diff --git a/Chapter08/cases/case_1.png b/Chapter08/cases/case_1.png
new file mode 100644
index 0000000000000000000000000000000000000000..f49f90a9a392ab491da1cf805c58a8a8394ec7f3
Binary files /dev/null and b/Chapter08/cases/case_1.png differ
diff --git a/Chapter08/cases/case_2.png b/Chapter08/cases/case_2.png
new file mode 100644
index 0000000000000000000000000000000000000000..ad68f1c93a8155a3bcd08a5079a32eeb47977071
Binary files /dev/null and b/Chapter08/cases/case_2.png differ
diff --git a/Chapter08/cases/case_3.png b/Chapter08/cases/case_3.png
new file mode 100644
index 0000000000000000000000000000000000000000..15d5694144c6172d2461b370dc292948c8ba414f
Binary files /dev/null and b/Chapter08/cases/case_3.png differ
diff --git a/Chapter08/cases/case_4.png b/Chapter08/cases/case_4.png
new file mode 100644
index 0000000000000000000000000000000000000000..9f9c27aabae7efd3bb5987577a2a82a45ce35f83
Binary files /dev/null and b/Chapter08/cases/case_4.png differ
diff --git a/Chapter08/cases/case_5.png b/Chapter08/cases/case_5.png
new file mode 100644
index 0000000000000000000000000000000000000000..4d4071d3186aa4fb901f3efb8e00ae3267097893
Binary files /dev/null and b/Chapter08/cases/case_5.png differ
diff --git a/Chapter08/cases/case_6.png b/Chapter08/cases/case_6.png
new file mode 100644
index 0000000000000000000000000000000000000000..34c744a3a1caf51295818628d1a0e0639e91cd07
Binary files /dev/null and b/Chapter08/cases/case_6.png differ
diff --git a/Chapter08/cases/case_7.png b/Chapter08/cases/case_7.png
new file mode 100644
index 0000000000000000000000000000000000000000..08195150435c2127b3668d66ccb99a3e0542d935
Binary files /dev/null and b/Chapter08/cases/case_7.png differ
diff --git a/Chapter08/make_data.py b/Chapter08/make_data.py
old mode 100755
new mode 100644
index 1a4419cb7ecf00a718f0e66757ed49fa51828204..442ad69850b828f383812d351e89614634b5d6cf
--- a/Chapter08/make_data.py
+++ b/Chapter08/make_data.py
@@ -1,107 +1,86 @@
-#%%
import numpy as np
+import matplotlib.pyplot as plt
+import skimage.io
+import os
-
-def make_data(example_nr, n = 200, noise = 1):
- '''
- Generate data for training a simple neural network.
-
- Arguments:
- example_nr: a number 1 to 3 for each example.
- n: number of points in each class set.
- noise: noise level, best between 0.5 and 2.
- Returns:
- X: 2 x 2n array of points (there are n points in each class).
- T: 2 x 2n target values.
- x: grid points for testing the neural network.
- dim: size of the area covered by the grid points.
-
- Authors: Vedrana Andersen Dahl and Anders Bjorholm Dahl - 25/3-2020
- vand@dtu.dk, abda@dtu.dk
- '''
-
- rg = np.random.default_rng()
-
- dim = (100, 100)
+def make_data(example_nr, n_pts = 200, noise = 1):
+ '''Make data for the neural network. The data is read from a png file in the
+ cases folder, which must be placed together with your code.
