(4)tensorflow数据索引与切片

最新推荐文章于 2022-07-18 09:07:32 发布

小蜗笔记

最新推荐文章于 2022-07-18 09:07:32 发布

阅读量310

点赞数

分类专栏： Tensorflow基础入门

本文链接：https://blog.csdn.net/qq_42830971/article/details/108168224

版权

Tensorflow基础入门专栏收录该内容

29 篇文章 1 订阅

订阅专栏

数据索引与切片

索引

通过随机数模拟输入x为 5张6 × 6大小的彩色图片, 张量表达为x[5,6,6,3]
x[k][m][n][h] 与 x[k,m,n,h]表达方式等价

import tensorflow as tf
x = tf.random.normal([5,6,6,3])
print(x[1])   #索引第1张图片
print(x[1,2]) #索引第2张图片第3行
print(x[1,2,3])#索引第2张图片第3行第4列
print(x[1,2,3,2])#索引第2张图片第3行第4列第3个元素

out:
tf.Tensor(
[[[-0.91212404 -2.0427992  -0.46262553]
  [-0.20069174 -0.05861099  0.11027909]
  [-1.0540271   0.07322102  2.559264  ]
  [-0.03430535  0.12940659  0.06428348]
  [ 0.6088471   0.5363448   3.1524873 ]
  [ 0.02713859  0.39051694 -0.34645185]]

 [[ 1.1095203  -0.15183792  0.5406034 ]
  [-0.54709756  0.6370621   0.8347229 ]
  [-0.73936665  0.32023484 -1.3877583 ]
  [ 1.783203    1.4412103   0.6021151 ]
  [ 2.0264266   0.10415354  1.3440856 ]
  [-0.38457033  0.47926706 -0.91988194]]

 [[-0.28226608  0.79410243  1.4675037 ]
  [ 0.83049303  3.0758872   0.8136213 ]
  [-1.0627513  -0.23855098 -0.60079205]
  [ 0.35610384 -1.6600429  -0.10547343]
  [-2.0607834  -0.4370456   1.1417316 ]
  [-0.16526382 -0.3777384   1.650753  ]]

 [[-0.0859533   2.0710986  -0.23100522]
  [ 0.7997451   0.90333855 -0.54443187]
  [-1.1791725   0.29392138 -1.0544866 ]
  [ 0.48906276 -1.0226036   0.749924  ]
  [-0.19917172 -1.5447452   0.16254298]
  [-0.11428637 -0.37739387 -0.9465357 ]]

 [[-0.0104594  -0.08451813  0.3053848 ]
  [-1.4742563   0.79318255  1.5941502 ]
  [-0.0227184  -0.62140083 -1.2267344 ]
  [-0.13176128 -0.9073583   1.3964368 ]
  [ 2.7342134   0.6610965   0.01895647]
  [ 0.71866316 -1.3300588  -1.0430887 ]]

 [[-1.4389948  -1.0463942  -0.13926208]
  [-0.9728994   1.8755643   0.67373216]
  [-2.354436   -0.09357089  0.1805726 ]
  [ 0.61139655 -0.9339481  -0.52572894]
  [-0.41425255 -0.20685263 -0.72041327]
  [ 0.582748    0.4415481   1.1500107 ]]], shape=(6, 6, 3), dtype=float32)
tf.Tensor(
[[-0.28226608  0.79410243  1.4675037 ]
 [ 0.83049303  3.0758872   0.8136213 ]
 [-1.0627513  -0.23855098 -0.60079205]
 [ 0.35610384 -1.6600429  -0.10547343]
 [-2.0607834  -0.4370456   1.1417316 ]
 [-0.16526382 -0.3777384   1.650753  ]], shape=(6, 3), dtype=float32)
tf.Tensor([ 0.35610384 -1.6600429  -0.10547343], shape=(3,), dtype=float32)
tf.Tensor(-0.10547343, shape=(), dtype=float32)

