关于Tensorflow模型保存与读取的问题

求助大神，Tensorflow构架的保存读取问题

想请教一下各位大神，我用tensorflow搭建了一个神经网络，想要保存和读取神经网络的输出，看过一篇相关的代码，自己也尝试着写了一下，但是有问题，哪位大神可以解答一下应该怎么改？代码如下。

import tensorflow as tf
import numpy as np
import pandas as pddef add_layer_hidden(inputs,in_size,out_size,activation_function=None):weights1 = tf.Variable(tf.random_normal([in_size, out_size]),dtype=tf.float32)biases1 = tf.Variable(tf.zeros([1, out_size]) + 0.1,dtype=tf.float32)a = weights1[0]b = weights1[1]Wx_plus_b = tf.matmul(inputs, weights1) + biases1if activation_function == None:outputs = Wx_plus_belse:outputs = activation_function( Wx_plus_b )return outputs,a,b
x_train = np.linspace(0,2,100,endpoint=True)
X_t=pd.read_csv('E:/test.csv',header=0,encoding='gbk')
X=X_t.values  #生成输入X值Xs=tf.placeholder(tf.float32,[None,2])#生成X占位符#定义隐含层,隐含层有10个神经元
l1=add_layer_hidden(Xs,2,10,activation_function=tf.nn.sigmoid)[0]#定义输出层,假设没有任何激活函数
def add_layer_output(inputs,in_size,out_size,activation_function=None):weights2 = tf.Variable(tf.random_normal([in_size, out_size]),dtype=tf.float32)biases2= tf.Variable(tf.zeros([1, out_size]) + 0.1,dtype=tf.float32)c = weights2Wx_plus_b = tf.matmul(inputs, weights2) + biases2if activation_function == None:outputs = Wx_plus_belse:outputs = activation_function(Wx_plus_b)return outputs,cprediction=add_layer_output(l1,10,1,activation_function=None)[0]w11=add_layer_hidden(Xs,2,10,activation_function=tf.nn.sigmoid)[1]
w12=add_layer_hidden(Xs,2,10,activation_function=tf.nn.sigmoid)[2]
w2=add_layer_output(l1,10,1,activation_function=None)[1]
difx = tf.matmul(tf.multiply(l1*(1-l1),w11),w2)#dy/dx,dif形状[100,1],即对应点的导数值
dift = tf.matmul(tf.multiply(l1*(1-l1),w12),w2)#dy/dt,dif形状[100,1],即对应点的导数值
loss1 = tf.square(difx+dift)
loss2 = tf.square(prediction[0]-prediction[99])
loss=tf.reduce_mean(tf.reduce_sum(loss1+loss2,reduction_indices=[1]))#生成损失函数
train_step=tf.train.GradientDescentOptimizer(0.1).minimize(loss)#进行梯度计算以及反向传播
init=tf.global_variables_initializer()
sess = tf.InteractiveSession()sess.run(init)for i in range(3000):#训练50000次sess.run(train_step,feed_dict={Xs:X})if i%50 == 0:total_loss = sess.run(loss,feed_dict={Xs:X})print(total_loss)
saver = tf.train.Saver(max_to_keep=1)
saver.save(sess,'E:/my net/nn.ckpt',global_step=3000)
saver = tf.train.Saver(max_to_keep=1) #保存模型，训练一次后可以将训练过程注释掉
saver.restore(sess, 'E:/my net/nn.ckpt')  #复现保存的模型

运行后错误如下：

NotFoundError: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for E:/my net/nn.ckpt
[[Node: save_29/RestoreV2_6 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_arg_save_29/Const_0_0, save_29/RestoreV2_6/tensor_names, save_29/RestoreV2_6/shape_and_slices)]]

