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)

        g_vars = tf.trainable_variables()

        with tf.name_scope('Update'):
            opt_g = optimizer.minimize(self.loss['G'], var_list=g_vars, global_step=global_step)
        return {
            'g': opt_g,
            'global_step': global_step
        }