切片

索引基础上通过start: end: step进行切片，不包含end

import tensorflow as tf
x = tf.random.normal([5,6,6,3])
print(x)
print(x[1:4:2])   #索引第2,4张图片
print(x[1:4,2:5]) #索引第2-3张图片第3-4行
print(x[1,2,3:6])#索引第2张图片第2行4-5列
print(x[1,2,3,:])#索引第2张图片第3行第4列第1-3个全部元素

out:
数据列出来了，不服气的小朋友慢慢数
tf.Tensor(
[[[[ 1.21995068e+00 -1.82602501e+00  7.54228652e-01]
   [-9.63172019e-01  4.07960325e-01  1.87039375e+00]
   [-2.89596528e-01  2.18894497e-01 -5.82021236e-01]
   [ 1.52084684e+00 -1.05854821e+00  5.88759840e-01]
   [-5.22327274e-02  4.00639057e-01 -1.55639076e+00]
   [ 1.48189008e+00  4.90545124e-01 -1.17132354e+00]]

  [[ 1.16303813e+00 -7.59640872e-01 -1.18237659e-01]
   [-1.57255471e-01  1.63788390e+00 -7.29934990e-01]
   [ 1.07842229e-01  2.15927623e-02  2.73860097e-01]
   [ 7.70342827e-01 -3.36311162e-01 -8.44469368e-01]
   [ 7.31797695e-01  1.70461214e+00 -1.58359504e+00]
   [ 8.03975940e-01 -1.15609241e+00  1.08483076e+00]]

  [[ 1.51283517e-01 -6.22181952e-01  7.43213117e-01]
   [-2.28845668e+00 -1.09288800e+00 -2.45538428e-01]
   [-9.15578067e-01 -2.74817848e+00 -6.78314090e-01]
   [ 2.46793061e-01 -3.51126105e-01 -5.02893150e-01]
   [ 6.39017001e-02  1.19011652e+00  9.59298253e-01]
   [ 9.83435869e-01 -3.21146190e-01 -1.85808897e+00]]

  [[-5.58637798e-01  2.74601102e-01  5.99787831e-01]
   [ 7.58920372e-01  5.14156640e-01  8.62197340e-01]
   [-3.86666596e-01 -4.55476820e-01  3.04826587e-01]
   [ 4.65631276e-01 -1.76610506e+00  1.18209505e+00]
   [-6.11416042e-01  1.02123439e+00 -1.40619785e-01]
   [ 8.24159265e-01  9.10359144e-01  4.83515501e-01]]

  [[ 1.03788424e+00 -4.62827712e-01 -5.36569059e-01]
   [ 1.38037598e+00 -7.72561610e-01 -1.53996825e+00]
   [-8.54215145e-01  2.04571700e+00 -7.85223007e-01]
   [ 1.84613872e+00 -2.25179434e+00  2.78542414e-02]
   [ 1.71851516e-01 -9.38572407e-01  1.69299769e+00]
   [-2.18426085e+00 -8.14803004e-01  2.68277359e+00]]

  [[-1.63348699e+00 -5.75200558e-01 -2.33097777e-01]
   [-4.82167870e-01 -1.14078283e+00  3.76927048e-01]
   [-1.07462680e+00 -7.01448843e-02  6.99388325e-01]
   [ 1.95185542e-01 -3.38425696e-01  4.83320877e-02]
   [-8.92554447e-02  1.96258581e+00 -2.74416184e+00]
   [ 1.95600331e+00  1.23645045e-01  5.74126184e-01]]]


 [[[ 1.87568888e-01 -9.05686915e-01  1.92977977e+00]
   [ 9.11024287e-02  6.23378754e-01 -1.09670031e+00]
   [-1.39939582e+00 -1.00379653e-01  3.61826062e-01]
   [ 4.95849490e-01 -1.21929228e+00  2.02186614e-01]
   [-9.45614055e-02  1.49201274e+00 -7.97860980e-01]
   [ 1.47168243e+00 -1.07721651e+00 -1.07484353e+00]]