- QX, QY = np.meshgrid(range(0, dim[0]), range(0, dim[1]))
- x_grid = np.c_[np.ravel(QX), np.ravel(QY)]
-
- # Targets: first half class 0, second half class 1
- T = np.vstack((np.tile([True, False], (n, 1)),
- np.tile([False, True], (n, 1))))
-
- if example_nr == 1 : # two separated clusters
-
- X = np.vstack((np.tile([30., 30.], (n, 1)),
- np.tile([70., 70.], (n, 1))))
- X += rg.normal(size=X.shape, scale=10*noise) # add noise
-
- elif example_nr == 2 : # concentric clusters
-
- rand_ang = 2 * np.pi * rg.uniform(size=n)
- X = np.vstack((30 * np.array([np.cos(rand_ang), np.sin(rand_ang)]).T,
- np.tile([0., 0.], (n, 1))))
- X += [50, 50] # center
- X += rg.normal(size=X.shape, scale=5*noise)# add noise
+ Parameters:
+ example_nr : int
+ 1-7
+ n_pts : int
+ Number of points in each of the two classes
+ noise : float
+ Standard deviation of the Gaussian noise
+
+ Returns:
+ X : ndarray
+ 2 x n_pts array of points
+ T : ndarray
+ 2 x n_pts array of boolean values
+ x_grid : ndarray
+ 2 x n_pts array of points in regular grid for visualization
+ dim : tuple of int
+ Dimensions of the grid
- elif example_nr == 3 : # 2x2 checkerboard
- n1 = n//2
- n2 = n//2 + n%2 # if n is odd n2 will have 1 element more
-
- X = np.vstack((np.tile([30., 30.], (n1, 1)),
- np.tile([70., 70.], (n2, 1)),
- np.tile([30. ,70.], (n1, 1)),
- np.tile([70., 30.], (n2, 1))))
- X += rg.normal(size=X.shape, scale=10*noise) # add noise
-
- else:
- print('No data returned - example_nr must be 1, 2, or 3')
-
- o = rg.permutation(range(2*n))
-
- return X[o].T, T[o].T, x_grid.T, dim
+ Example:
+ example_nr = 1
+ n_pts = 2000
+ noise = 2
+ X, T, x_grid, dim = make_data(example_nr, n_pts, noise)
+
+ fig, ax = plt.subplots()
+ ax.plot(X[0,T[0]], X[1,T[0]], '.r', alpha=0.3)
+ ax.plot(X[0,T[1]], X[1,T[1]], '.g', alpha=0.3)
+ ax.set_xlim(0, 100)
+ ax.set_ylim(0, 100)
+ ax.set_box_aspect(1)
+
+ Authors: Vedrana Andersen Dahl and Anders Bjorholm Dahl - 20/3-2024
+ vand@dtu.dk, abda@dtu.dk
+ '''
-#%% Test of the data generation
-if __name__ == "__main__":
- #%%
+ in_dir = 'cases/'
+ file_names = sorted(os.listdir(in_dir))
+ file_names = [f for f in file_names if f.endswith('.png')]
- import matplotlib.pyplot as plt
-
- n = 1000
- noise = 1
-
- fig, ax = plt.subplots(1, 3)
- for i, a in enumerate(ax):
- example_nr = i + 1
- X, T, x_grid, dim = make_data(example_nr, n, noise)
- a.scatter(X[0][T[0]], X[1][T[0]], c='r', alpha=0.3, s=15)
- a.scatter(X[0][T[1]], X[1][T[1]], c='g', alpha=0.3, s=15)
- a.set_aspect('equal', 'box')
- a.set_title(f'Example {i} data')
-
- plt.show()
-
+ im = skimage.io.imread(in_dir + file_names[example_nr-1])
- #%% Before training, you should make data zero mean
-
- c = np.mean(X, axis=1, keepdims=True)
- X_c = X - c
-
- fig, ax = plt.subplots(1,1)
- ax.scatter(X_c[0][T[0]], X_c[1][T[0]], c='r', alpha=0.3, s=15)
- ax.scatter(X_c[0][T[1]], X_c[1][T[1]], c='g', alpha=0.3, s=15)
- ax.set_aspect('equal', 'box')
- plt.title('Zero-mean data')
- plt.show()
-
-
+ [r_white, c_white] = np.where(im == 255)
+ [r_gray, c_gray] = np.where(im == 127)
+ n_white = np.minimum(r_white.shape[0], n_pts)
+ n_gray = np.minimum(r_gray.shape[0], n_pts)
+ rid_white = np.random.permutation(r_white.shape[0])
+ rid_gray = np.random.permutation(r_gray.shape[0])
+ pts_white = np.array([c_white[rid_white[:n_white]], r_white[rid_white[:n_white]]])
+ pts_gray = np.array([c_gray[rid_gray[:n_gray]], r_gray[rid_gray[:n_gray]]])
+ X = np.hstack((pts_white, pts_gray))/5 + np.random.randn(2, n_white+n_gray)*noise
+ T = np.zeros((2, n_white+n_gray), dtype=bool)
+ T[0,:n_white] = True
+ T[1,n_white:] = True
+ dim = (100, 100)
+ QX, QY = np.meshgrid(range(0, dim[0]), range(0, dim[1]))
+ x_grid = np.vstack((np.ravel(QX), np.ravel(QY)))
+ return X, T, x_grid, dim
+if __name__ == "__main__":
+ example_nr = 1
+ n_pts = 2000
+ noise = 3
+ X, T, x_grid, dim = make_data(example_nr, n_pts, noise)
+
+ fig, ax = plt.subplots()
+ ax.plot(X[0,T[0]], X[1,T[0]], '.r', alpha=0.3)
+ ax.plot(X[0,T[1]], X[1,T[1]], '.g', alpha=0.3)
+ ax.set_xlim(0, 100)
+ ax.set_ylim(0, 100)
+ ax.set_box_aspect(1)
-# %%
diff --git a/Chapter08/make_data_simple.py b/Chapter08/make_data_simple.py
new file mode 100755
index 0000000000000000000000000000000000000000..1a4419cb7ecf00a718f0e66757ed49fa51828204
--- /dev/null
+++ b/Chapter08/make_data_simple.py
@@ -0,0 +1,107 @@
+#%%
+
+import numpy as np
+
+
+def make_data(example_nr, n = 200, noise = 1):
+ '''
+ Generate data for training a simple neural network.
