卷积函数-conv2d
2017-12-09 23:56
330 查看
import tensorflow as tf import numpy as np input_data = tf.Variable( np.random.rand(10, 9, 9 ,3), dtype = np.float32 ) filter_data = tf.Variable( np.random.rand(2, 2, 3, 2), dtype = np.float32) y = tf.nn.conv2d(input_data, filter_data, strides = [1, 1, 1, 1], padding = 'SAME') with tf.Session() as sess: sess.run(tf.global_variables_initializer()) print sess.run(y) print sess.run(tf.shape(y))
[[[[ 2.28441477 3.06847477]
[ 2.86936951 3.36118436]
[ 2.90876746 3.83813024]
...,
[ 1.63569283 2.06621099]
[ 2.24114609 3.10374069]
[ 1.23497581 1.39789116]]
[[ 2.01059985 2.70281553]
[ 2.31235123 2.97695923]
[ 2.71346474 2.56986856]
...,
[ 1.97958255 2.39565802]
[ 1.52550602 2.40602493]
[ 1.44903207 0.7784394 ]]
[[ 2.93185854 2.95032263]
[ 1.82584941 2.5140605 ]
[ 2.92788196 3.14288759]
...,
[ 2.48327637 3.02099347]
[ 2.35544467 2.80534363]
[ 0.96245033 0.80687135]]
...,
[[ 2.78728533 3.08616018]
[ 2.81141281 3.79395676]
[ 2.73261857 2.61715674]
...,
[ 2.75830841 3.11794996]
[ 2.61598086 2.74874234]
[ 0.9380343 0.91474104]]
[[ 2.01401186 2.82440901]
[ 3.01286578 3.90122676]
[ 3.22464895 3.72051382]
...,
[ 1.95198154 2.38326359]
[ 2.19041157 2.90743423]
[ 1.71184278 0.91215426]]
[[ 0.69879651 1.29733109]
[ 1.66762972 1.41474044]
[ 1.3976984 2.02703118]
...,
[ 1.0184195 0.74748439]
[ 0.82535017 0.90885115]
[ 0.8296777 0.61198354]]]
[[[ 3.00285864 3.66854453]
[ 2.17865944 3.95667744]
[ 3.32269382 3.90519333]
...,
[ 1.75325131 3.03243518]
[ 1.56798875 2.7367065 ]
[ 1.06911421 0.64623517]]
[[ 3.87107611 4.34347582]
[ 2.23594332 3.65853691]
[ 2.44312477 3.2281127 ]
...,
[ 2.77767992 2.86911583]
[ 2.37514257 2.77617216]
[ 1.10845053 0.97984314]]
[[ 2.17275143 3.11631107]
[ 2.43488026 2.70688319]
[ 2.20407176 2.63178682]
...,
[ 2.49707651 2.8172946 ]
[ 2.74680591 3.23685098]
[ 1.72101617 1.719607 ]]
...,
[[ 2.876616 3.53369856]
[ 2.5170207 3.24979591]
[ 2.33437181 2.35978389]
...,
[ 3.04654884 4.5875473 ]
[ 3.86541176 4.33993578]
[ 1.66550374 1.12523925]]
[[ 2.58393836 3.94380355]
[ 3.24331427 3.53925443]
[ 3.06660414 2.72423649]
...,
[ 3.28876805 4.26353025]
[ 2.73433876 3.29844904]
[ 1.35066676 0.89224339]]
[[ 1.31961608 2.05621338]
[ 1.57045865 1.73030257]
[ 1.38873529 1.23816729]
...,
[ 1.94063663 2.15966296]
[ 0.89746934 1.36882854]
[ 0.54245079 0.14804356]]]
[[[ 2.35181999 2.92467499]
[ 3.41341424 3.52672577]
[ 2.47169447 3.50138426]
...,
[ 1.36647558 2.8227663 ]
[ 2.13923836 2.57541609]
[ 0.57179981 1.19623995]]
[[ 2.94395542 4.073771 ]
[ 3.0283916 3.84947634]
[ 3.35602498 4.05159855]
...,
[ 2.15090227 3.11249089]
[ 2.2351923 2.56126785]
[ 1.36848688 0.72942787]]
[[ 3.27091742 4.36461735]
[ 2.64745045 2.80718303]
[ 2.3807416 3.63565207]
...,
[ 2.19285297 2.68066025]
[ 2.62513781 2.92402267]
[ 1.10025692 1.16136837]]
...,
[[ 3.01076126 3.4119482 ]
[ 1.85087693 3.22764778]
[ 2.76176405 2.91168904]
...,
[ 2.55947065 3.47643113]
[ 2.65126657 3.58177614]
[ 1.59869909 1.23286581]]
[[ 2.59230924 3.38325787]
[ 2.22486281 2.48523927]
[ 1.72652149 2.69701433]
...,
[ 2.23065948 2.60219693]
[ 2.36404562 3.73067355]
[ 1.77414346 1.37843394]]
[[ 0.97523886 1.13877046]
[ 1.45419931 0.98639047]
[ 0.75436819 0.8086229 ]
...,
[ 0.93567371 1.45672941]
[ 1.35910726 1.7025404 ]
[ 1.2021718 0.9415859 ]]]
...,
[[[ 2.46098757 3.22544956]
[ 2.47662306 3.55110836]
[ 2.4317894 2.48825502]
...,
[ 2.17777824 2.89912939]
[ 3.05267835 3.78674769]
[ 1.83052111 1.28529596]]
[[ 2.10993528 2.68119574]
