- html - 出于某种原因,IE8 对我的 Sass 文件中继承的 html5 CSS 不友好?
- JMeter 在响应断言中使用 span 标签的问题
- html - 在 :hover and :active? 上具有不同效果的 CSS 动画
- html - 相对于居中的 html 内容固定的 CSS 重复背景?
我已经在 Tensorflow 中训练了一个模型。在训练过程中,我在优化器中设置了一个 var_list,换句话说,我在 CNN 之上训练了一个 GRU。这是优化器的代码:
with tf.name_scope('optimizer'):
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
with tf.control_dependencies(update_ops):
optimizer = tf.train.AdamOptimizer(0.0001).minimize(MSE, var_list=gru_output_var_list)
var_list
来自优化器为了能够微调整个网络,使用 GRU 卷积层。但是,这引发了一个错误:
Key weight_fc_sig/Adam_1 not found in checkpoint
weight_fc_sig
是模型中变量之一的名称。
最佳答案
首先,我在 tensorflow 中构建了一个模型,然后我将带有变量的图形保存到一个检查点中:
saver = tf.train.Saver()
saver.save(sess, model_path + "ckpt")
因此,当我检查通过以下方式存储的变量列表时:
from tensorflow.python import pywrap_tensorflow
model_path = 'C:/Users/user/PycharmProjects/TensorflowDifferentProjects/MNIStDataset/tensorlogs/ckpt'
reader = pywrap_tensorflow.NewCheckpointReader(model_path)
var_to_shape_map = reader.get_variable_to_shape_map()
for key in sorted(var_to_shape_map):
print("tensor_name: ", key)
我得到以下变量列表:
tensor_name: Adam_optimizer/beta1_power
tensor_name: Adam_optimizer/beta2_power
tensor_name: conv1/biases
tensor_name: conv1/biases/Adam
tensor_name: conv1/biases/Adam_1
tensor_name: conv1/weights
tensor_name: conv1/weights/Adam
tensor_name: conv1/weights/Adam_1
tensor_name: conv2/biases
tensor_name: conv2/biases/Adam
tensor_name: conv2/biases/Adam_1
tensor_name: conv2/weights
tensor_name: conv2/weights/Adam
tensor_name: conv2/weights/Adam_1
tensor_name: fc1/biases
tensor_name: fc1/biases/Adam
tensor_name: fc1/biases/Adam_1
tensor_name: fc1/weights
tensor_name: fc1/weights/Adam
tensor_name: fc1/weights/Adam_1
tensor_name: fc2/biases
tensor_name: fc2/biases/Adam
tensor_name: fc2/biases/Adam_1
tensor_name: fc2/weights
tensor_name: fc2/weights/Adam
tensor_name: fc2/weights/Adam_1
当我再次训练相同的模型时,但这一次,我仅将权重和偏差列表传递给保护程序:
tensor_name: conv1/biases
tensor_name: conv1/weights
tensor_name: conv2/biases
tensor_name: conv2/weights
tensor_name: fc1/biases
tensor_name: fc1/weights
tensor_name: fc2/biases
tensor_name: fc2/weights
现在,当我尝试再次运行相同的模型时,但删除了要恢复的变量列表,所以我现在有了这个保护程序:
saver = tf.train.Saver(),
我遇到了以下错误:
Key fc2/weights/Adam_1 not found in checkpoint.
因此,解决方案是明确提及我需要恢复的变量列表。换句话说,即使当我只
saver = tf.train.Saver(var_list=lst_vars)
哪里
lst_vars
是我需要恢复的变量列表,它与那个相同
saver = tf.train.Saver(var_list=lst_vars)
这不会造成任何问题
with tf.name_scope('Adam_optimizer'):
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy, var_list=lst_vars[:3])
saver = tf.train.Saver(var_list=lst_vars)
然后我可以再次运行相同的模型,但优化器中没有 var_list 参数。所以这就是微调的情况。
tensor_name: conv1/biases
tensor_name: conv1/weights
tensor_name: conv2/biases
tensor_name: conv2/weights
tensor_name: fc1/biases
tensor_name: fc1/weights
tensor_name: fc2/biases
tensor_name: fc2/weights
我应该向保护程序提及这些是我正在恢复的变量。所以我说了以下几点:
saver = tf.train.Saver(var_list=[lst_vars[0], lst_vars[1], lst_vars[2], lst_vars[3],
lst_vars[6], lst_vars[7], lst_vars[8], lst_vars[9]])
在这种情况下,不会有任何问题并且代码会运行良好!!!
