nvdm.py 文件源码

def build_model(self):
    self.x = tf.placeholder(tf.float32, [self.reader.vocab_size], name="input")
    self.x_idx = tf.placeholder(tf.int32, [None], name="x_idx")

    self.build_encoder()
    self.build_generator()

    # Kullback Leibler divergence
    self.e_loss = -0.5 * tf.reduce_sum(1 + self.log_sigma_sq - tf.square(self.mu) - tf.exp(self.log_sigma_sq))

    # Log likelihood
    self.g_loss = -tf.reduce_sum(tf.log(tf.gather(self.p_x_i, self.x_idx) + 1e-10))

    self.loss = self.e_loss + self.g_loss

    self.encoder_var_list, self.generator_var_list = [], []
    for var in tf.trainable_variables():
      if "encoder" in var.name:
        self.encoder_var_list.append(var)
      elif "generator" in var.name:
        self.generator_var_list.append(var)

    # optimizer for alternative update
    self.optim_e = tf.train.AdamOptimizer(learning_rate=self.lr) \
                         .minimize(self.e_loss, global_step=self.step, var_list=self.encoder_var_list)
    self.optim_g = tf.train.AdamOptimizer(learning_rate=self.lr) \
                         .minimize(self.g_loss, global_step=self.step, var_list=self.generator_var_list)

    # optimizer for one shot update
    self.optim = tf.train.AdamOptimizer(learning_rate=self.lr) \
                         .minimize(self.loss, global_step=self.step)

    _ = tf.scalar_summary("encoder loss", self.e_loss)
    _ = tf.scalar_summary("generator loss", self.g_loss)
    _ = tf.scalar_summary("total loss", self.loss)