  [[ 1.93246994e-02 -4.47692610e-02  2.16924191e-01]
   [-1.59404904e-01  1.77266356e-02 -1.19980514e+00]
   [ 2.56454498e-01 -1.93552411e+00 -2.78844774e-01]
   [-2.11205080e-01  8.01900208e-01 -7.95955718e-01]
   [-1.10443056e+00  9.17201042e-01  3.34371686e-01]
   [ 8.29509139e-01 -1.46660089e+00 -1.02417874e+00]]

  [[-7.60529280e-01  1.97552228e+00 -1.02420533e+00]
   [ 7.27354765e-01  5.60459554e-01 -4.93120193e-01]
   [-1.72625124e+00  2.56123155e-01 -1.69175613e+00]
   [ 7.67536342e-01 -8.13769847e-02 -8.31038952e-01]
   [ 2.49379444e+00  7.14681685e-01 -1.13818312e+00]
   [ 7.62467146e-01  7.60188639e-01  2.27576599e-01]]

  [[ 8.11537862e-01 -1.73559570e+00  4.82792139e-01]
   [-8.10701668e-01 -1.77008879e+00  3.07443857e+00]
   [ 1.26510334e+00  1.78836977e+00  1.19583404e+00]
   [ 2.20478907e-01  1.05564153e+00 -2.50364020e-02]
   [-3.47511798e-01  1.93252003e+00 -1.00490141e+00]
   [ 5.87290347e-01  3.04456204e-01 -5.29687166e-01]]

  [[ 4.23865765e-02  1.06133819e+00  5.35515785e-01]
   [-2.54426012e-03 -5.86938500e-01  5.35167575e-01]
   [-3.23457927e-01 -4.12681818e-01 -7.32864916e-01]
   [ 7.40105450e-01 -7.75660157e-01  9.32435632e-01]
   [ 1.66822493e+00 -9.69057441e-01 -9.50969011e-02]
   [ 2.95461893e-01 -7.14342415e-01 -2.67090887e-01]]

  [[-2.46500410e-02  3.10926765e-01  9.75172579e-01]
   [ 6.02231920e-01 -4.95087773e-01  6.44952476e-01]
   [ 1.40725851e+00 -1.21028149e+00 -1.24190554e-01]
   [ 3.04605424e-01 -1.33452094e+00  7.74351239e-01]
   [ 4.93379474e-01 -4.03011709e-01  2.44138032e-01]
   [ 8.14318731e-02 -1.17603682e-01  6.78545296e-01]]]


 [[[ 8.75092804e-01 -1.10378023e-02 -1.01706874e+00]
   [-7.95813739e-01  8.59931648e-01 -1.62870729e+00]
   [-2.87507463e+00  5.76485461e-03  1.20340645e+00]
   [ 1.35247633e-01 -9.74470615e-01 -7.66023219e-01]
   [-2.67201960e-01 -1.26797646e-01 -5.76727875e-02]
   [ 5.52461505e-01  2.07091165e+00  1.54172629e-01]]

  [[-4.34081554e-01  3.19299132e-01  1.48354077e+00]
   [ 1.04536772e+00  2.52427757e-02  4.75366235e-01]
   [ 1.36828899e+00  1.25927353e+00  7.55341709e-01]
   [ 1.48851007e-01  2.37889871e-01  7.09099829e-01]
   [ 1.44865379e-01 -1.61129105e+00  4.75254953e-01]
   [-1.79089522e+00  1.41933584e+00 -7.83861279e-01]]

