easy_install pip virtualenv tensorenv source bin/activate #pip install tensorflow #pip install --upgrade https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.8.0-cp27-none-linux_x86_64.whl #easy_install --upgrade six #pip install --upgrade pip #pip install six #pip install matplotlib pip install --upgrade tensorflow
helloworld
(tensorflow)$ cd tensorflow/models/image/mnist
(tensorflow)$ python convolutional.py
>>> import tensorflow as tf
>>> hello = tf.constant('hello TensorFlow!')
>>> sess = tf.Session()
>>> print sess.run(hello)
hello TensorFlow!
>>> a = tf.constant(10)
>>> b = tf.constant(32)
>>> print sess.run(a+b)
42
cd tensorenv/lib/python2.7/site-packages/tensorflow/models/image/mnist
python convolutional.py
基本概念
https://blog.csdn.net/ls617386/article/details/60572770
基本用法
http://wiki.jikexueyuan.com/project/tensorflow-zh/get_started/basic_usage.html
deepspeaker
gmm
Kaldi
Caffe
测试集的使用
下载MNIST训练集
http://wiki.jikexueyuan.com/project/tensorflow-zh/tutorials/mnist_beginners.html
gzip -d * 解压四个文件
安装生成图片的必要的库
yum install libpng-devel freetype-devel -y pip install matplotlib xxd t10k-images-idx3-ubyte |less hexdump t10k-images-idx3-ubyte |less yum install libjpeg yum install libjpeg-devel -y pip install pillow
把数据生成图片
参考
https://blog.csdn.net/u010194274/article/details/50817999
#
encoding: utf-8
import struct
import numpy as np
import matplotlib.pyplot as plt
#import Image
from PIL import Image
#二进制的形式读入
filename='./MNIST_data_back/train-images-idx3-ubyte'
binfile=open(filename,'rb')
buf=binfile.read()
#大端法读入4个unsigned int32
#struct用法参见网站 http://www.cnblogs.com/gala/archive/2011/09/22/2184801.html
index=0
magic,numImages,numRows,numColumns=struct.unpack_from('>IIII',buf,index)
index+=struct.calcsize('>IIII')
#将每张图片按照格式存储到对应位置
for image in range(0,numImages):
im=struct.unpack_from('>784B',buf,index)
index+=struct.calcsize('>784B')
#这里注意 Image对象的dtype是uint8，需要转换
im=np.array(im,dtype='uint8')
im=im.reshape(28,28)
# fig=plt.figure()
# plotwindow=fig.add_subplot(111)
# plt.imshow(im,cmap='gray')
# plt.show()
im=Image.fromarray(im)
im.save('train/train_%s.bmp'%image,'bmp')
如果是解析
参考 https://www.jianshu.com/p/84f72791806f
# encoding: utf-8 """ @author: monitor1379 @contact: [email protected] @site: www.monitor1379.com @version: 1.0 @license: Apache Licence @file: mnist_decoder.py @time: 2016/8/16 20:03 对MNIST手写数字数据文件转换为bmp图片文件格式。 数据集下载地址为http://yann.lecun.com/exdb/mnist。 相关格式转换见官网以及代码注释。 ======================== 关于IDX文件格式的解析规则： ======================== THE IDX FILE FORMAT the IDX file format is a simple format for vectors and multidimensional matrices of various numerical types. The basic format is magic number size in dimension 0 size in dimension 1 size in dimension 2 ..... size in dimension N data The magic number is an integer (MSB first). The first 2 bytes are always 0. The third byte codes the type of the data: 0x08: unsigned byte 0x09: signed byte 0x0B: short (2 bytes) 0x0C: int (4 bytes) 0x0D: float (4 bytes) 0x0E: double (8 bytes) The 4-th byte codes the number of dimensions of the vector/matrix: 1 for vectors, 2 for matrices.... The sizes in each dimension are 4-byte integers (MSB first, high endian, like in most non-Intel processors). The data is stored like in a C array, i.e. the index in the last dimension changes the fastest. """ import numpy as np import struct import matplotlib.pyplot as plt # 训练集文件 train_images_idx3_ubyte_file = './MNIST_data_back/train-images-idx3-ubyte' # 训练集标签文件 train_labels_idx1_ubyte_file = './MNIST_data_back/train-labels-idx1-ubyte' # 测试集文件 test_images_idx3_ubyte_file = './MNIST_data_back/t10k-images-idx3-ubyte' # 测试集标签文件 test_labels_idx1_ubyte_file = './MNIST_data_back/t10k-labels-idx1-ubyte' def decode_idx3_ubyte(idx3_ubyte_file): """ 解析idx3文件的通用函数 :param idx3_ubyte_file: idx3文件路径 :return: 数据集 """ # 读取二进制数据 bin_data = open(idx3_ubyte_file, 'rb').read() # 