def self_test():
"""Test the translation model."""
with tf.Session() as sess:
print("Self-test for neural translation model.")
# Create model with vocabularies of 10, 2 small buckets, 2 layers of 32.
model = seq2seq_model.Seq2SeqModel(10,
10, [(3, 3), (6, 6)],
32,
2,
5.0,
32,
0.3,
0.99,
num_samples=8)
sess.run(tf.global_variables_initialize())
# Fake data set for both the (3, 3) and (6, 6) bucket.
data_set = ([([1, 1], [2, 2]), ([3, 3], [4]),
([5], [6])], [([1, 1, 1, 1, 1], [2, 2, 2, 2, 2]),
([3, 3, 3], [5, 6])])
for _ in xrange(5): # Train the fake model for 5 steps.
bucket_id = random.choice([0, 1])
encoder_inputs, decoder_inputs, target_weights = model.get_batch(
data_set, bucket_id)
model.step(sess, encoder_inputs, decoder_inputs, target_weights,
bucket_id, False)
0,
[self.actions[rindex] -
1]] = self.rewards[rindex] + self.discount * next_state_max_Q
inputs[i] = current_input_state
targets[i] = target
return inputs, targets
memory = ReplayMemory(env.nx, env.ny, max_memory, gamma)
win_cnt = 0
sess = tf.InteractiveSession()
sess.run(tf.global_variables_initialize())
saver = tf.train.Saver()
for episode in range(n_episodes):
err = 0
s = env.reset()
for t in range(max_steps):
if np.random.rand() < epsilon:
a = np.random.randint(env.na) # random action
else:
q = sess.run(
y_hat,
feed_dict={x: np.reshape(s, [1, env.ny, env.nx, env.nf])})
a = np.random.choice(np.where(q[0] == np.max(q))[0])
sn, r, terminal, _, _, _, _, _, _, _, _ = env.run(
a - 1) # action to take is -1, 0, 1
def style_loss(sess,model):
pass
def content_loss(sess,model):
pass
IMAGE_WIDTH=248
IMAGE_HEIGHT=248
learning_rate=0.1
total_loss=style_weight*style_loss(sess,model)+contents_weight*content_loss(sess,model)
optimizer=tf.train.AdamOptimizer(2.0)
train_step=optimizer.minimize(total_loss)
init=tf.global_variables_initialize()
with tf.Session() as sess:
sess.run(init)
sess.
def train():
pass
# The network has two loss functions
# one is style loss and the other is contents loss
#
contents_image=np.fromfile(contents_image_filename)
weights={
if __name__=='__main__':
def initialize(self):
self.sess = tf.Session()
self.sess.run(tf.global_variables_initialize())