saver = tf.train.Saver()
然后恢复模型的一部分(通过再次运行模型,并通过:
saver = tf.train.Saver(var_list=lst_vars))
此外,我可以修改模型并添加更多的卷积层。所以我可以微调模型,只要我确切地提到了什么
saver = tf.train.Saver(var_list=[lst_vars[0], lst_vars[1], lst_vars[2], lst_vars[3],
lst_vars[6], lst_vars[7], lst_vars[8], lst_vars[9]])
所有这些解释都是因为我认为优化器可能存在一些问题,我需要知道如何休息。在 github 上提出了一个问题,正是关于如何让优化器休息,这也是我得出所有这些结论的原因
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
import os
def conv2d(x, w):
return tf.nn.conv2d(x, w, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
def weight_variable(shape, name):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial, name=name)
def bias_variable(shape, name):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial, name=name)
def deepnn(x):
with tf.name_scope('reshape'):
x_image = tf.reshape(x, [-1, 28, 28, 1])
# First convolutional layer, maps one grayscale image to 32 feature maps.
with tf.name_scope('conv1'):
w_conv1 = weight_variable([5, 5, 1, 32], name='weights')
b_conv1 = bias_variable([32], name='biases')
h_conv1 = tf.nn.relu(conv2d(x_image, w_conv1) + b_conv1)
# Pooling layer, downsampling by 2X
with tf.name_scope('pool1'):
h_pool1 = max_pool_2x2(h_conv1)
# Second convolutional layer -- maps 32 feature maps to 64
with tf.name_scope('conv2'):
w_conv2 = weight_variable([5, 5, 32, 64], name='weights')
b_conv2 = bias_variable([64], name='biases')
h_conv2 = tf.nn.relu(conv2d(h_pool1, w_conv2) + b_conv2)
# Second pooling layer
with tf.name_scope('pool2'):
h_pool2 = max_pool_2x2(h_conv2)
# Fully connected layer 1 -- after 2 round of downsampling, our 28 x 28 image is
# down to 7 x 7 x 64 feature maps -- maps this to 1024 features.
with tf.name_scope('fc1'):
w_fc1 = weight_variable([7 * 7 * 64, 1024], name='weights')
b_fc1 = bias_variable([1024], name='biases')
h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, w_fc1) + b_fc1)
# Dropout - control the complexity of the model, prevents co-adaptation of features
with tf.name_scope('dropout'):
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# Map the 1024 features to 10 classes, one for each digit.
with tf.name_scope('fc2'):
w_fc2 = weight_variable([1024, 10], name='weights')
b_fc2 = bias_variable([10], name='biases')
y_conv = tf.matmul(h_fc1_drop, w_fc2) + b_fc2
return y_conv, keep_prob
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
# Create the model
x = tf.placeholder(tf.float32, [None, 784])
# Define loss and optimizer
y_ = tf.placeholder(tf.float32, [None, 10])
# Build the graph for the deep net
y_conv, keep_prob = deepnn(x)
with tf.name_scope('loss'):
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv)
cross_entropy = tf.reduce_mean(cross_entropy)
# Note that this list of variables only include the weights and biases in the model.
lst_vars = []
for v in tf.global_variables():
lst_vars.append(v)
print(v.name, '....')
with tf.name_scope('Adam_optimizer'):
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
with tf.name_scope('accuracy'):
correct_prediction = tf.equal(tf.arg_max(y_conv, 1), tf.arg_max(y_, 1))
correct_prediction = tf.cast(correct_prediction, tf.float32)
accuracy = tf.reduce_mean(correct_prediction)
model_path = 'C:/Users/user/PycharmProjects/TensorflowDifferentProjects/MNIStDataset/tensorlogs/'
saver = tf.train.Saver(var_list=lst_vars)
train_writer = tf.summary.FileWriter(model_path + "EventsFile/")
train_writer.add_graph(tf.get_default_graph())
for v in tf.global_variables():
print(v.name)
# Note that a session is created within a with block so that it is destroyed
# once the block has been exited.
with tf.Session() as sess:
print('all variables initialized!!')
sess.run(tf.global_variables_initializer())
ckpt = tf.train.get_checkpoint_state(
os.path.dirname(model_path))
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
print('checkpoints are saved!!!')
