train.py

   1 import numpy as np
   2 from keras.models import Sequential
   3 from keras.layers import Dense, Dropout  # , Activation
   4
   5 model = Sequential()
   6
   7 model.add(Dense(26, input_shape=(13,), activation='relu'))
   8 model.add(Dense(100, activation='relu'))
   9 model.add(Dropout(0.25))
  10 model.add(Dense(100, activation='relu'))
  11 model.add(Dense(26, activation='relu'))
  12 model.add(Dense(1, activation='sigmoid'))
  13
  14 model.compile(
  15     loss='binary_crossentropy',
  16     optimizer='rmsprop',
  17     metrics=['accuracy'])
  18
  19 model.summary()
  20
  21 dat = np.genfromtxt('train.txt', dtype=float, delimiter='\t', usecols=range(1, 14))
  22 lab = np.genfromtxt('train.txt', dtype=int, delimiter='\t', usecols=[0])
  23
  24 model.fit(dat, lab, epochs=10, batch_size=32)
  25
  26 with open('model.json', 'w') as f:
  27     f.write(model.to_json())
  28 model.save_weights('model.hdf5')