+
+ Arguments:
+ example_nr: a number 1 to 3 for each example.
+ n: number of points in each class set.
+ noise: noise level, best between 0.5 and 2.
+ Returns:
+ X: 2 x 2n array of points (there are n points in each class).
+ T: 2 x 2n target values.
+ x: grid points for testing the neural network.
+ dim: size of the area covered by the grid points.
+
+ Authors: Vedrana Andersen Dahl and Anders Bjorholm Dahl - 25/3-2020
+ vand@dtu.dk, abda@dtu.dk
+ '''
+
+ rg = np.random.default_rng()
+
+ dim = (100, 100)
+
+ QX, QY = np.meshgrid(range(0, dim[0]), range(0, dim[1]))
+ x_grid = np.c_[np.ravel(QX), np.ravel(QY)]
+
+ # Targets: first half class 0, second half class 1
+ T = np.vstack((np.tile([True, False], (n, 1)),
+ np.tile([False, True], (n, 1))))
+
+ if example_nr == 1 : # two separated clusters
+
+ X = np.vstack((np.tile([30., 30.], (n, 1)),
+ np.tile([70., 70.], (n, 1))))
+ X += rg.normal(size=X.shape, scale=10*noise) # add noise
+
+ elif example_nr == 2 : # concentric clusters
+
+ rand_ang = 2 * np.pi * rg.uniform(size=n)
+ X = np.vstack((30 * np.array([np.cos(rand_ang), np.sin(rand_ang)]).T,
+ np.tile([0., 0.], (n, 1))))
+ X += [50, 50] # center
+ X += rg.normal(size=X.shape, scale=5*noise)# add noise
+
+ elif example_nr == 3 : # 2x2 checkerboard
+ n1 = n//2
+ n2 = n//2 + n%2 # if n is odd n2 will have 1 element more
+
+ X = np.vstack((np.tile([30., 30.], (n1, 1)),
+ np.tile([70., 70.], (n2, 1)),
+ np.tile([30. ,70.], (n1, 1)),
+ np.tile([70., 30.], (n2, 1))))
+ X += rg.normal(size=X.shape, scale=10*noise) # add noise
+
+ else:
+ print('No data returned - example_nr must be 1, 2, or 3')
+
+ o = rg.permutation(range(2*n))
+
+ return X[o].T, T[o].T, x_grid.T, dim
+
+
+#%% Test of the data generation
+if __name__ == "__main__":
+ #%%
+
+ import matplotlib.pyplot as plt
+
+ n = 1000
+ noise = 1
+
+ fig, ax = plt.subplots(1, 3)
+ for i, a in enumerate(ax):
+ example_nr = i + 1
+ X, T, x_grid, dim = make_data(example_nr, n, noise)
+ a.scatter(X[0][T[0]], X[1][T[0]], c='r', alpha=0.3, s=15)
+ a.scatter(X[0][T[1]], X[1][T[1]], c='g', alpha=0.3, s=15)
+ a.set_aspect('equal', 'box')
+ a.set_title(f'Example {i} data')
+
+ plt.show()
+
+
+ #%% Before training, you should make data zero mean
+
+ c = np.mean(X, axis=1, keepdims=True)
+ X_c = X - c
+
+ fig, ax = plt.subplots(1,1)
+ ax.scatter(X_c[0][T[0]], X_c[1][T[0]], c='r', alpha=0.3, s=15)
+ ax.scatter(X_c[0][T[1]], X_c[1][T[1]], c='g', alpha=0.3, s=15)
+ ax.set_aspect('equal', 'box')
+ plt.title('Zero-mean data')
+ plt.show()
+
+
+
+
+
+
+
+
+# %%