1 如何使用pb文件保存和恢复模型进行迁移学习（学习Tensorflow 实战google深度学习框架）

importtensorflow as tf
from tensorflow.python.framework importgraph_util
v1=tf.constant([10000.0],name='v1')
#v1 = tf.placeholder(tf.float32,shape=[1],name='v1')
v2 = tf.Variable(tf.constant(2.0, shape=[1]), name = "v2")
result = v1 +v2

init_op =tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init_op,{v1:[100]})
    print (sess.run(result,{v1:[1000]}))
    writer = tf.summary.FileWriter('./graphs/model_graph', sess.graph)
    writer.close()    
    graph_def =tf.get_default_graph().as_graph_def()
    output_graph_def = graph_util.convert_variables_to_constants(sess, graph_def,['add'])
    with tf.gfile.GFile("Saved_model/combined_model.pb", "wb") as f:
        f.write(output_graph_def.SerializeToString())

#这是我以前写的程序,是错误的
"""因为我以前写的只是获取一个值。
而现在修正的v1则是一个tensor。我们可以修正tensor的值。
所以，tensorflow 实战google深度学习框架中有重大bug。
不懂的联系我手机 18627711314 杰
"""
importtensorflow as tf
importnumpy as np
from numpy.random importRandomState
from tensorflow.python.platform importgfile
with tf.Session() as sess:
    model_filename = "Saved_model/combined_model.pb"  
    #model_filename = "inception_dec_2015/tensorflow_inception_graph.pb"  
with gfile.FastGFile(model_filename, 'rb') as f:
        graph_def =tf.GraphDef()
        graph_def.ParseFromString(f.read())
    """将模型的相关信息写入文件，和利用tensorboard进行可视化
    f = open("xiaojie2.txt", "w")
    print ("xiaojie2
",file = f)
    print (graph_def,file=f)
    f.close()
    writer = tf.summary.FileWriter('./graphs/model_graph2', graph_def)
    writer.close()
    """
    """④输出所有可训练的变量名称，也就是神经网络的参数"""trainable_variables=tf.trainable_variables()
    variable_list_name = [c.name for c intf.trainable_variables()]
    variable_list =sess.run(variable_list_name)
    for k,v inzip(variable_list_name,variable_list):
        print("variable name:",k)
        print("shape:",v.shape)
        #print(v) 
    """④输出所有可训练的变量名称，也就是神经网络的参数"""
v1= tf.import_graph_def(graph_def, return_elements=["v1:0"])
    print (v1)
    print (sess.run(v1))
    v2= tf.import_graph_def(graph_def, return_elements=["v2:0"])
    print (sess.run(v2))
    result = tf.import_graph_def(graph_def, return_elements=["add:0"])
    print (sess.run(result))
    x=np.array([2000.0])
    print (sess.run(result,feed_dict={v1: x}))

importtensorflow as tf
importnumpy as np
from numpy.random importRandomState
from tensorflow.python.platform importgfile
with tf.Graph().as_default():
    output_graph_def =tf.GraphDef()
    output_graph_path='Saved_model/combined_model.pb'with open(output_graph_path, "rb") as f:
        output_graph_def.ParseFromString(f.read())
        _ = tf.import_graph_def(output_graph_def, name="")
    with tf.Session() as sess:
"""④输出所有可训练的变量名称，也就是神经网络的参数"""trainable_variables=tf.trainable_variables()
        variable_list_name = [c.name for c intf.trainable_variables()]
        variable_list =sess.run(variable_list_name)
        for k,v inzip(variable_list_name,variable_list):
            print("variable name:",k)
            print("shape:",v.shape)
            #print(v) 
"""④输出所有可训练的变量名称，也就是神经网络的参数"""input_x = sess.graph.get_tensor_by_name("v1:0")
        result = tf.import_graph_def(graph_def, return_elements=["add:0"])
        print(input_x)
        x=np.array([2000.0])
        print (sess.run(result,feed_dict={input_x: x}))

v1= tf.import_graph_def(graph_def, return_elements=["v1:0"])
print(v1)
print(sess.run(v1))
v2= tf.import_graph_def(graph_def, return_elements=["v2:0"])
print(sess.run(v2))
result = tf.import_graph_def(graph_def, return_elements=["add:0"])
print(sess.run(result))
x=np.array([2000.0])
#print (sess.run(result,feed_dict={v1: x}))

print (sess.run(result,feed_dict={v1[0]: x}))

importtensorflow as tf
importnumpy as np
from numpy.random importRandomState
from tensorflow.python.platform importgfile
output_graph_def =tf.GraphDef()
output_graph_path='Saved_model/combined_model.pb'with open(output_graph_path, "rb") as f:
    output_graph_def.ParseFromString(f.read())
    _ = tf.import_graph_def(output_graph_def, name="")
with tf.Session() as sess:
"""④输出所有可训练的变量名称，也就是神经网络的参数"""trainable_variables=tf.trainable_variables()
    variable_list_name = [c.name for c intf.trainable_variables()]
    variable_list =sess.run(variable_list_name)
    for k,v inzip(variable_list_name,variable_list):
        print("variable name:",k)
        print("shape:",v.shape)
        #print(v) 
  """④输出所有可训练的变量名称，也就是神经网络的参数"""input_x = sess.graph.get_tensor_by_name("v1:0")
    result = tf.import_graph_def(graph_def, return_elements=["add:0"])
    print(input_x)
    x=np.array([2000.0])
    print (sess.run(result,feed_dict={input_x: x}))