TensorFlow - Tensor Reshape -


i'm using tensorflow , have following matrix:

u2 = tf.constant([[1,3],[0,1],[1,0]],dtype=tf.float32)  [[ 1.  3.]  [ 0.  1.]  [ 1.  0.]] 

what's easiest way reshape matrix results in tensor:

tf.constant([[[1,1],[0,0],[1,1]],[[3,3],[1,1],[0,0]]],dtype=tf.float32)  [[[ 1.  1.]   [ 0.  0.]   [ 1.  1.]]   [[ 3.  3.]   [ 1.  1.]   [ 0.  0.]]] 

this 1 quick way create first submatrix using tensorflow api:

u2 = tf.constant([[1,3],[0,1],[1,0]],dtype=tf.float32) first_col = tf.unpack(u2, axis=1)[0] repeated_cols = tf.tile(first_col, [2]) repeated_cols = tf.reshape(repeated_cols, [3,2]) 

which create

[[ 1.  1.]   [ 0.  0.]   [ 1.  1.]] 

Comments

Popular posts from this blog

java - SSE Emitter : Manage timeouts and complete() -

jquery - uncaught exception: DataTables Editor - remote hosting of code not allowed -

java - How to resolve error - package com.squareup.okhttp3 doesn't exist? -