Tensorflow初探之MNIST数据集学习

官方文档传送门

MNIST数据集是手写数字0~9的数据集，一般被用作机器学习领域的测试，相当于HelloWorld级别。

本程序先从网上导入数据，再利用最小梯度法进行训练使得样本交叉熵最小，最后给出训练之后程序的准确率。

交叉熵的定义：

y 是我们预测的概率分布, y' 是实际的分布。

该指标用来衡量学习结果与实际情况的差距。

import tensorflow.examples.tutorials.mnist.input_data as input_data
import tensorflow as tf
#initialize
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
y = tf.nn.softmax(tf.matmul(x,W) + b)
y_ = tf.placeholder("float", [None,10])
cross_entropy = -tf.reduce_sum(y_*tf.log(y))
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
#train
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
for i in range(1000):batch_xs, batch_ys = mnist.train.next_batch(100)sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
#predict
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))

先用placeholder和variable初始化。

placeholder(占位符)一般用于导入数据，而Variable一般是与学习过程相关的变量。

之后，启动Session进行训练，本程序当中随机选取了100张图片进行训练。

最后运行的准确率为91.49%.

/home/jcole/PycharmProjects/MNIST-HelloWorld/venv/bin/python /home/jcole/PycharmProjects/MNIST-HelloWorld/venv/MNIST.py
WARNING:tensorflow:From /home/jcole/PycharmProjects/MNIST-HelloWorld/venv/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/datasets/base.py:198: retry (from tensorflow.contrib.learn.python.learn.datasets.base) is deprecated and will be removed in a future version.
Instructions for updating:
Use the retry module or similar alternatives.
WARNING:tensorflow:From /home/jcole/PycharmProjects/MNIST-HelloWorld/venv/MNIST.py:4: read_data_sets (from tensorflow.contrib.learn.python.learn.datasets.mnist) is deprecated and will be removed in a future version.
Instructions for updating:
Please use alternatives such as official/mnist/dataset.py from tensorflow/models.
WARNING:tensorflow:From /home/jcole/PycharmProjects/MNIST-HelloWorld/venv/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/datasets/mnist.py:260: maybe_download (from tensorflow.contrib.learn.python.learn.datasets.base) is deprecated and will be removed in a future version.
Instructions for updating:
Please write your own downloading logic.
WARNING:tensorflow:From /home/jcole/PycharmProjects/MNIST-HelloWorld/venv/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/datasets/base.py:219: retry.<locals>.wrap.<locals>.wrapped_fn (from tensorflow.contrib.learn.python.learn.datasets.base) is deprecated and will be removed in a future version.
Instructions for updating:
Please use urllib or similar directly.
Successfully downloaded train-images-idx3-ubyte.gz 9912422 bytes.
Extracting MNIST_data/train-images-idx3-ubyte.gz
WARNING:tensorflow:From /home/jcole/PycharmProjects/MNIST-HelloWorld/venv/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/datasets/mnist.py:262: extract_images (from tensorflow.contrib.learn.python.learn.datasets.mnist) is deprecated and will be removed in a future version.
Instructions for updating:
Please use tf.data to implement this functionality.
WARNING:tensorflow:From /home/jcole/PycharmProjects/MNIST-HelloWorld/venv/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/datasets/mnist.py:267: extract_labels (from tensorflow.contrib.learn.python.learn.datasets.mnist) is deprecated and will be removed in a future version.
Instructions for updating:
Please use tf.data to implement this functionality.
WARNING:tensorflow:From /home/jcole/PycharmProjects/MNIST-HelloWorld/venv/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/datasets/mnist.py:110: dense_to_one_hot (from tensorflow.contrib.learn.python.learn.datasets.mnist) is deprecated and will be removed in a future version.
Instructions for updating:
Please use tf.one_hot on tensors.
Successfully downloaded train-labels-idx1-ubyte.gz 28881 bytes.
Extracting MNIST_data/train-labels-idx1-ubyte.gz
Successfully downloaded t10k-images-idx3-ubyte.gz 1648877 bytes.
Extracting MNIST_data/t10k-images-idx3-ubyte.gz
Successfully downloaded t10k-labels-idx1-ubyte.gz 4542 bytes.
WARNING:tensorflow:From /home/jcole/PycharmProjects/MNIST-HelloWorld/venv/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/datasets/mnist.py:290: DataSet.__init__ (from tensorflow.contrib.learn.python.learn.datasets.mnist) is deprecated and will be removed in a future version.
Extracting MNIST_data/t10k-labels-idx1-ubyte.gz
Instructions for updating:
Please use alternatives such as official/mnist/dataset.py from tensorflow/models.
WARNING:tensorflow:From /home/jcole/PycharmProjects/MNIST-HelloWorld/venv/lib/python3.5/site-packages/tensorflow/python/util/tf_should_use.py:118: 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.
2018-04-23 16:27:25.917321: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
0.9149Process finished with exit code 0

