初始tensorflow

最新推荐文章于 2022-05-02 16:24:27 发布

Mr_哲

最新推荐文章于 2022-05-02 16:24:27 发布

阅读量2.9k

点赞数 2

分类专栏： tensorflow 文章标签： tensorflow anaconda python mnist

本文链接：https://blog.csdn.net/baymax_007/article/details/83060758

版权

tensorflow 专栏收录该内容

5 篇文章 0 订阅

订阅专栏

很早之前就听闻tensorflow大名，作为深度学习框架的明星产品tensorflow从诞生之初，就备受关注。作为入门小白，以后也会逐步学起，更新tensorflow认识和技能。

TensorFlow是Google开源的一款人工智能学习系统。为什么叫这个名字呢？Tensor的意思是张量，代表N维数组；Flow的意思是流，代表基于数据流图的计算。把N维数字从流图的一端流动到另一端的过程，就是人工智能神经网络进行分析和处理的过程。

使用tensorflow需要注意：

使用图 (graph) 来表示计算任务.
在被称之为 会话 (Session) 的上下文 (context) 中执行图.
使用 tensor 表示数据.
通过 变量 (Variable) 维护状态.
使用 feed 和 fetch 可以为任意的操作(arbitrary operation) 赋值或者从其中获取数据.

OK，讲了这么多概念，还是快速上手安装体验下吧。

一、安装

机器环境是：ubuntu18.04 LTS+anaconda 5.2+python 3.6.5+tensorflow 1.11.0

1. cpu or gpu？

gpu可以加速tensorflow速度，如果显存在8G以上gpu远快于cpu。需要现查看下自己机器gpu情况如下，可以看出gpu不行，选择cpu版本进行安装。

cat /proc/cpuinfo #查看cpu
lspci | grep VGA #查看gpu

2. pip安装

由于python不同版本包依赖存在冲突，而anaconda是一个开源的包、环境管理器，可以用于在同一个机器上安装不同版本的软件包及其依赖，并能够在不同的环境之间切换，选用anaconda进行管理。

2.1 anaconda安装

在https://mirrors.tuna.tsinghua.edu.cn/anaconda/archive/选取合适的安装包，进行安装，如下：

sh Anaconda3-5.2.0-Linux-x86_64.sh

一路按yes即可。

2.2 tensorflow安装

建立一个conda计算环境，并激活该环境，最后安装tensorflow，如下。

conda create -n tensorflow #创建

source activate tensorflow #激活

pip install --ignore-installed --upgrade https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-1.11.0-cp36-cp36m-linux_x86_64.whl

2.3 测试是否安装成功

启动python shell，并导入tensorflow，如果没有报错，则成功。

import tensorflow as tf

二、MNIST入门

当我们开始学习编程的时候，第一件事往往是学习打印"Hello World"。就好比编程入门有Hello World，机器学习入门有MNIST。

1. 数据集

MNIST是一个入门级的计算机视觉数据集，它包含各种手写数字图片（每一张图片包含28像素X28像素，长度是 28x28 = 784），也包含每一张图片对应的标签，MNIST数据集的官网是Yann LeCun's website。下载下来的数据集被分成两部分：60000行的训练数据集（mnist.train）和10000行的测试数据集（mnist.test）。

对于由784个像素点组成图片，如何展开这个数组（数字间的顺序）不重要，只要保持各个图片采用相同的方式展开。因此，在MNIST训练数据集中，mnist.train.images 是一个形状为 [60000, 784] 的张量，第一个维度数字用来索引图片，第二个维度数字用来索引每张图片中的像素点。在此张量里的每一个元素，都表示某张图片里的某个像素的强度值，值介于0和1之间。

相对应的MNIST数据集的标签是介于0到9的数字，用来描述给定图片里表示的数字。使用one-hot处理标签，标签0将表示成([1,0,0,0,0,0,0,0,0,0,0])。因此， mnist.train.labels 是一个 [60000, 10] 的数字矩阵。

2. softmax回归

softmax模型可以用来给不同的对象分配概率。对于MNIST，每一张图片都表示一个数字，从0到9。我们希望得到给定图片代表每个数字的概率。比如说，我们的模型可能推测一张包含9的图片代表数字9的概率是80%但是判断它是8的概率是5%（因为8和9都有上半部分的小圆），然后给予它代表其他数字的概率更小的值。数学公式如下：

y=softmax(Wx+b)

3. 实现softmax回归模型

tensorflow实现softmax代码只需要一行，如下

y = tf.nn.softmax(tf.matmul(x, W) + b)