  [[-1.10588348e+00 -9.94613230e-01  6.00860000e-01]
   [-2.44121149e-01 -7.15020061e-01  2.79501170e-01]
   [ 7.11960375e-01  1.29095876e+00  1.84043765e+00]
   [ 1.45472002e+00 -6.26912475e-01 -1.80779129e-01]
   [ 6.90204024e-01 -8.66856337e-01 -7.01095581e-01]
   [ 6.63630009e-01  3.05033833e-01 -2.54252166e-01]]

  [[ 4.11499709e-01  4.68432695e-01 -4.64654088e-01]
   [-5.89771092e-01 -4.17504102e-01 -1.49989581e+00]
   [-1.52413952e+00 -1.34892929e+00 -2.44500235e-01]
   [ 6.24343753e-01  1.79490769e+00  2.30400085e+00]
   [-8.64937484e-01  9.41639602e-01 -9.68136936e-02]
   [ 5.26732922e-01 -5.71692228e-01 -1.98144436e-01]]

  [[-6.78959012e-01  4.88408148e-01  1.63855064e+00]
   [ 1.55291367e+00  7.07992435e-01 -6.87405169e-01]
   [-2.72624850e+00 -5.42363107e-01 -5.62665999e-01]
   [-1.43916875e-01  4.66028571e-01 -3.20459992e-01]
   [-8.61000240e-01 -1.44493163e+00  1.58243462e-01]
   [ 9.35931280e-02 -7.95558393e-01  9.83834803e-01]]

  [[ 6.75981164e-01  1.21164608e+00 -1.11420369e-02]
   [ 7.67833948e-01 -3.05648237e-01 -2.18352437e-01]
   [ 1.22868645e+00  1.11119497e+00 -4.35290277e-01]
   [ 1.13787398e-01 -3.51443172e-01 -3.52215797e-01]
   [ 1.46461308e-01 -9.92367044e-02  6.39443576e-01]
   [ 1.64520514e+00  6.30294859e-01 -5.83436370e-01]]]


 [[[-7.56267607e-02  5.40018022e-01 -2.81866968e-01]
   [ 8.24308753e-01 -7.99638987e-01 -4.43951219e-01]
   [-1.46431461e-01 -1.97807586e+00  1.93104672e+00]
   [-4.39257413e-01  1.18934357e+00 -8.08273673e-01]
   [-3.95637989e-01  3.10701430e-01  1.16561759e+00]
   [-1.08877070e-01  6.23527288e-01  1.46148145e+00]]

  [[-2.30798975e-01  3.11027914e-01  6.36408150e-01]
   [-1.82630539e+00 -1.03319860e+00 -5.85951388e-01]
   [-4.45587397e-01  4.79556441e-01 -5.13381064e-01]
   [-1.71187177e-01  2.39717454e-01  9.58223641e-01]
   [ 9.40057397e-01 -9.00054991e-01 -1.27614081e+00]
   [ 2.52930578e-02  8.43691528e-01  5.50522625e-01]]

  [[ 8.89593899e-01  9.35105801e-01 -9.42700207e-01]
   [-1.46005559e+00 -1.20610738e+00  3.50007653e-01]
   [ 1.09740973e+00  2.77690023e-01  1.95056105e+00]
   [ 1.55103588e+00 -5.41439414e-01 -6.09899759e-01]
   [ 1.14235699e+00  3.66110086e-01 -8.69393826e-01]
   [ 1.47368360e+00 -7.89088130e-01 -3.54609728e-01]]

  [[ 6.03936970e-01 -9.67897713e-01  1.16938703e-01]
   [-1.19850588e+00  7.70850033e-02  1.77066755e-02]
   [ 7.98823237e-01  4.93932515e-01 -9.48468566e-01]
   [ 8.82252872e-01  7.01487243e-01 -5.00254929e-01]
   [-1.71791494e-01 -1.60632479e+00 -3.65251660e-01]
   [ 5.94976902e-01 -2.81773806e-01  1.53991389e+00]]