else:
print('No stored checkpoints')
for i in range(700):
batch = mnist.train.next_batch(50)
if i % 100 == 0:
train_accuracy = accuracy.eval(feed_dict={x: batch[0], y_: batch[1], keep_prob: 1.0})
print('step %d, training accuracy %g' % (i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
print('test accuracy %g' % accuracy.eval(feed_dict={
x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))
save_path = saver.save(sess, model_path + "ckpt")
和修改后的模型(我添加了另一个卷积层):
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
import os
def conv2d(x, w):
return tf.nn.conv2d(x, w, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
def weight_variable(shape, name):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial, name=name)
def bias_variable(shape, name):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial, name=name)
def deepnn(x):
with tf.name_scope('reshape'):
x_image = tf.reshape(x, [-1, 28, 28, 1])
# First convolutional layer, maps one grayscale image to 32 feature maps.
with tf.name_scope('conv1'):
w_conv1 = weight_variable([5, 5, 1, 32], name='weights')
b_conv1 = bias_variable([32], name='biases')
h_conv1 = tf.nn.relu(conv2d(x_image, w_conv1) + b_conv1)
# Pooling layer, downsampling by 2X
with tf.name_scope('pool1'):
h_pool1 = max_pool_2x2(h_conv1)
# Second convolutional layer -- maps 32 feature maps to 64
with tf.name_scope('conv2'):
w_conv2 = weight_variable([5, 5, 32, 64], name='weights')
b_conv2 = bias_variable([64], name='biases')
h_conv2 = tf.nn.relu(conv2d(h_pool1, w_conv2) + b_conv2)
# Second pooling layer
with tf.name_scope('pool2'):
h_pool2 = max_pool_2x2(h_conv2)
with tf.name_scope('conv3'):
w_conv3 = weight_variable([1, 1, 64, 64], name='weights')
b_conv3 = bias_variable([64], name='biases')
h_conv3 = tf.nn.relu(conv2d(h_pool2, w_conv3) + b_conv3)
# Fully connected layer 1 -- after 2 round of downsampling, our 28 x 28 image is
# down to 7 x 7 x 64 feature maps -- maps this to 1024 features.
with tf.name_scope('fc1'):
w_fc1 = weight_variable([7 * 7 * 64, 1024], name='weights')
b_fc1 = bias_variable([1024], name='biases')
h_conv3_flat = tf.reshape(h_conv3, [-1, 7 * 7 * 64])
h_fc1 = tf.nn.relu(tf.matmul(h_conv3_flat, w_fc1) + b_fc1)
# Dropout - control the complexity of the model, prevents co-adaptation of features
with tf.name_scope('dropout'):
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# Map the 1024 features to 10 classes, one for each digit.
with tf.name_scope('fc2'):
w_fc2 = weight_variable([1024, 10], name='weights')
b_fc2 = bias_variable([10], name='biases')
y_conv = tf.matmul(h_fc1_drop, w_fc2) + b_fc2
return y_conv, keep_prob
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
# Create the model
x = tf.placeholder(tf.float32, [None, 784])
# Define loss and optimizer
y_ = tf.placeholder(tf.float32, [None, 10])
# Build the graph for the deep net
y_conv, keep_prob = deepnn(x)
with tf.name_scope('loss'):
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv)
cross_entropy = tf.reduce_mean(cross_entropy)
# Note that this list of variables only include the weights and biases in the model.
lst_vars = []
for v in tf.global_variables():
lst_vars.append(v)
print(v.name, '....')
with tf.name_scope('Adam_optimizer'):
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
with tf.name_scope('accuracy'):
correct_prediction = tf.equal(tf.arg_max(y_conv, 1), tf.arg_max(y_, 1))
correct_prediction = tf.cast(correct_prediction, tf.float32)
accuracy = tf.reduce_mean(correct_prediction)
model_path = 'C:/Users/user/PycharmProjects/TensorflowDifferentProjects/MNIStDataset/tensorlogs/'
saver = tf.train.Saver(var_list=[lst_vars[0], lst_vars[1], lst_vars[2], lst_vars[3],
lst_vars[6], lst_vars[7], lst_vars[8], lst_vars[9]])
train_writer = tf.summary.FileWriter(model_path + "EventsFile/")
train_writer.add_graph(tf.get_default_graph())
for v in tf.global_variables():
print(v.name)
# Note that a session is created within a with block so that it is destroyed
# once the block has been exited.
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
print('all variables initialized!!')
ckpt = tf.train.get_checkpoint_state(
os.path.dirname(model_path))
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
print('checkpoints are saved!!!')
