Scribd
Upload
8 views8 pages

Unit 3

The document discusses tensors in TensorFlow, describing them as multi-dimensional arrays that represent data in computational graphs. It outlines key properties of tensors, such as shape, data type, and rank, and provides examples of their usage in Python code. Additionally, it touches on the mathematical nature of tensors and their application in describing physical properties.

Uploaded by

Imon Nomi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
8 views8 pages

Unit 3

The document discusses tensors in TensorFlow, describing them as multi-dimensional arrays that represent data in computational graphs. It outlines key properties of tensors, such as shape, data type, and rank, and provides examples of their usage in Python code. Additionally, it touches on the mathematical nature of tensors and their application in describing physical properties.

Uploaded by

Imon Nomi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 8

#heN

fDELTA|açe
Dat.

bpulan paclears

Hessian
Diadasalety DELTAP No
HDimas

qnda
Galdtr
Aigsiuha dikett
Mehod

otkagl Seuy

funthns Ch
L-BPs-8

=6.6/9

isterat -
Suura liby fu MLLDL
Lopeo
LbBeand thals-fie builaliag haalag nenelhe
Rased an glala pla grgis wht nadu

Adanage
and dishmaded lGmpu
) Flihle- sups custam modd and opealia

) Bxlensie ELosysken -loekaitd madsh , nvalzstim led

Disadrant1ges
Deuatop ed y ongle k humaniecd
L qpen savre /DELTAJPag Na.
Avidas foals

Based am clataflas- hoda (apsaha


eolgea-.lensars ( dafe

Prplcaim
Data pepanahn.
QModel consheu;hnheamlino paess af buldiyg
hanin and ypotiy malls.

Butnow.araiasle h
ucenced unde Aach wanse 2a

handle laige daksd


dhitiolcanubg
2)_Piehie Supprt-tsten motts topoos
4) Bxiensit Etosyster
Are halnecl
In TensorFlow, tensors are the fundamental
building blocks for representing data. Here's
a breakdown:

What are Tensors?


" Tensors are multi-dimensional arrays with a
uniform data type(e.g., float32, int64).
" They can be thought of as generalizations of
vectors (1-D tensors) and matrices (2-D
tensors) to higher dimensions.
Tensors are immnutable, meaning youcan't
modify their values directly. You can only
create new tensors based on existing ones.

Key Properties of Tensors:


Shape:
The shape of atensor defines its dimensions
(e.g., (2, 3) for a2x3 matrix).
Data Type:
The data type specifies the kind of values stored
in the tensor (e.g., integers, floats, strings).
Rank:
The rank of atensor refers to the number of
dimensions it has (e.g., a scalar has rank 0, a
vector has rank 1, a matrix has rank 2).

How are Tensors Used in TensorFlow?


How are Tensors Used in TensorFlow?

Tensors are used to represent data flowing


through acomputational graph in TensorFlow.
They can hold input data, model parameters,
intermediate results, and the final output of a
computation.
" TensorFlow operations are applied to tensors
to perform various mathematical calculations
and manipulations.

Example:
Python

import tensorflow as tf

# Creating a 2x3 tensor


tensor= tf.constant ([[1, 2, 3], [4, 5, 6

# Printing the tensor


print(tensor)
What is a Tensor? <Previous Next >

Tensors are simply mathematical objects that can


be used to describe physical properties, just like
scalars and vectors. In fact tensors are merely a
generalisation of scalars and vectors; a scalar is a
zero rank tensor, and a vector is a first rank tensor.

The rank (or order) of a tensor is defined by the


number of directions (and hence the dimensionality
of the aray)required to describe it. For example,
properties that require one direction (first rank) can
be fully described by a 3x1 column vector, and
propertiesthat require two directions (second rank
tensors), can be described by 9 numbers, as a 3x3
matrix. As such, in general an n rank tensor can be
described by 3 coefficients.
The need for second rank tensors comes when we
need to consider more than one direction to
describe one of these physical properties. A good
example of this is if we need to describe the
electrical conductivity of a general, anisotropic
crystal. We know that in general for isotropic
onductors that obey Ohm's law:
Cseahn oadod aps DELTAPago No.

Shepsin AAdrad davels


Plan Yaur pp -gel Pupu
asklL Android shdio
c) Soup Davelpen Envienmat sety Ardyoe sDk

Kotin -(Androd -madea


Java - hecina Ardr
SML desilgang tayads

resprs e ur wh Metoval Design Gueb.

shg Mvc, MWMnhit ual pntte


oganize coce
needet
Use Ar! to fnegrat Sovices f
s) Test yau Ppp Emulatn a
4,
phekiial doae Foc keahng
Use Aodrotd

pp-pepae appesak mkde.


obsh the Gentresa sgnet Afk
GoogiePay Sre aahn
Subms th cpp on

Rleoa pdatr

You might also like