vae.py 文件源码

def _optimize(self):
        '''
        NOTE: The author said that there was no need for 100 d_iter per 100 iters.
              https://github.com/igul222/improved_wgan_training/issues/3
        '''
        global_step = tf.Variable(0, name='global_step')
        lr = self.arch['training']['lr']
        b1 = self.arch['training']['beta1']
        b2 = self.arch['training']['beta2']

        optimizer = tf.train.AdamOptimizer(lr, b1, b2)

        trainables = tf.trainable_variables()
        g_vars = [v for v in trainables if 'Generator' in v.name or 'y_emb' in v.name]
        d_vars = [v for v in trainables if 'Discriminator' in v.name]
        e_vars = [v for v in trainables if 'Encoder' in v.name]

        # # Debug ===============
        # debug(['Generator', 'Discriminator'], [g_vars, d_vars])
        # # ============================

        with tf.name_scope('Update'):
            opt_d = optimizer.minimize(self.loss['l_D'], var_list=d_vars)
            opt_e = optimizer.minimize(self.loss['l_E'], var_list=e_vars)
            with tf.control_dependencies([opt_e]):
                opt_g = optimizer.minimize(self.loss['l_G'], var_list=g_vars, global_step=global_step)
        return {
            'd': opt_d,
            'g': opt_g,
            'e': opt_e,
            'global_step': global_step
        }