from tensorflow.examples.tutorials.mnist.input_data import read_data_sets
import numpy as np
import cv2
SAMPLES_PATH ='./MNIST_data'deftemp_reshape_transpose():
x = np.random.randint(0,10, size=[64,64])for row in x:print('[', end='')for e in row:print(e, end=' ')print(']')
x = np.reshape(x,[64,32,2])
x = np.transpose(x,[1,0,2])# [32, 64, 2]
x = np.reshape(x,[32,32,4])# [32, 32, 4]
x = np.max(x, axis=2)# [32, 32]
x = np.transpose(x,[1,0])print('-'*200)for row in x:print('[', end='')for e in row:print(e, end=' ')print(']')if __name__ =='__main__':
ds =read_data_sets(SAMPLES_PATH)print(ds.train.num_examples)#55000print(ds.validation.num_examples)#5000print(ds.test.num_examples)#10000
xs,ys = ds.train.next_batch(200)#print(xs[0])# xs: [200, 784],28X28# ys: [200]print(ys)#xs = np.reshape(xs,[-1,28])#设置可视化长宽度28*28,此宽度看着手写数字比较合适,#可以看到是一个数字一行
xs = np.reshape(xs,[-1,28,28])
xs = np.transpose(xs,[1,0,2])#[28,-1,28]
xs = np.reshape(xs,[28,-1,28*20])#[28,-1,560]
xs = np.transpose(xs,[1,0,2])#[-1,28,560]
xs = np.reshape(xs,[-1,28*20])#变成了10行20列的数字print("*"*200)
temp_reshape_transpose()
cv2.imshow('My digits',xs)
cv2.waitKey()
D:\Anaconda\python.exe D:/AI20/06_codes/deeplearning_20/p25_mnist/mnist01.py
WARNING:tensorflow:From D:/AI20/06_codes/deeplearning_20/p25_mnist/mnist01.py:32: 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 D:\Anaconda\lib\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 D:\Anaconda\lib\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.
Extracting ./MNIST_data\train-images-idx3-ubyte.gz
Extracting ./MNIST_data\train-labels-idx1-ubyte.gz
Extracting ./MNIST_data\t10k-images-idx3-ubyte.gz
WARNING:tensorflow:From D:\Anaconda\lib\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.
Extracting ./MNIST_data\t10k-labels-idx1-ubyte.gz
WARNING:tensorflow:From D:\Anaconda\lib\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.
Instructions for updating:
Please use alternatives such as official/mnist/dataset.py from tensorflow/models.55000500010000[65816429952724002027154097090302170611942684197437922496616798614046879970732433636086169240551487201878877875784827628139093864474396845623564289881754870427511432076708517431550568009099573953290085]********************************************************************************************************************************************************************************************************[1338161992198418369446529932978981384640106391918206508837813681][5059743233106752691036579485390859864809727594499568589688826667][2858099694930614851232953908509725531410537301721381256034388420][0989479186943887913331123331669163776206355106626319823987740615][2475826020612733709841837257732699366185226564160079738280695838][5384152539113180817664795288985263017510107861401556886730791193][4602171702342868236874562452428463358515474566111623970725236106][0284420273297575756747399913895328652304719562871981126625409751][6306446591500415791247453606514323661221085434342424154671778872][0200970784744527551593609156268361130218548275344915148516655333][4627170626647440306657392298703732123665096822617092699540854489][0828671639212696094523042903589727022797455044180528634785818733][4125525143032299225177194303258554860042145312945427254429226618][2859446595364685544632655088959577646497092543006129628987045600][2596182594225478811394793624260832535700599237944859426126204031][0548284577628410639113558927641111756350027722954972423636199378][4384406201535379601262795935112769409459452421758373575597430943][8175774591283742863098442619259924590298814978622745541456077709][3795886291497121557587637878614018017200634756669465863447845588][5991106132965417547024023099454705180314016733723128496289287975][1051253886344862632061463473901587243144231529029162829776717304][6058438160897933541392384659525562396514269670068285592959599326][5929036747401492388282715421622455291549273543408991944716122263][0163631638831667969613548169149535020544250891047305307382586801][0702070291765161069604320170916306646669172730854480141336099008][6326908766579079629409150221128133777083351831572255821892743703][5355764070216531588720879181637146185656640868796325638515408893][9902752081707307486765423284903181119794449101334401506149874864][5747317429375050089231377856073105946179003528316110489142914875][6224946232661675666529099867453450787151979554503785270992254737][7688590956962520991746098861129559769700154639701684139773861815][4464008507531493695336574606444258240205399535783654546950115184][3370166677305812176348246644306785915193334930741075788324147243][0794824536879053885233914120629711689448500945138416910873374963][5281546525369546719791905846407396907300591224987922192513712121][5480311233786053774213926483302774895040542481712707257464626293][7201642204866962917643487470696765073681410088862610555163444567][6738246159323154570297772445254484380991186155806749803663788398][2319649413009907917288653997023692159261342814102877071825046934][8382389850292198571459285198599712597308601675189411481278032370][6486156232888133830341451866118670005343328562103890315346825673][5005983726455736083347429007503594099211988509580255274671310022][0155393501977213405013070507134843026096812686723646817210815994][9368495812177357388313750199687890224583389404289101853305671957][6883086084748974234398370225192755818957551482725325783700624636][4707353740881026074823445759860509941465843131110523894708370901][1121222774782649457750460825510195280633989065465904994389300366][6893554628464960007543300491269967590472264405806350043029958713][5050999855293741113110786859370973257572823654858996120040710219][0471649981537595846252867317059442798379033075963656700714580176][7569464466656762015176599932816984550946412273114986679486485024][5056303562578186249247877835912696709635974272538676191481722505][8069679929332560759656650477901130171349187904678445126599873504][5296073763680778937344154532769379414267257801874725635592662729][6433569126303987224700476509379658615468383443112930076398907329][6040226108091090325687821978372293000404700718817602643367150828][1136684445059941405649598061043180488370132390706784968001631000][7633887839708800091594772106891437958419049841436365794278501999][1877984974614233574396288941485045100650275052197599370398569673][5315377384977003459767170788369636553272399993867016107454301068][6438240965750317277442907447364056313324908175499013780279283859][7978163009456711604575359179105347655562272374901859793246889001][3397810805663015129962275329025132096040264258240059113310203245][6630005006682836250500541163362203348479212051935520162911693050]--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------[59799988996798999889779998898868][99999988933998696766576769898885][58869678896978969678286659888989][68777988787995988685796898975496][66979757959696686628887495587787][88769679967999897279984879998889][89569669567958997869954969699468][59859688899997683775997999466998][88769879839999599999898787759799][99869977578689678874676798969898][68588996639869958964699698999996][99678869998789695959789499978886][76989799699527986779783848889998][95748777886898978899698965689889][77979767899997745979998578899987][78997959976986499795999868597888][79867895868964698999595787987796][58565896799988479974948997976769][78669896979877978899868879866889][89895999979899999998687897888497][68976886837597589994989889767867][98982977883759889269898896875899][88878897789779979997848755978796][89578899575689699967996895949986][57998979865889797989867999774829][79656788497995999796947598998855][89799878996657999749894885669879][64698999378899799658878893769989][76889794969986948989499778988699][87998973799898896567999979779698][98699777777999657656987999939899][69886886596759653989648959691935]
Process finished with exit code 0