第一个参数logits：就是神经网络最后一层的输出，如果有batch的话，它的大小就是[batchsize, num_classes]，单样本的话，大小就是num_classes。

第二个参数labels：实际的标签，大小同上。

具体执行流程分为两部：

第一步是先对网络最后一层的输出做一个softmax，这一步通常是求取输出属于某一类的概率，对于单样本而言，输出就是一个num_classes大小的向量（ $[Y_{1},Y_{2},Y_{3}...]$ 元素分别代表了是属于该类的概率）。

第二步是softmax输出向量 $[Y_{1},Y_{2},Y_{3}...]$ 向量和样本的实际标签做一个交叉熵，公式如下：

$H_{y_{i}^{'}}(y) = \sum_{i} y_{i}^{'} log(y_{i})$

其中， $y_{i}^{'}$ 是实际的标签中第i个的值（用mnist数据举例，如果是3，那么标签是 [0,0,0,1,0,0,0,0,0,0] ， $y_{i}$ 是softmax输出向量 $[Y_{1},Y_{2},Y_{3}...]$ 中，第i个元素的值。

具体代码见git。

4. tensorflow版本改动api bug说明

4.1 ValueError: Shapes (2, 100, 1) and () are incompatible

Traceback (most recent call last):
  File "/home/lee/PycharmProjects/mnist/fully_connected_feed.py", line 222, in <module>
    tf.app.run()
  File "/opt/modules/anaconda3/envs/mnist/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
    _sys.exit(main(argv))
  File "/home/lee/PycharmProjects/mnist/fully_connected_feed.py", line 218, in main
    run_training()
  File "/home/lee/PycharmProjects/mnist/fully_connected_feed.py", line 138, in run_training
    loss = mnist.loss(logits, labels_placeholder)
  File "/home/lee/PycharmProjects/mnist/mnist.py", line 97, in loss
    concated = tf.concat(1, [indices, labels])
  File "/opt/modules/anaconda3/envs/mnist/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py", line 1122, in concat
    tensor_shape.scalar())
  File "/opt/modules/anaconda3/envs/mnist/lib/python3.6/site-packages/tensorflow/python/framework/tensor_shape.py", line 848, in assert_is_compatible_with
    raise ValueError("Shapes %s and %s are incompatible" % (self, other))
ValueError: Shapes (2, 100, 1) and () are incompatible

解决方案：

concated = tf.concat(1, [indices, sparse_labels])改为：

concated= tf.concat([indices, sparse_labels], 1)

4.2 AttributeError: module 'tensorflow' has no attribute 'pack'

Traceback (most recent call last):
  File "/home/lee/PycharmProjects/mnist/fully_connected_feed.py", line 222, in <module>
    tf.app.run()
  File "/opt/modules/anaconda3/envs/mnist/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
    _sys.exit(main(argv))
  File "/home/lee/PycharmProjects/mnist/fully_connected_feed.py", line 218, in main
    run_training()
  File "/home/lee/PycharmProjects/mnist/fully_connected_feed.py", line 138, in run_training
    loss = mnist.loss(logits, labels_placeholder)
  File "/home/lee/PycharmProjects/mnist/mnist.py", line 99, in loss
    concated, tf.pack([batch_size, NUM_CLASSES]), 1.0, 0.0)
AttributeError: module 'tensorflow' has no attribute 'pack'

TF后面的版本修改了这个函数的名称，把tf.pack改为 tf.stack，解决方案：
onehot_labels = tf.sparse_to_dense(
concated, tf.pack([batch_size, NUM_CLASSES]), 1.0, 0.0)改为：
onehot_labels = tf.sparse_to_dense(
concated, tf.stack([batch_size, NUM_CLASSES]), 1.0, 0.0)

4.3 ValueError: Only call `softmax_cross_entropy_with_logits` with named arguments (labels=..., logits=..., ...)

WARNING:tensorflow:From /home/lee/PycharmProjects/mnist/mnist.py:102: softmax_cross_entropy_with_logits (from tensorflow.python.ops.nn_ops) is deprecated and will be removed in a future version.
Instructions for updating:

Future major versions of TensorFlow will allow gradients to flow
into the labels input on backprop by default.

See `tf.nn.softmax_cross_entropy_with_logits_v2`.

