def test_ntm_gradients():
state_size = 1
memory_shape = (5,1)
batch_size=10
controller_num_layers=1
controller_hidden_size=10
input_size=1
n_batches=20
T=2
controller_network = MLP((input_size, memory_shape[1]),
controller_num_layers, controller_hidden_size,
state_size)
x = tf.placeholder(tf.float32, [batch_size, T, input_size])
x_ = np.random.randn(batch_size*n_batches, T, input_size)
y_ = 2*x_ + 1.
addr = ShortcircuitAddressing(memory_shape, batch_size)
rh = ReadHead(state_size, memory_shape, addresser=addr, batch_size=batch_size,
hidden_size=2)
#ntm_cell = NTMCell(controller_network, memory_shape, batch_size,
# read_head=rh)
ntm_cell = NTMCell(controller_network, memory_shape, batch_size)
ntm = Network(ntm_cell, x)
loss = lambda a, b: tf.nn.l2_loss(a - b)
optimizer = tf.train.GradientDescentOptimizer(1e-4)
ntm.compile(loss, optimizer)
ntm.train(x_, y_, batch_size=batch_size, n_epochs=2)
def test_rnn():
input_size = 1
output_size = 1
T = 10
n_batches = 5
batch_size = 5
cell = RNNLayer(input_size, output_size, batch_size)
x = tf.placeholder(tf.float32, [batch_size, T, input_size])
y = tf.placeholder(tf.float32, [batch_size, T, output_size])
network = Network(cell, x)
x_ = np.random.randn(batch_size, T, input_size)
y_ = 2*x_ + 1
optimizer = tf.train.GradientDescentOptimizer(1e-4)
loss = lambda a, b: tf.reduce_mean(tf.pow(a - b, 2))
#loss = tf.reduce_mean(tf.pow(network.output()[0] - y, 2))
network.compile(loss, optimizer)
losses = network.train(x_, y_, batch_size=batch_size, verbose=False)