[吃药深度学习随笔] 搭建模块化的神经网络八股

 

def forward(x, regularizer):
    w=
    b=
    y=
    return y

def get_weight(shape, regularizer):
    w=tf.Variable()
    tf.add_to_collection('losses', tf.contrib.layers.l2_regularizer(regularizer)(w))
    return w

def get_biase(shape):
    b = tf.Variable()
    return b

 

 

def backward(    ):
    x = tf.placeholder(    )
    y_ = tf.placeholder(    )
    y = forward.forward(x, REGULARIZER)
    global_step = tf.Variable(0,trainable=False)
    loss =

learning_rate = tf.train.exponential_decay(
    LEARNING_RATE_BASE,
    global_step
    数据集总样本数 / BATCH_SIZE,
    LEARNING_RATE_DECAY,
    staircase = True
)
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step = global_step)

 

ema = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
ema_op = ema.apply(tf.trainable_variables())
with tf.control_dependencies([train_step, ema_op]):
    train_op = tf.no_op(name='train')

 

with tf.Session() as sess:
    init_op = tf.global_variables_initializer()
    sess.run(init_op)
    for i in range(STEPS):
        sess.run(train_step, feed_dict={x:    , y_:    })
        if i % 轮数 == 0:
            print