[ 2.99710703 3.28453517]
[ 2.70201182 3.97987652]
...,
[ 1.7376579 1.41152024]
[ 2.55227089 3.20672607]
[ 1.97965407 1.46010005]]
[[ 2.19772291 2.62603664]
[ 2.60253549 2.83817363]
[ 2.25216103 3.78826547]
...,
[ 1.45738602 2.01276708]
[ 2.51962566 2.96650028]
[ 1.43600976 1.2179904 ]]
...,
[[ 1.93896747 3.25516057]
[ 2.49237108 2.79077721]
[ 2.79178309 2.67786503]
...,
[ 2.65839028 1.96878338]
[ 2.11396408 2.84220266]
[ 0.94130039 1.41221488]]
[[ 2.20868111 1.97231257]
[ 1.83280671 2.05507207]
[ 2.29310036 3.86106825]
...,
[ 2.73892999 3.28985763]
[ 2.72056603 2.56073999]
[ 0.84322411 1.36854875]]
[[ 1.21004152 1.46410084]
[ 1.04700136 0.97574151]
[ 1.16823506 2.28405547]
...,
[ 1.72344029 1.56731033]
[ 1.42622149 1.47656095]
[ 0.67297661 0.17105176]]]
[[[ 2.1493187 2.83201408]
[ 2.40550518 3.64812636]
[ 3.01165819 3.45196104]
...,
[ 3.18396378 4.28989172]
[ 3.0395472 3.2183466 ]
[ 1.02563179 1.2394067 ]]
[[ 2.56986713 3.39787626]
[ 3.14118719 3.60724711]
[ 2.42699313 3.05054379]
...,
[ 3.02555251 3.84614849]
[ 2.5915637 3.60050106]
[ 1.08133292 0.9801904 ]]
[[ 2.7895484 3.26012802]
[ 2.68198657 3.03690243]
[ 1.55666649 2.69858265]
...,
[ 2.37659574 2.86296129]
[ 2.12536287 3.17281008]
[ 1.06695342 0.90059114]]
...,
[[ 2.559901 3.9107275 ]
[ 2.4477582 3.25638652]
[ 2.41677403 2.12277007]
...,
[ 2.21316862 3.35137677]
[ 2.10929203 2.41750932]
[ 0.56258953 0.76881254]]
[[ 3.8143177 4.02317667]
[ 1.98848999 2.80659127]
[ 2.05915785 3.13008142]
...,
[ 2.07863283 3.25673485]
[ 2.28678918 3.44819236]
[ 0.9778313 1.25186169]]
[[ 2.16899443 1.81443906]
[ 1.1907239 1.3821789 ]
[ 1.15051484 1.89745927]
...,
[ 1.17642415 1.05422068]
[ 1.17066789 1.91201067]
[ 0.6694082 0.69027495]]]
[[[ 2.33095121 3.84507108]
[ 3.19045091 3.5068593 ]
[ 3.05367851 3.88874531]
...,
[ 3.08059406 3.65819788]
[ 2.46952462 2.62755013]
[ 0.56767726 0.56772256]]
[[ 2.63759875 3.17783689]
[ 3.31892586 3.78526974]
[ 3.32958961 4.31831121]
...,
[ 2.47733831 3.25966549]
[ 3.15235138 2.89481115]
[ 0.9032011 0.98115283]]
[[ 1.84606934 2.23636961]
[ 2.82043672 3.00273299]
[ 3.02201033
4000
3.40184736]
...,
[ 2.59918952 3.28301144]
[ 3.64022636 4.21657276]
[ 1.75729036 1.51518643]]
...,
[[ 2.35361028 2.86604118]
[ 1.91406894 2.41733742]
[ 2.22170973 3.23638821]
...,
[ 2.36277723 3.06239462]
[ 1.57983088 1.56720269]
[ 0.73788458 0.78195465]]
[[ 2.50267982 3.19840217]
[ 1.86310196 2.16363358]
[ 2.35080171 2.87520361]
...,
[ 3.0470252 3.58498788]
[ 2.39537287 2.6719594 ]
[ 1.14137316 1.12938166]]
[[ 1.32827282 1.30217993]
[ 0.70091486 0.56333184]
[ 0.78078008 1.46257758]
...,
[ 1.97750568 1.89606833]
[ 1.58064485 1.86012006]
[ 1.2703805 0.57370603]]]]
[10 9 9 2]
内容来自用户分享和网络整理，不保证内容的准确性，如有侵权内容，可联系管理员处理 
相关文章推荐
- 卷积函数-depthwise_conv2d
- 卷积函数-separable_conv2d
- 卷积函数-atrous_conv2d
- 卷积函数-conv2d_transpose
- tf.nn.atrous_conv2d 实例
- tf.nn.conv2d理解
- 【Tensorflow】tf.nn.atrous_conv2d如何实现空洞卷积？
- tf.nn.conv2d()
- tf.nn.separable_conv2d 用法
- tensorflow学习：tf.nn.conv2d 和 tf.layers.conv2d
- tf.nn.conv2d用法简介
- tensorflow_conv2d_max_pool卷积池化padding参数为SAME和VALID的区别
- TensorFlow基础笔记(11) conv2D函数
- 【Tensorflow】tf.nn.atrous_conv2d如何实现空洞卷积？
- tensorflow学习笔记(三十二):conv2d_transpose ("解卷积")
- tensorflow学习基础篇1——conv2d 函数说明
- CNN tflearn处理mnist图像识别代码解说——conv_2d参数解释，整个网络的训练，主要就是为了学那个卷积核啊。
- tf.nn.atrous_conv2d(value, filters, rate, padding, name=None) {#atrous_conv2d}
- 对比 tf.layers.conv2d_transpose和tf.nn.conv2d_transpose区别
- tf.nn.conv2d与tf.contrib.slim.conv2d