import tensorflow as tf
# PS：本篇的重担是saver，不过为了方便阅读还是说明下参数
# 参数
# name：创建卷基层的代码这么多，必须要函数化，而为了防止变量冲突就需要用tf.name_scope
# input_data：输入数据
# width, high：卷积小窗口的宽、高
# deep_before, deep_after：卷积前后的神经元数量
# stride：卷积小窗口的移动步长
def make_conv(name, input_data, width, high, deep_before,deep_after, stride, padding_type='SAME'):
 global parameters
 with tf.name_scope(name) asscope:
  weights =tf.Variable(tf.truncated_normal([width, high, deep_before, deep_after],
   dtype=tf.float32,stddev=0.01), trainable=True, name='weights')
  biases =tf.Variable(tf.constant(0.1, shape=[deep_after]), trainable=True, name='biases')
  conv =tf.nn.conv2d(input_data, weights, [1, stride, stride, 1], padding=padding_type)
  bias = tf.add(conv,biases)
  bias = batch_norm(bias,deep_after, 1) # batch_norm是自己写的batchnorm函数
  conv =tf.maximum(0.1*bias, bias)
  return conv

conv1 =make_conv('simple-conv1', images, 3, 3, 3, 32, 1)

conv1 = make_conv('complex-conv1',images, 3, 3, 3, 32, 1)
pool1= make_max_pool('layer1-pool1', conv1, 2, 2)
conv2= make_conv('complex-conv2', pool1, 3, 3, 32, 64, 1)

saver = tf.train.Saver()
with tf.Session() as sess:
saver.save(sess,'model.ckpt')

all_v =tf.global_variables()
for i in all_v: print i

<tf.Variable'simple-conv1/weights:0' shape=(3, 3, 3, 32) dtype=float32_ref>

<tf.Variable'simple-conv1/biases:0' shape=(32,) dtype=float32_ref>

<tf.Variable 'simple-conv1/Variable:0' shape=(32,)dtype=float32_ref>

<tf.Variable 'simple-conv1/Variable_1:0' shape=(32,)dtype=float32_ref>

<tf.Variable 'simple-conv1/Variable_2:0' shape=(32,)dtype=float32_ref>

<tf.Variable 'simple-conv1/Variable_3:0' shape=(32,)dtype=float32_ref>

parm_dict={}

parm_dict['complex-conv1/weights']= weights
parm_dict['complex-conv1/']= biases

saver= tf.train.Saver(parm_dict)

parameters= []

parameters+= [weights, biases]

saver= tf.train.Saver(parameters)

with tf.Session() as sess:
 ckpt= tf.train.get_checkpoint_state('.')
 if ckpt and ckpt.model_checkpoint_path:
  saver.restore(sess,ckpt.model_checkpoint_path)
 else:
  print ' no saver.'
  exit()