tensor

Published by onesixx on

종류

The Important definitions in Tensorflow(Compared to PyTorch): Tensor,  Operation, Graph, Session (1… – mc.ai

5D vector (5-dimensional vector) length() =5 shape(5)

5D tensor (tensor of rank 5) dim() = 5 , 5개의 axis , shape(6,2,3,4)

Operation

tensor 연산 = 데이터의 기하학적 해석 (geometric interpretation)

product (dot)

Reshape

(R의 column중심이 아닌 , keras가 활용하는 Numpy, tensorflow가 array의 차원을 해석하는 방식에 부합되는 )
row 중심 구문으로 데이터를 재번역(re-interpret)하는 것

(Network에 입력전 Pre-processing에서) Target shape에 맞게 row/column을 재배치하는 것 (rank의 변화는 없이)

> xx <- matrix(c(0,1,
 \t\t\t\t 2,3,
 \t\t\t\t 4,5), nrow=3, ncol=2, byrow=T)
> 
> array_reshape(xx, dim=c(6,1))
     [,1]
[1,]    0
[2,]    1
[3,]    2
[4,]    3
[5,]    4
[6,]    5
> array_reshape(xx, dim=c(2,3))
     [,1] [,2] [,3]
[1,]    0    1    2
[2,]    3    4    5
> t(xx)  # transpose
     [,1] [,2] [,3]
[1,]    0    2    4
[2,]    1    3    5
Categories: DeepLearning

onesixx

Blog Owner

Subscribe
Notify of
guest

0 Comments
Oldest
Newest Most Voted
Inline Feedbacks
View all comments
0
Would love your thoughts, please comment.x
()
x