Caused by op ‘save_29/RestoreV2_6’, defined at:
File “E:\Anaconda\envs\tensorflow\lib\site-packages\spyder\utils\ipython\start_kernel.py”, line 241, in
main()
File “E:\Anaconda\envs\tensorflow\lib\site-packages\spyder\utils\ipython\start_kernel.py”, line 237, in main
kernel.start()
File “E:\Anaconda\envs\tensorflow\lib\site-packages\ipykernel\kernelapp.py”, line 477, in start
ioloop.IOLoop.instance().start()
File “E:\Anaconda\envs\tensorflow\lib\site-packages\zmq\eventloop\ioloop.py”, line 177, in start
super(ZMQIOLoop, self).start()
File “E:\Anaconda\envs\tensorflow\lib\site-packages\tornado\ioloop.py”, line 888, in start
handler_func(fd_obj, events)
File “E:\Anaconda\envs\tensorflow\lib\site-packages\tornado\stack_context.py”, line 277, in null_wrapper
return fn(*args, **kwargs)
File “E:\Anaconda\envs\tensorflow\lib\site-packages\zmq\eventloop\zmqstream.py”, line 440, in _handle_events
self._handle_recv()
File “E:\Anaconda\envs\tensorflow\lib\site-packages\zmq\eventloop\zmqstream.py”, line 472, in _handle_recv
self._run_callback(callback, msg)
File “E:\Anaconda\envs\tensorflow\lib\site-packages\zmq\eventloop\zmqstream.py”, line 414, in _run_callback
callback(*args, **kwargs)
File “E:\Anaconda\envs\tensorflow\lib\site-packages\tornado\stack_context.py”, line 277, in null_wrapper
return fn(*args, **kwargs)
File “E:\Anaconda\envs\tensorflow\lib\site-packages\ipykernel\kernelbase.py”, line 283, in dispatcher
return self.dispatch_shell(stream, msg)
File “E:\Anaconda\envs\tensorflow\lib\site-packages\ipykernel\kernelbase.py”, line 235, in dispatch_shell
handler(stream, idents, msg)
File “E:\Anaconda\envs\tensorflow\lib\site-packages\ipykernel\kernelbase.py”, line 399, in execute_request
user_expressions, allow_stdin)
File “E:\Anaconda\envs\tensorflow\lib\site-packages\ipykernel\ipkernel.py”, line 196, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File “E:\Anaconda\envs\tensorflow\lib\site-packages\ipykernel\zmqshell.py”, line 533, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File “E:\Anaconda\envs\tensorflow\lib\site-packages\IPython\core\interactiveshell.py”, line 2698, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File “E:\Anaconda\envs\tensorflow\lib\site-packages\IPython\core\interactiveshell.py”, line 2808, in run_ast_nodes
if self.run_code(code, result):
File “E:\Anaconda\envs\tensorflow\lib\site-packages\IPython\core\interactiveshell.py”, line 2862, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File “”, line 1, in
runfile(‘E:/学习材料/偏微分方程与神经网络/tensorflow搭建神经网络.py’, wdir=‘E:/学习材料/偏微分方程与神经网络’)
File “E:\Anaconda\envs\tensorflow\lib\site-packages\spyder\utils\site\sitecustomize.py”, line 710, in runfile
execfile(filename, namespace)
File “E:\Anaconda\envs\tensorflow\lib\site-packages\spyder\utils\site\sitecustomize.py”, line 101, in execfile
exec(compile(f.read(), filename, ‘exec’), namespace)
File “E:/学习材料/偏微分方程与神经网络/tensorflow搭建神经网络.py”, line 67, in
saver = tf.train.Saver(max_to_keep=1) #保存模型，训练一次后可以将训练过程注释掉
File “E:\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\training\saver.py”, line 1139, in init
self.build()
File “E:\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\training\saver.py”, line 1170, in build
restore_sequentially=self._restore_sequentially)
File “E:\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\training\saver.py”, line 691, in build
restore_sequentially, reshape)
File “E:\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\training\saver.py”, line 407, in _AddRestoreOps
tensors = self.restore_op(filename_tensor, saveable, preferred_shard)
File “E:\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\training\saver.py”, line 247, in restore_op
[spec.tensor.dtype])[0])
File “E:\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\ops\gen_io_ops.py”, line 640, in restore_v2
dtypes=dtypes, name=name)
File “E:\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\framework\op_def_library.py”, line 767, in apply_op
op_def=op_def)
File “E:\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\framework\ops.py”, line 2506, in create_op
original_op=self._default_original_op, op_def=op_def)
File “E:\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\framework\ops.py”, line 1269, in init
self._traceback = _extract_stack()

NotFoundError (see above for traceback): Unsuccessful TensorSliceReader constructor: Failed to find any matching files for E:/my net/nn.ckpt
[[Node: save_29/RestoreV2_6 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_arg_save_29/Const_0_0, save_29/RestoreV2_6/tensor_names, save_29/RestoreV2_6/shape_and_slices)]]

关于Tensorflow模型保存与读取的问题相关推荐

Sklearn，TensorFlow，keras模型保存与读取
一.sklearn模型保存与读取 1.保存 1 from sklearn.externals import joblib 2 from sklearn import svm 3 X = [[0, 0 ...
TensorFlow模型保存和加载方法
TensorFlow模型保存和加载方法模型保存 import tensorflow as tfw1 = tf.Variable(tf.constant(2.0, shape=[1]), name=& ...
TensorFlow模型保存和提取方法
2019独角兽企业重金招聘Python工程师标准>>> 一.TensorFlow模型保存和提取方法 1. TensorFlow通过tf.train.Saver类实现神经网络模型的保存 ...
TensorFlow模型保存和提取方法（含滑动平均模型）
一.TensorFlow模型保存和提取方法 1. TensorFlow通过tf.train.Saver类实现神经网络模型的保存和提取.tf.train.Saver对象saver的save方法将Tens ...
Tensorflow 模型保存与恢复（2）使用SavedModel
使用SavedModel 保存和恢复模型本篇介绍使用SavedModel进行模型的保存与恢复. 其他相关: Tensorflow 模型保存与恢复(1)使用tf.train.Saver() Tenso ...
TensorFlow 模型保存/载入的两种方法
TensorFlow 模型保存/载入我们在上线使用一个算法模型的时候,首先必须将已经训练好的模型保存下来.tensorflow保存模型的方式与sklearn不太一样,sklearn很直接,一个skl ...
[tensorflow] 模型保存、加载与转换详解
TensorFlow模型加载与转换详解本次讲解主要涉及到TensorFlow框架训练时候模型文件的管理以及转换. 首先我们需要明确TensorFlow模型文件的存储格式以及文件个数: model_f ...
tensorflow随笔-保存与读取使用模型
1.MNIST是深度学习的经典入门demo,他是由6万张训练图片和1万张测试图片构成的,每张图片都是2828大小(如下图),而且都是黑白色构成(这里的黑色是一个0-1的浮点数,黑色越深表示数值越靠近1 ...
TensorFlow模型保存pb或ckpt
Tensorflow的保存分为三种:1. checkpoint模式:2. pb模式:3. saved_model模式. https://www.zhihu.com/collection/6445044 ...
Tensorflow2 图像分类-Flowers数据深度学习模型保存、读取、参数查看和图像预测
目录 1.原文完整代码 1.1 模型运行参数总结 1.2模型训练效果编辑2.模型的保存 3.读取模型model 4.使用模型进行图片预测 5.补充如何查看保存模型参数 5.1 model_wei ...

关于Tensorflow模型保存与读取的问题

求助大神，Tensorflow构架的保存读取问题

关于Tensorflow模型保存与读取的问题相关推荐

最新文章

热门文章