.py b/06_01_gradient_torch_loss_optim.py
new file mode 100644
index 0000000..e69de29
diff --git a/06_02_gradient_torch_model.py b/06_02_gradient_torch_model.py
new file mode 100644
index 0000000..e69de29