square_root.py

import time

import keras
import matplotlib.pyplot as plt
import numpy as np
from keras.layers import Dense, Activation
from keras.models import Sequential

x = np.arange(-100, 100, 0.5)
y = x ** 2

model = Sequential()
model.add(keras.layers.normalization.BatchNormalization(input_shape=(1,)))
model.add(Dense(200))
model.add(Activation('relu'))
model.add(Dense(50))
model.add(Activation('elu'))
model.add(Dense(1))
model.compile(loss='mse', optimizer='adam')

t1 = time.clock()
for i in range(100):
    model.fit(x, y, epochs=1000, batch_size=len(x), verbose=0)
    predictions = model.predict(x)
    print(i, " ", np.mean(np.square(predictions - y)), " t: ", time.clock() - t1)

    # plt.hold(False)
    # plt.plot(x, y, 'b', x, predictions, 'r--')
    # plt.hold(True)
    # plt.ylabel('Y / Predicted Value')
    # plt.xlabel('X Value')
    # plt.title([str(i), " Loss: ", np.mean(np.square(predictions - y)), " t: ", str(time.clock() - t1)])
    # plt.pause(0.001)
# plt.show()
model.save("./out.model")

xor.py

#%%
import numpy as np
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.optimizers import RMSprop

#%%
batch_size = 128
num_classes = 10
epochs = 8000
X_train =np.array( [[1,0],[0,1],[1,1],[0,0]], "float32")
y_train=np.array( [[1],[1],[1],[0]], "float32")
#%%

def test_model(model):
    model.summary()
    model.compile(loss='mean_squared_error',optimizer='adam',metrics=['binary_accuracy'])
    model.fit(X_train,y_train, epochs=epochs,verbose=0)
    return model

#%%

model = test_model(Sequential(
    layers=[
        Dense(32, input_dim=2, activation='relu'),
        Dense(1, activation='sigmoid')
    ]
))
model.predict(X_train)
#%%
model.predict(X_train).round()
#%%