Simple GAN with Keras

You can follow along with the code in the Jupyter notebook ch-14a_SimpleGAN.

Now let us implement the same model in Keras: 

  1. The hyper-parameter definitions remain the same as the last section:
# graph hyperparametersg_learning_rate = 0.00001d_learning_rate = 0.01n_x = 784  # number of pixels in the MNIST image # number of hidden layers for generator and discriminatorg_n_layers = 3d_n_layers = 1# neurons in each hidden layerg_n_neurons = [256, 512, 1024]d_n_neurons = [256]
  1. Next, define the generator network:
# define generatorg_model = Sequential()g_model.add(Dense(units=g_n_neurons[0],                   input_shape=(n_z,),                  name='g_0'))g_model.add(LeakyReLU())for i in range(1,g_n_layers):    g_model.add(Dense(units=g_n_neurons[i], name='g_{}'.format(i) ...

Get Mastering TensorFlow 1.x now with the O’Reilly learning platform.

O’Reilly members experience live online training, plus books, videos, and digital content from nearly 200 publishers.