  [[-9.50697243e-01  2.31539607e+00  1.53236735e+00]
   [ 2.06644163e-01  1.08118683e-01  6.60135150e-01]
   [-4.32774782e-01  3.59143674e-01 -3.65802616e-01]
   [-6.76360056e-02  4.68644828e-01  9.71726030e-02]
   [-9.84152138e-01  2.83071637e-01 -7.02350676e-01]
   [ 9.88596380e-01  1.39296412e+00  3.15732419e-01]]

  [[-5.48708797e-01  1.53010404e+00 -8.07920456e-01]
   [ 2.57065803e-01  3.47336233e-01  1.12220800e+00]
   [ 1.03562379e+00  9.75245953e-01  5.40709913e-01]
   [ 5.15106022e-01  5.34687877e-01  3.18394929e-01]
   [-9.35099363e-01 -9.41445529e-01  2.70357668e-01]
   [ 1.77524889e+00  2.22546577e+00 -8.73117566e-01]]]


 [[[-5.90452254e-01 -1.91829288e+00  8.95935655e-01]
   [ 6.68458343e-01  7.10035384e-01 -1.08721328e+00]
   [ 5.19418836e-01 -5.68011589e-02  4.41899896e-01]
   [-4.63488847e-01  1.63937438e+00  1.47250250e-01]
   [-1.02653682e+00 -2.72489995e-01 -6.05541587e-01]
   [-8.72299612e-01  6.58887923e-02  1.10179603e+00]]

  [[ 6.22758210e-01  1.20778608e+00  8.44374597e-02]
   [-4.34562862e-01 -1.67422015e-02  1.17835248e+00]
   [ 9.35374618e-01  7.05550760e-02  4.73234355e-02]
   [ 1.05805770e-01 -3.81742895e-01  1.95683515e+00]
   [-1.34741187e-01  1.92640293e+00  3.44054937e-01]
   [ 7.08339453e-01  5.39803743e-01 -2.89226532e-01]]

  [[-1.97299814e+00 -3.91609907e-01  2.92416424e-01]
   [ 9.11852300e-01 -2.09843564e+00 -1.80300808e+00]
   [-1.02715874e+00 -7.04122841e-01  7.36957192e-01]
   [ 9.11616206e-01 -6.97094947e-02  7.19270945e-01]
   [-1.04748547e-01  1.06924012e-01 -9.07992721e-01]
   [-8.81381273e-01 -7.47072279e-01 -6.51555717e-01]]

  [[ 5.87742150e-01 -5.89153528e-01  5.17881095e-01]
   [ 4.45124358e-01 -6.21006727e-01 -1.88742852e+00]
   [-1.75815606e+00 -2.22720467e-02  4.96855915e-01]
   [ 4.67428327e-01  6.02962971e-01 -1.51036787e+00]
   [ 2.01645207e+00  1.38428795e+00  1.27890062e+00]
   [ 3.88175130e-01 -4.87619400e-01 -5.65113425e-01]]

  [[-2.24400115e+00  6.50866210e-01 -3.57408315e-01]
   [ 4.93292719e-01  6.31041944e-01  1.94613159e+00]
   [ 1.66355669e-01  1.79212070e+00 -4.99554813e-01]
   [ 2.96100676e-01 -1.00269890e+00 -4.26939875e-01]
   [-5.87311327e-01 -6.44681334e-01  1.51777297e-01]
   [-4.27154824e-02 -5.14798880e-01  1.28021216e+00]]

