updated keras models (#259)

* updated keras models

* few more changes

keras/klab-04-1-multi_input_linear_regression.py

@@ -3,24 +3,27 @@
 from keras.optimizers import RMSprop
 import numpy as np
 
-x_data = [[73., 80., 75.],
+x_data = np.array([[73., 80., 75.],
           [93., 88., 93.],
           [89., 91., 90.],
           [96., 98., 100.],
-          [73., 66., 70.]]
-y_data = [[152.],
+          [73., 66., 70.]])
+y_data = np.array([[152.],
           [185.],
           [180.],
           [196.],
-          [142.]]
+          [142.]])
+
+print(x_data.shape)
+print(y_data.shape)          
 
 model = Sequential()
 model.add(Dense(input_dim=3, units=1))
 model.add(Activation('linear'))
 
-rmsprop = RMSprop(lr=1e-10)
-model.compile(loss='mse', optimizer=rmsprop)
+rmsprop = RMSprop(lr=0.1)
+model.compile(loss='mse', optimizer=rmsprop,  metrics=['accuracy'])
 model.fit(x_data, y_data, epochs=1000)
 
 y_predict = model.predict(np.array([[95., 100., 80]]))
-print(y_predict)
+print(y_predict)

keras/klab-04-2-multi_input_linear_regression.py

@@ -2,22 +2,22 @@
 from keras.layers import Dense
 import numpy as np
 
-x_data = [[73., 80., 75.],
+x_data = np.array([[73., 80., 75.],
           [93., 88., 93.],
           [89., 91., 90.],
           [96., 98., 100.],
-          [73., 66., 70.]]
-y_data = [[152.],
+          [73., 66., 70.]])
+y_data = np.array([[152.],
           [185.],
           [180.],
           [196.],
-          [142.]]
+          [142.]])
 
 model = Sequential()
 model.add(Dense(input_dim=3, units=1))
 
-model.compile(loss='mse', optimizer='rmsprop')
-model.fit(x_data, y_data)
+model.compile(loss='mse', optimizer='adam', metrics=['accuracy'])
+model.fit(x_data, y_data, epochs=500)
 
 y_predict = model.predict(np.array([[0, 2, 1]]))
-print(y_predict)
+print(y_predict)

keras/klab-05-1-logistic_regression.py

@@ -3,27 +3,27 @@
 from keras.optimizers import SGD
 import numpy as np
 
-x_data = [[1, 2],
+x_data = np.array([[1, 2],
           [2, 3],
           [3, 1],
           [4, 3],
           [5, 3],
-          [6, 2]]
-y_data = [[0],
+          [6, 2]])
+y_data = np.array([[0],
           [0],
           [0],
           [1],
           [1],
-          [1]]
+          [1]])
 
 model = Sequential()
 model.add(Dense(1, input_dim=2, activation='sigmoid'))
 
 sgd = SGD(lr=0.1)
-model.compile(loss='binary_crossentropy', optimizer=sgd)
+model.compile(loss='binary_crossentropy', optimizer=sgd, metrics=['accuracy'])
 
 model.summary()
 model.fit(x_data, y_data, epochs=2000)
 
 print("2,1", model.predict_classes(np.array([[2, 1]])))
-print("6,5", model.predict_classes(np.array([[6, 5]])))
+print("6,5", model.predict_classes(np.array([[6, 5]])))

keras/klab-05-2-logistic_regression_diabetes.py

@@ -3,18 +3,18 @@
 from keras.optimizers import SGD
 import numpy as np
 
-x_data = [[1, 2],
+x_data = np.array([[1, 2],
           [2, 3],
           [3, 1],
           [4, 3],
           [5, 3],
-          [6, 2]]
-y_data = [[0],
+          [6, 2]])
+y_data = np.array([[0],
           [0],
           [0],
           [1],
           [1],
-          [1]]
+          [1]])
 
 model = Sequential()
 model.add(Dense(1, input_dim=2, activation='sigmoid'))

keras/klab-07-1-learning_rate_and_evaluation.py

@@ -5,14 +5,14 @@
 import numpy as np
 np.random.seed(777)  # for reproducibility
 
-x_data = [[1, 2, 1], [1, 3, 2], [1, 3, 4], [1, 5, 5],
-          [1, 7, 5], [1, 2, 5], [1, 6, 6], [1, 7, 7]]
-y_data = [[0, 0, 1], [0, 0, 1], [0, 0, 1], [0, 1, 0],
-          [0, 1, 0], [0, 1, 0], [1, 0, 0], [1, 0, 0]]
+x_data = np.array([[1, 2, 1], [1, 3, 2], [1, 3, 4], [1, 5, 5],
+          [1, 7, 5], [1, 2, 5], [1, 6, 6], [1, 7, 7]])
+y_data = np.array([[0, 0, 1], [0, 0, 1], [0, 0, 1], [0, 1, 0],
+          [0, 1, 0], [0, 1, 0], [1, 0, 0], [1, 0, 0]])
 
 # Evaluation our model using this test dataset
-x_test = [[2, 1, 1], [3, 1, 2], [3, 3, 4]]
-y_test = [[0, 0, 1], [0, 0, 1], [0, 0, 1]]
+x_test = np.array([[2, 1, 1], [3, 1, 2], [3, 3, 4]])
+y_test = np.array([[0, 0, 1], [0, 0, 1], [0, 0, 1]])
 
 
 model = Sequential()

keras/klab-09-1-xor.py

@@ -2,14 +2,14 @@
 from keras.layers import Dense
 from keras.optimizers import SGD
 
-x_data = [[0., 0.],
+x_data = np.array([[0., 0.],
           [0., 1.],
           [1., 0.],
-          [1., 1.]]
-y_data = [[0.],
+          [1., 1.]])
+y_data = np.array([[0.],
           [1.],
           [1.],
-          [0.]]
+          [0.]])
 
 model = Sequential()
 model.add(Dense(1, input_dim=2, activation='sigmoid'))

keras/klab-09-2-xor-nn.py

@@ -2,14 +2,14 @@
 from keras.layers import Dense
 from keras.optimizers import SGD
 
-x_data = [[0., 0.],
+x_data = np.array([[0., 0.],
           [0., 1.],
           [1., 0.],
-          [1., 1.]]
-y_data = [[0.],
+          [1., 1.]])
+y_data = np.array([[0.],
           [1.],
           [1.],
-          [0.]]
+          [0.]])
 
 model = Sequential()
 model.add(Dense(2, input_dim=2, activation='sigmoid'))