def __init__(self, embed_matrix):
self.graph = tf.Graph()
with self.graph.as_default():
# Input
self.input_matrix = tf.constant(embed_matrix, name="embed_matrix")
self.word_ids = tf.placeholder(tf.int32,
shape=[None],
name="word_ids")
# 圧縮したい分散表現 (batch_size,embed_size)
self.input_embeds = tf.nn.embedding_lookup(self.input_matrix,
self.word_ids,
name="input_embeds")
# Codebooks
self.codebooks = tf.get_variable("codebook",
[hp.M * hp.K, hp.embed_size])
# Encoding
self.logits = encode(self.input_embeds) # (batch_size, M, K)
# Discretization
self.D = gumbel_softmax(self.logits,
hp.tau_value) # (batch_size,M,K)
self.gumbel_output = tf.reshape(
self.D, [-1, hp.M * hp.K]) # (batch_size, M * K)
self.maxp = tf.reduce_mean(tf.reduce_max(self.D, axis=2))
# Decoding
self.output_embeds = decode(
self.gumbel_output,
self.codebooks) # (batch_size, M*K) * (M*K, embed_size)
# Loss
self.loss = tf.reduce_mean(0.5 * tf.reduce_sum(
(self.output_embeds - self.input_embeds)**2, axis=1),
name="loss")
# Optimization
self.train_vars = tf.trainable_variables()
self.grads, self.global_norm = tf.clip_by_global_norm(
tf.gradients(self.loss, self.train_vars), clip_norm=0.001)
self.global_norm = tf.identity(self.global_norm,
name="global_norm")
self.optimizer = tf.train.AdamOptimizer(0.0001)
self.train_op = self.optimizer.apply_gradients(zip(
self.grads, self.train_vars),
name="train_op")
modules.yaz("\nKullanabileceğiniz komutlar şunlardır:")
modules.yaz("""
cikis, c : yazilimi durdurmak icin kullanilir.
decode, d: sifreli yaziyi cozmek icin kullanılır. (Aktif degil)
encode, e: sifrelemek icin kullanılır.
yardim, y: yardim yazisini gosterir.
""")
yardim()
while True: #Dongu baslangaci
komut = input("\n>>> ")
if komut in ["cikis", "c"]:
break
elif komut in ["encode", "e"]:
text = input("Encode edilecek yazi: ")
modules.yaz(modules.encode(text))
elif komut in ["decode", "d"]:
text = input("Decode edilecek yazi: ")
modules.yaz(modules.decode(text))
elif komut in ["yardim", "y"]:
yardim()
else:
modules.yaz("\nVar olan bir komutu yazmadınız.\n")
def test_DecoderString_CorrectDecoding(self):
y = np.array([[1, 0], [0, 1], [0, 1]])
cdict = {'cat': np.array([1, 0]), 'dog': np.array([0, 1])}
y1 = decode(y, cdict)
y2 = ['cat', 'dog', 'dog']
self.assertEqual(y1, y2)
def test_Decoder1dim_CorrectDecoding(self):
y = np.array([[1, 0], [0, 1], [0, 1]])
cdict = {1: np.array([1, 0]), 2: np.array([0, 1])}
y1 = decode(y, cdict)
y2 = [1, 2, 2]
np.testing.assert_array_almost_equal(y1, y2)
def test_DecoderString_CorrectDecoding(self):
y = np.array([[1, 0], [0, 1], [0, 1]])
cdict = {'cat': np.array([1, 0]), 'dog': np.array([0, 1])}
y1 = decode(y, cdict)
y2 = ['cat', 'dog', 'dog']
self.assertEqual(y1, y2)
def test_Decoder1dim_CorrectDecoding(self):
y = np.array([[1, 0], [0, 1], [0, 1]])
cdict = {1: np.array([1, 0]), 2: np.array([0, 1])}
y1 = decode(y, cdict)
y2 = [1, 2, 2]
np.testing.assert_array_almost_equal(y1, y2)