  [[-5.74473619e-01  4.39765185e-01 -1.16566658e+00]
   [-1.10310149e+00  1.01146150e+00 -8.24879587e-01]
   [ 1.24667752e+00  2.32458055e-01 -7.13590384e-02]
   [ 1.20023799e+00 -2.21296713e-01 -1.31394529e+00]
   [ 8.28605235e-01  5.57520330e-01  2.38089752e+00]
   [-1.74523020e+00  1.05198395e+00  2.07037282e+00]]]], shape=(5, 6, 6, 3), dtype=float32)
tf.Tensor(
[[[[ 1.87568888e-01 -9.05686915e-01  1.92977977e+00]
   [ 9.11024287e-02  6.23378754e-01 -1.09670031e+00]
   [-1.39939582e+00 -1.00379653e-01  3.61826062e-01]
   [ 4.95849490e-01 -1.21929228e+00  2.02186614e-01]
   [-9.45614055e-02  1.49201274e+00 -7.97860980e-01]
   [ 1.47168243e+00 -1.07721651e+00 -1.07484353e+00]]

  [[ 1.93246994e-02 -4.47692610e-02  2.16924191e-01]
   [-1.59404904e-01  1.77266356e-02 -1.19980514e+00]
   [ 2.56454498e-01 -1.93552411e+00 -2.78844774e-01]
   [-2.11205080e-01  8.01900208e-01 -7.95955718e-01]
   [-1.10443056e+00  9.17201042e-01  3.34371686e-01]
   [ 8.29509139e-01 -1.46660089e+00 -1.02417874e+00]]

  [[-7.60529280e-01  1.97552228e+00 -1.02420533e+00]
   [ 7.27354765e-01  5.60459554e-01 -4.93120193e-01]
   [-1.72625124e+00  2.56123155e-01 -1.69175613e+00]
   [ 7.67536342e-01 -8.13769847e-02 -8.31038952e-01]
   [ 2.49379444e+00  7.14681685e-01 -1.13818312e+00]
   [ 7.62467146e-01  7.60188639e-01  2.27576599e-01]]

  [[ 8.11537862e-01 -1.73559570e+00  4.82792139e-01]
   [-8.10701668e-01 -1.77008879e+00  3.07443857e+00]
   [ 1.26510334e+00  1.78836977e+00  1.19583404e+00]
   [ 2.20478907e-01  1.05564153e+00 -2.50364020e-02]
   [-3.47511798e-01  1.93252003e+00 -1.00490141e+00]
   [ 5.87290347e-01  3.04456204e-01 -5.29687166e-01]]

  [[ 4.23865765e-02  1.06133819e+00  5.35515785e-01]
   [-2.54426012e-03 -5.86938500e-01  5.35167575e-01]
   [-3.23457927e-01 -4.12681818e-01 -7.32864916e-01]
   [ 7.40105450e-01 -7.75660157e-01  9.32435632e-01]
   [ 1.66822493e+00 -9.69057441e-01 -9.50969011e-02]
   [ 2.95461893e-01 -7.14342415e-01 -2.67090887e-01]]

  [[-2.46500410e-02  3.10926765e-01  9.75172579e-01]
   [ 6.02231920e-01 -4.95087773e-01  6.44952476e-01]
   [ 1.40725851e+00 -1.21028149e+00 -1.24190554e-01]
   [ 3.04605424e-01 -1.33452094e+00  7.74351239e-01]
   [ 4.93379474e-01 -4.03011709e-01  2.44138032e-01]
   [ 8.14318731e-02 -1.17603682e-01  6.78545296e-01]]]


 [[[-7.56267607e-02  5.40018022e-01 -2.81866968e-01]
   [ 8.24308753e-01 -7.99638987e-01 -4.43951219e-01]
   [-1.46431461e-01 -1.97807586e+00  1.93104672e+00]
   [-4.39257413e-01  1.18934357e+00 -8.08273673e-01]
   [-3.95637989e-01  3.10701430e-01  1.16561759e+00]
   [-1.08877070e-01  6.23527288e-01  1.46148145e+00]]

  [[-2.30798975e-01  3.11027914e-01  6.36408150e-01]
   [-1.82630539e+00 -1.03319860e+00 -5.85951388e-01]
   [-4.45587397e-01  4.79556441e-01 -5.13381064e-01]
   [-1.71187177e-01  2.39717454e-01  9.58223641e-01]
   [ 9.40057397e-01 -9.00054991e-01 -1.27614081e+00]
   [ 2.52930578e-02  8.43691528e-01  5.50522625e-01]]

