Create tensorflowproject1.py

Author: mhjensen

doc/src/week44/Programs/tensorflowproject1.py

@@ -0,0 +1,81 @@
+# import necessary packages
+import numpy as np
+import matplotlib.pyplot as plt
+import tensorflow as tf
+from tensorflow.keras.layers import Input
+from tensorflow.keras.models import Sequential      #This allows appending layers to existing models
+from tensorflow.keras.layers import Dense           #This allows defining the characteristics of a particular layer
+from tensorflow.keras import optimizers             #This allows using whichever optimiser we want (sgd,adam,RMSprop)
+from tensorflow.keras import regularizers           #This allows using whichever regularizer we want (l1,l2,l1_l2)
+from tensorflow.keras.utils import to_categorical   #This allows using categorical cross entropy as the cost function
+from sklearn.model_selection import train_test_split
+
+
+# Define the Runge function
+def runge_function(x):
+    return 1 / (1 + 25 * x**2)
+
+# Generate training data
+np.random.seed(0)
+x  = np.linspace(-1, 1, 200).reshape(-1, 1)
+y  = runge_function(x)
+
+# split into train and test data
+train_size = 0.8
+test_size = 1 - train_size
+X_train, X_test, Y_train, Y_test = train_test_split(x, y, train_size=train_size,test_size=test_size)
+
+epochs = 1000
+batch_size = 100
+n_neurons_layer1 = 128
+n_neurons_layer2 = 128
+n_categories = 1
+eta_vals = np.logspace(-5, 1, 7)
+lmbd_vals = np.logspace(-5, 1, 7)
+def create_neural_network_keras(n_neurons_layer1, n_neurons_layer2, n_categories, eta, lmbd):
+    model = Sequential()
+    model.add(Dense(n_neurons_layer1, activation='tanh', kernel_regularizer=regularizers.l2(lmbd)))
+    model.add(Dense(n_neurons_layer2, activation='tanh', kernel_regularizer=regularizers.l2(lmbd)))
+    model.add(Dense(n_categories, activation='linear'))
+    sgd = optimizers.SGD(learning_rate=eta)
+    model.compile(loss='mse', optimizer=sgd, metrics=['mse'])
+    return model
+
+DNN_keras = np.zeros((len(eta_vals), len(lmbd_vals)), dtype=object)
+for i, eta in enumerate(eta_vals):
+    for j, lmbd in enumerate(lmbd_vals):
+        DNN = create_neural_network_keras(n_neurons_layer1, n_neurons_layer2, n_categories,
+                                         eta=eta, lmbd=lmbd)
+        DNN.fit(X_train, Y_train, epochs=epochs, batch_size=batch_size, verbose=0)
+        scores = DNN.evaluate(X_test, Y_test)        
+        DNN_keras[i][j] = DNN
+        print("Learning rate = ", eta)
+        print("Lambda = ", lmbd)
+        print("Test MSE: %.3f" % scores[1])
+        print()
+
+import seaborn as sns
+sns.set()
+train_accuracy = np.zeros((len(eta_vals), len(lmbd_vals)))
+test_accuracy = np.zeros((len(eta_vals), len(lmbd_vals)))
+for i in range(len(eta_vals)):
+    for j in range(len(lmbd_vals)):
+        DNN = DNN_keras[i][j]
+        train_accuracy[i][j] = DNN.evaluate(X_train, Y_train)[1]
+        test_accuracy[i][j] = DNN.evaluate(X_test, Y_test)[1]
+fig, ax = plt.subplots(figsize = (10, 10))
+sns.heatmap(train_accuracy, annot=True, ax=ax, cmap="viridis")
+ax.set_title("Training Accuracy")
+ax.set_ylabel("$\eta$")
+ax.set_xlabel("$\lambda$")
+plt.show()
+
+fig, ax = plt.subplots(figsize = (10, 10))
+sns.heatmap(test_accuracy, annot=True, ax=ax, cmap="viridis")
+ax.set_title("Test Accuracy")
+ax.set_ylabel("$\eta$")
+ax.set_xlabel("$\lambda$")
+plt.show()
+
+
+