Tensorflow初探之MNIST数据集学习相关推荐

基于tensorflow+RNN的MNIST数据集手写数字分类
2018年9月25日笔记 tensorflow是谷歌google的深度学习框架,tensor中文叫做张量,flow叫做流. RNN是recurrent neural network的简称,中文叫做循环 ...
MNIST数据集学习
第一章提到,最常见的监督式学习任务包括回归任务(预测值)和分类任务(预测类). 第二章探讨了一个回归任务–预测住房价格,用到了线性回归.决策树以及随机森林等各种算法(我们会在后续章节中进一步讲解这些算 ...
tensorflow 自编码器 MNIST数据集
写在前头这段时间在学习利用tensorflow编写自编码器代码,在B站上看到了一个教学视频,觉得很有用,但很遗憾视频的画质和声音都有点渣,UP主也没有提供源代码,我在网上搜了下,也没找到,因此自己根 ...
北京大学曹健——Tensorflow笔记 05 MNIST数据集输出手写数字识别准确率
# 前向传播:描述了网络结构 minist_forward.py # 反向传播:描述了模型参数的优化方法 mnist_backward.py # 测试输出准确率minist_tes ...
tensorflow（七）实现mnist数据集上图片的训练和测试
本文使用tensorflow实现在mnist数据集上的图片训练和测试过程,使用了简单的两层神经网络,代码中涉及到的内容,均以备注的形式标出. 关于文中的数据集,大家如果没有下载下来,可以到我的网盘去下 ...
主成分分析降维（MNIST数据集）
北京 | 高性能计算之GPU CUDA课程11月24-26日3天密集学习快速带你晋级阅读全文> 刘凯欣,中国矿业大学在校学生,曾参加过ThoughtWorks举办的结对编程活动. 今天看了用主 ...
深度学习之利用TensorFlow实现简单的卷积神经网络（MNIST数据集）
卷积神经网络(Convolutional Neural Networks, CNN)是一类包含卷积计算且具有深度结构的前馈神经网络(Feedforward Neural Networks),是深度学习 ...
TensorFlow：实战Google深度学习框架（四）MNIST数据集识别问题
第5章 MNIST数字识别问题 5.1 MNIST数据处理 5.2 神经网络的训练以及不同模型结果的对比 5.2.1 TensorFlow训练神经网络 5.2.2 使用验证数据集判断模型的效果 5.2 ...
深度学习4：使用MNIST数据集（tensorflow）
本文将介绍MNIST数据集的数据格式和使用方法,使用到的是tensorflow中封装的类,包含代码. MNIST数据集来源于这里, 如果希望下载原始格式的数据集,可以从这里下载.而本文中讲解的是已经使 ...

Tensorflow初探之MNIST数据集学习

Tensorflow初探之MNIST数据集学习相关推荐

最新文章

热门文章