  [[ 8.89593899e-01  9.35105801e-01 -9.42700207e-01]
   [-1.46005559e+00 -1.20610738e+00  3.50007653e-01]
   [ 1.09740973e+00  2.77690023e-01  1.95056105e+00]
   [ 1.55103588e+00 -5.41439414e-01 -6.09899759e-01]
   [ 1.14235699e+00  3.66110086e-01 -8.69393826e-01]
   [ 1.47368360e+00 -7.89088130e-01 -3.54609728e-01]]

  [[ 6.03936970e-01 -9.67897713e-01  1.16938703e-01]
   [-1.19850588e+00  7.70850033e-02  1.77066755e-02]
   [ 7.98823237e-01  4.93932515e-01 -9.48468566e-01]
   [ 8.82252872e-01  7.01487243e-01 -5.00254929e-01]
   [-1.71791494e-01 -1.60632479e+00 -3.65251660e-01]
   [ 5.94976902e-01 -2.81773806e-01  1.53991389e+00]]

  [[-9.50697243e-01  2.31539607e+00  1.53236735e+00]
   [ 2.06644163e-01  1.08118683e-01  6.60135150e-01]
   [-4.32774782e-01  3.59143674e-01 -3.65802616e-01]
   [-6.76360056e-02  4.68644828e-01  9.71726030e-02]
   [-9.84152138e-01  2.83071637e-01 -7.02350676e-01]
   [ 9.88596380e-01  1.39296412e+00  3.15732419e-01]]

  [[-5.48708797e-01  1.53010404e+00 -8.07920456e-01]
   [ 2.57065803e-01  3.47336233e-01  1.12220800e+00]
   [ 1.03562379e+00  9.75245953e-01  5.40709913e-01]
   [ 5.15106022e-01  5.34687877e-01  3.18394929e-01]
   [-9.35099363e-01 -9.41445529e-01  2.70357668e-01]
   [ 1.77524889e+00  2.22546577e+00 -8.73117566e-01]]]], shape=(2, 6, 6, 3), dtype=float32)
tf.Tensor(
[[[[-7.6052928e-01  1.9755223e+00 -1.0242053e+00]
   [ 7.2735476e-01  5.6045955e-01 -4.9312019e-01]
   [-1.7262512e+00  2.5612316e-01 -1.6917561e+00]
   [ 7.6753634e-01 -8.1376985e-02 -8.3103895e-01]
   [ 2.4937944e+00  7.1468168e-01 -1.1381831e+00]
   [ 7.6246715e-01  7.6018864e-01  2.2757660e-01]]

  [[ 8.1153786e-01 -1.7355957e+00  4.8279214e-01]
   [-8.1070167e-01 -1.7700888e+00  3.0744386e+00]
   [ 1.2651033e+00  1.7883698e+00  1.1958340e+00]
   [ 2.2047891e-01  1.0556415e+00 -2.5036402e-02]
   [-3.4751180e-01  1.9325200e+00 -1.0049014e+00]
   [ 5.8729035e-01  3.0445620e-01 -5.2968717e-01]]

  [[ 4.2386577e-02  1.0613382e+00  5.3551579e-01]
   [-2.5442601e-03 -5.8693850e-01  5.3516757e-01]
   [-3.2345793e-01 -4.1268182e-01 -7.3286492e-01]
   [ 7.4010545e-01 -7.7566016e-01  9.3243563e-01]
   [ 1.6682249e+00 -9.6905744e-01 -9.5096901e-02]
   [ 2.9546189e-01 -7.1434242e-01 -2.6709089e-01]]]