Traceback (most recent call last):
  File "/home/lee/PycharmProjects/mnist/fully_connected_feed.py", line 222, in <module>
    tf.app.run()
  File "/opt/modules/anaconda3/envs/mnist/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
    _sys.exit(main(argv))
  File "/home/lee/PycharmProjects/mnist/fully_connected_feed.py", line 218, in main
    run_training()
  File "/home/lee/PycharmProjects/mnist/fully_connected_feed.py", line 138, in run_training
    loss = mnist.loss(logits, labels_placeholder)
  File "/home/lee/PycharmProjects/mnist/mnist.py", line 102, in loss
    name='xentropy')
  File "/opt/modules/anaconda3/envs/mnist/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 306, in new_func
    return func(*args, **kwargs)
  File "/opt/modules/anaconda3/envs/mnist/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 1971, in softmax_cross_entropy_with_logits
    logits)
  File "/opt/modules/anaconda3/envs/mnist/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 1783, in _ensure_xent_args
    "named arguments (labels=..., logits=..., ...)" % name)
ValueError: Only call `softmax_cross_entropy_with_logits` with named arguments (labels=..., logits=..., ...)

解决方案为：
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits,
onehot_labels,
name='xentropy')改为：
cross_entropy = tf.nn.softmax_cross_entropy_with_logits_v2(logits=logits,
labels=onehot_labels,
name='xentropy')

4.4 AttributeError: module 'tensorflow' has no attribute 'scalar_summary'

Traceback (most recent call last):
  File "/home/lee/PycharmProjects/mnist/fully_connected_feed.py", line 222, in <module>
    tf.app.run()
  File "/opt/modules/anaconda3/envs/mnist/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
    _sys.exit(main(argv))
  File "/home/lee/PycharmProjects/mnist/fully_connected_feed.py", line 218, in main
    run_training()
  File "/home/lee/PycharmProjects/mnist/fully_connected_feed.py", line 141, in run_training
    train_op = mnist.training(loss, FLAGS.learning_rate)
  File "/home/lee/PycharmProjects/mnist/mnist.py", line 120, in training
    tf.scalar_summary(loss.op.name, loss)
AttributeError: module 'tensorflow' has no attribute 'scalar_summary'

解决方案为：
tf.scalar_summary(loss.op.name, loss)改为：tf.summary.scalar(loss.op.name, loss)

4.5 AttributeError: module 'tensorflow' has no attribute 'merge_all_summaries'

Traceback (most recent call last):
  File "/home/lee/PycharmProjects/mnist/fully_connected_feed.py", line 222, in <module>
    tf.app.run()
  File "/opt/modules/anaconda3/envs/mnist/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
    _sys.exit(main(argv))
  File "/home/lee/PycharmProjects/mnist/fully_connected_feed.py", line 218, in main
    run_training()
  File "/home/lee/PycharmProjects/mnist/fully_connected_feed.py", line 147, in run_training
    summary_op = tf.merge_all_summaries()
AttributeError: module 'tensorflow' has no attribute 'merge_all_summaries'

解决方案为：
summary_op = tf.merge_all_summaries()改为：summary_op = tf.summary.merge_all()

4.6 AttributeError: module 'tensorflow.train' has no attribute 'SummaryWriter'

WARNING:tensorflow:From /opt/modules/anaconda3/envs/mnist/lib/python3.6/site-packages/tensorflow/python/util/tf_should_use.py:189: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.
Instructions for updating:
Use `tf.global_variables_initializer` instead.
Traceback (most recent call last):
  File "/home/lee/PycharmProjects/mnist/fully_connected_feed.py", line 222, in <module>
    tf.app.run()
  File "/opt/modules/anaconda3/envs/mnist/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
    _sys.exit(main(argv))
  File "/home/lee/PycharmProjects/mnist/fully_connected_feed.py", line 218, in main
    run_training()
  File "/home/lee/PycharmProjects/mnist/fully_connected_feed.py", line 160, in run_training
    summary_writer = tf.train.SummaryWriter(FLAGS.train_dir,
AttributeError: module 'tensorflow.train' has no attribute 'SummaryWriter'

解决方案为：
(1) init=initialize_all_variables改为：init = tf.global_variables_initializer
(2) summary_writer = tf.summary.FileWriter(FLAGS.train_dir,graph_def=sess.graph_def)改为：summary_writer = tf.summary.FileWriter(FLAGS.train_dir,graph_def=sess.graph_def)

4.7 WARNING:tensorflow:Passing a `GraphDef` to the SummaryWriter is deprecated

WARNING:tensorflow:Passing a `GraphDef` to the SummaryWriter is deprecated. Pass a `Graph` object instead, such as `sess.graph`.

summary_writer = tf.summary.FileWriter(FLAGS.train_dir,graph_def=sess.graph_def)修改为：
summary_writer = tf.summary.FileWriter(FLAGS.train_dir,sess.graph)

参考文章

http://www.tensorfly.cn/tfdoc/tutorials/mnist_beginners.html

https://www.cnblogs.com/welhzh/p/6595032.html