else:
print('No stored checkpoints')
for i in range(700):
batch = mnist.train.next_batch(50)
if i % 100 == 0:
train_accuracy = accuracy.eval(feed_dict={x: batch[0], y_: batch[1], keep_prob: 1.0})
print('step %d, training accuracy %g' % (i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
print('test accuracy %g' % accuracy.eval(feed_dict={
x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))
save_path = saver.save(sess, model_path + "ckpt")
关于optimization - 更改优化器参数后在 Tensorflow 中错误恢复模型,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/48161147/
可不可以命名为MVVM模型?因为View通过查看模型数据。 View 是否应该只与 ViewModelData 交互?我确实在某处读到正确的 MVVM 模型应该在 ViewModel 而不是 Mode
我正在阅读有关设计模式的文章,虽然作者们都认为观察者模式很酷,但在设计方面,每个人都在谈论 MVC。 我有点困惑,MVC 图不是循环的,代码流具有闭合拓扑不是很自然吗?为什么没有人谈论这种模式: mo
我正在开发一个 Sticky Notes 项目并在 WPF 中做 UI,显然将 MVVM 作为我的架构设计选择。我正在重新考虑我的模型、 View 和 View 模型应该是什么。 我有一个名为 Not
不要混淆:How can I convert List to Hashtable in C#? 我有一个模型列表,我想将它们组织成一个哈希表,以枚举作为键,模型列表(具有枚举的值)作为值。 publi
我只是花了一些时间阅读这些术语(我不经常使用它们,因为我们没有任何 MVC 应用程序,我通常只说“模型”),但我觉得根据上下文,这些意味着不同的东西: 实体 这很简单,它是数据库中的一行: 2) In
我想知道你们中是否有人知道一些很好的教程来解释大型应用程序的 MVVM。我发现关于 MVVM 的每个教程都只是基础知识解释(如何实现模型、 View 模型和 View ),但我对在应用程序页面之间传递
我想realm.delete() 我的 Realm 中除了一个模型之外的所有模型。有什么办法可以不列出所有这些吗? 也许是一种遍历 Realm 中当前存在的所有类型的方法? 最佳答案 您可以从您的 R
我正在尝试使用 alias 指令模拟一个 Eloquent 模型,如下所示: $transporter = \Mockery::mock('alias:' . Transporter::class)
我正在使用 stargazer 创建我的 plm 汇总表。 library(plm) library(pglm) data("Unions", package = "pglm") anb1 <- pl
我读了几篇与 ASP.NET 分层架构相关的文章和问题,但是读得太多后我有点困惑。 UI 层是在 ASP.NET MVC 中开发的,对于数据访问,我在项目中使用 EF。 我想通过一个例子来描述我的问题
我收到此消息错误: Inceptionv3.mlmodel: unable to read document 我下载了最新版本的 xcode。 9.4 版测试版 (9Q1004a) 最佳答案 您没有
(同样,一个 MVC 验证问题。我知道,我知道......) 我想使用 AutoMapper ( http://automapper.codeplex.com/ ) 来验证我的创建 View 中不在我
需要澄清一件事,现在我正在处理一个流程,其中我有两个 View 模型,一个依赖于另一个 View 模型,为了处理这件事,我尝试在我的基本 Activity 中注入(inject)两个 View 模型,
如果 WPF MVVM 应该没有代码,为什么在使用 ICommand 时,是否需要在 Window.xaml.cs 代码中实例化 DataContext 属性?我已经并排观看并关注了 YouTube
当我第一次听说 ASP.NET MVC 时,我认为这意味着应用程序由三个部分组成:模型、 View 和 Controller 。 然后我读到 NerdDinner并学习了存储库和 View 模型的方法
Platform : ubuntu 16.04 Python version: 3.5.2 mmdnn version : 0.2.5 Source framework with version :
我正在学习本教程:https://www.raywenderlich.com/160728/object-oriented-programming-swift ...并尝试对代码进行一些个人调整,看看
我正试图围绕 AngularJS。我很喜欢它,但一个核心概念似乎在逃避我——模型在哪里? 例如,如果我有一个显示多个交易列表的应用程序。一个列表向服务器查询匹配某些条件的分页事务集,另一个列表使用不同
我在为某个应用程序找出最佳方法时遇到了麻烦。我不太习惯取代旧 TLA(三层架构)的新架构,所以这就是我的来源。 在为我的应用程序(POCO 类,对吧??)设计模型和 DAL 时,我有以下疑问: 我的模
我有两个模型:Person 和 Department。每个人可以在一个部门工作。部门可以由多人管理。我不确定如何在 Django 模型中构建这种关系。 这是我不成功的尝试之一 [models.py]:
我是一名优秀的程序员,十分优秀!