解析文件头信息，依次为魔数、图片数量、每张图片高、每张图片宽 offset = 0 fmt_header = '>iiii' magic_number, num_images, num_rows, num_cols = struct.unpack_from(fmt_header, bin_data, offset) print '魔数:%d, 图片数量: %d张, 图片大小: %d*%d' % (magic_number, num_images, num_rows, num_cols) # 解析数据集 image_size = num_rows * num_cols offset += struct.calcsize(fmt_header) fmt_image = '>' + str(image_size) + 'B' images = np.empty((num_images, num_rows, num_cols)) for i in range(num_images): if (i + 1) % 10000 == 0: print '已解析 %d' % (i + 1) + '张' images[i] = np.array(struct.unpack_from(fmt_image, bin_data, offset)).reshape((num_rows, num_cols)) offset += struct.calcsize(fmt_image) return images def decode_idx1_ubyte(idx1_ubyte_file): """ 解析idx1文件的通用函数 :param idx1_ubyte_file: idx1文件路径 :return: 数据集 """ # 读取二进制数据 bin_data = open(idx1_ubyte_file, 'rb').read() # 解析文件头信息，依次为魔数和标签数 offset = 0 fmt_header = '>ii' magic_number, num_images = struct.unpack_from(fmt_header, bin_data, offset) print '魔数:%d, 图片数量: %d张' % (magic_number, num_images) # 解析数据集 offset += struct.calcsize(fmt_header) fmt_image = '>B' labels = np.empty(num_images) for i in range(num_images): if (i + 1) % 10000 == 0: print '已解析 %d' % (i + 1) + '张' labels[i] = struct.unpack_from(fmt_image, bin_data, offset)[0] offset += struct.calcsize(fmt_image) return labels def load_train_images(idx_ubyte_file=train_images_idx3_ubyte_file): """ TRAINING SET IMAGE FILE (train-images-idx3-ubyte): [offset] [type] [value] [description] 0000 32 bit integer 0x00000803(2051) magic number 0004 32 bit integer 60000 number of images 0008 32 bit integer 28 number of rows 0012 32 bit integer 28 number of columns 0016 unsigned byte ?? pixel 0017 unsigned byte ?? pixel ........ xxxx unsigned byte ?? pixel Pixels are organized row-wise. Pixel values are 0 to 255. 0 means background (white), 255 means foreground (black). :param idx_ubyte_file: idx文件路径 :return: n*row*col维np.array对象，n为图片数量 """ return decode_idx3_ubyte(idx_ubyte_file) def load_train_labels(idx_ubyte_file=train_labels_idx1_ubyte_file): """ TRAINING SET LABEL FILE (train-labels-idx1-ubyte): [offset] [type] [value] [description] 0000 32 bit integer 0x00000801(2049) magic number (MSB first) 0004 32 bit integer 60000 number of items 0008 unsigned byte ?? label 0009 unsigned byte ?? label ........ xxxx unsigned byte ?? label The labels values are 0 to 9. :param idx_ubyte_file: idx文件路径 :return: n*1维np.array对象，n为图片数量 """ return decode_idx1_ubyte(idx_ubyte_file) def load_test_images(idx_ubyte_file=test_images_idx3_ubyte_file): """ TEST SET IMAGE FILE (t10k-images-idx3-ubyte): [offset] [type] [value] [description] 0000 32 bit integer 0x00000803(2051) magic number 0004 32 bit integer 10000 number of images 0008 32 bit integer 28 number of rows 0012 32 bit integer 28 number of columns 0016 unsigned byte ?? pixel 0017 unsigned byte ?? pixel ........ xxxx unsigned byte ?? pixel Pixels are organized row-wise. Pixel values are 0 to 255. 0 means background (white), 255 means foreground (black). :param idx_ubyte_file: idx文件路径 :return: n*row*col维np.array对象，n为图片数量 """ return decode_idx3_ubyte(idx_ubyte_file) def load_test_labels(idx_ubyte_file=test_labels_idx1_ubyte_file): """ TEST SET LABEL FILE (t10k-labels-idx1-ubyte): [offset] [type] [value] [description] 0000 32 bit integer 0x00000801(2049) magic number (MSB first) 0004 32 bit integer 10000 number of items 0008 unsigned byte ?? label 0009 unsigned byte ?? label ........ xxxx unsigned byte ?? label The labels values are 0 to 9. :param idx_ubyte_file: idx文件路径 :return: n*1维np.array对象，n为图片数量 """ return decode_idx1_ubyte(idx_ubyte_file) def run(): train_images = load_train_images() train_labels = load_train_labels() # test_images = load_test_images() # test_labels = load_test_labels() # 查看前十个数据及其标签以读取是否正确 for i in range(10): print train_labels[i] plt.imshow(train_images[i], cmap='gray') plt.show() print 'done' if __name__ == '__main__': run()
- 查看图片附件