 [[[-1.1058835e+00 -9.9461323e-01  6.0086000e-01]
   [-2.4412115e-01 -7.1502006e-01  2.7950117e-01]
   [ 7.1196038e-01  1.2909588e+00  1.8404377e+00]
   [ 1.4547200e+00 -6.2691247e-01 -1.8077913e-01]
   [ 6.9020402e-01 -8.6685634e-01 -7.0109558e-01]
   [ 6.6363001e-01  3.0503383e-01 -2.5425217e-01]]

  [[ 4.1149971e-01  4.6843269e-01 -4.6465409e-01]
   [-5.8977109e-01 -4.1750410e-01 -1.4998958e+00]
   [-1.5241395e+00 -1.3489293e+00 -2.4450023e-01]
   [ 6.2434375e-01  1.7949077e+00  2.3040009e+00]
   [-8.6493748e-01  9.4163960e-01 -9.6813694e-02]
   [ 5.2673292e-01 -5.7169223e-01 -1.9814444e-01]]

  [[-6.7895901e-01  4.8840815e-01  1.6385506e+00]
   [ 1.5529137e+00  7.0799243e-01 -6.8740517e-01]
   [-2.7262485e+00 -5.4236311e-01 -5.6266600e-01]
   [-1.4391688e-01  4.6602857e-01 -3.2045999e-01]
   [-8.6100024e-01 -1.4449316e+00  1.5824346e-01]
   [ 9.3593128e-02 -7.9555839e-01  9.8383480e-01]]]


 [[[ 8.8959390e-01  9.3510580e-01 -9.4270021e-01]
   [-1.4600556e+00 -1.2061074e+00  3.5000765e-01]
   [ 1.0974097e+00  2.7769002e-01  1.9505610e+00]
   [ 1.5510359e+00 -5.4143941e-01 -6.0989976e-01]
   [ 1.1423570e+00  3.6611009e-01 -8.6939383e-01]
   [ 1.4736836e+00 -7.8908813e-01 -3.5460973e-01]]

  [[ 6.0393697e-01 -9.6789771e-01  1.1693870e-01]
   [-1.1985059e+00  7.7085003e-02  1.7706675e-02]
   [ 7.9882324e-01  4.9393252e-01 -9.4846857e-01]
   [ 8.8225287e-01  7.0148724e-01 -5.0025493e-01]
   [-1.7179149e-01 -1.6063248e+00 -3.6525166e-01]
   [ 5.9497690e-01 -2.8177381e-01  1.5399139e+00]]

  [[-9.5069724e-01  2.3153961e+00  1.5323673e+00]
   [ 2.0664416e-01  1.0811868e-01  6.6013515e-01]
   [-4.3277478e-01  3.5914367e-01 -3.6580262e-01]
   [-6.7636006e-02  4.6864483e-01  9.7172603e-02]
   [-9.8415214e-01  2.8307164e-01 -7.0235068e-01]
   [ 9.8859638e-01  1.3929641e+00  3.1573242e-01]]]], shape=(3, 3, 6, 3), dtype=float32)
tf.Tensor(
[[ 0.76753634 -0.08137698 -0.83103895]
 [ 2.4937944   0.7146817  -1.1381831 ]
 [ 0.76246715  0.76018864  0.2275766 ]], shape=(3, 3), dtype=float32)
tf.Tensor([ 0.76753634 -0.08137698 -0.83103895], shape=(3,), dtype=float32)

小蜗笔记

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
打赏
0
评论
(4)tensorflow数据索引与切片

数据索引与切片索引通过随机数模拟输入x为 5张6 × 6大小的彩色图片, 张量表达为x[5,6,6,3]x[k][m][n][h] 与 x[k,m,n,h]表达方式等价import tensorflow as tfx = tf.random.normal([5,6,6,3])print(x[1]) #索引第1张图片print(x[1,2]) #索引第2张图片第3行print(x[1,2,3])#索引第2张图片第3行第4列print(x[1,2,3,2])#索引第2张图片第3行第4列
复制链接

扫一扫