Discover millions of ebooks, audiobooks, and so much more with a free trial

Only $11.99/month after trial. Cancel anytime.

Advanced Applied Deep Learning: Convolutional Neural Networks and Object Detection
Advanced Applied Deep Learning: Convolutional Neural Networks and Object Detection
Advanced Applied Deep Learning: Convolutional Neural Networks and Object Detection
Ebook353 pages2 hours

Advanced Applied Deep Learning: Convolutional Neural Networks and Object Detection

Rating: 0 out of 5 stars

()

Read preview

About this ebook

Develop and optimize deep learning models with advanced architectures. This book teaches you the intricate details and subtleties of the algorithms that are at the core of convolutional neural networks. In Advanced Applied Deep Learning, you will study advanced topics on CNN and object detection using Keras and TensorFlow. 

Along the way, you will look at the fundamental operations in CNN, such as convolution and pooling, and then look at more advanced architectures such as inception networks, resnets, and many more. While the book discusses theoretical topics, you will discover how to work efficiently with Keras with many tricks and tips, including how to customize logging in Keras with custom callback classes, what is eager execution, and how to use it in your models.

Finally, you will study how object detection works, and build a complete implementation of the YOLO (you only look once) algorithm in Keras and TensorFlow. By the end of the book you will have implemented various models in Keras and learned many advanced tricks that will bring your skills to the next level.


What You Will Learn

  • See how convolutional neural networks and object detection work
  • Save weights and models on disk
  • Pause training and restart it at a later stage
  • Use hardware acceleration (GPUs) in your code
  • Work with the Dataset TensorFlow abstraction and use pre-trained models and transfer learning
  • Remove and add layers to pre-trained networks to adapt them to your specific project
  • Apply pre-trained models such as Alexnet and VGG16 to new datasets

 

Who This Book Is For

Scientists and researchers with intermediate-to-advanced Python and machine learning know-how. Additionally, intermediate knowledge of Keras and TensorFlow is expected.


LanguageEnglish
PublisherApress
Release dateSep 28, 2019
ISBN9781484249765
Advanced Applied Deep Learning: Convolutional Neural Networks and Object Detection

Related to Advanced Applied Deep Learning

Related ebooks

Intelligence (AI) & Semantics For You

View More

Related articles

Reviews for Advanced Applied Deep Learning

Rating: 0 out of 5 stars
0 ratings

0 ratings0 reviews

What did you think?

Tap to rate

Review must be at least 10 words

    Book preview

    Advanced Applied Deep Learning - Umberto Michelucci

    3bbook_preview_excerpt.html[˒rZ9ȸlZҌFHV (5 @xO^]|dV [^h Te5~_tY[]yn.2Y\YӔ~uu֦ިm5yaҶ{ˋ{?~?{g}VS׵\>Rĸ鳢;ckmKTzg ; -G>= cU_(+'!Q Gs9߼yy}/ԋ ۮt분<ɭqjeʜ+T:uf;Ze궶+S*˷֪[ZmV_޶nѵO/Yhuթ-NU6xNZzgNHZKfW~|=xjUiܖXV;=~yqT?BLz /MY muf;[*ߜX:?@N^y%k:z*ޘ^7H$BǠj~>+jlcr2Jin5dpMz :8jՊZ׆ljaRB4GzwJ]l4 D''k(GҮǐ!jlM: ,eg怣;{fyw\&tBߠE!U‡ev I-^lJO8QV+t2{D88,+Q$$۴Ya`BKa J N<`v%¶zBHJ}%zVd|tVo2kpXY*M*DW WA۾o=4m6‰Z8{%@#Y2L@g4d֒^fk2 >E4fIa#}uc4 $9 )l5ުIn.z^Zoٞ fלFI/3]bDko4 k)8xC;r64FYcqyOw= 5%! $P)ڒ_5mz!9F%[$QQQyi8~OIK@Yc<+ #ٰ<,Xjyn t+ `#P'e F,AЬluVZneT9(I 2.bQ"ٍ=6m,ܕ$Iq d7MdQYR@6J u\h?`q"۬G"O E+]k4Z| F~!湈akSZ_LT?+:H~M*'~˟MKRR;=jpzE#= Kկm!#+)¸l#a0%.3SR2_Ɔ=jfŵ5K4@.7|!<|f8vT9ӕs tא'u.HF t>ȣ;$ $Dz^CmnfGb0%# Fr0KK hJ9 y К2*ouFt%n>_^|Ԏ0sZOm35GيАxᣯ7DS'+2 :j:IQzATsZƯsO1PY ^žn 7|>W%K"z1*IA yX+V9>!]qJex5_ cU_vr0Pdk>`T,]P:F4gFڌC+`!#jc e.AcY}曫A\״Eet)fB#f[zr94AZ[]6F2m029{R tyJ3䗱(K[eWq=Zc3]0 &[ ƺn`ڐ>2X(Χ1Pv6U2VX$;%jƁbFI6_:o:.Ca(7`> g+S"Uu~JVY3 p xCTE&H\F!5Շ!PA~,'YwKZv舳Bd(ɖA#5'uH1R|/EkWx$ZRkF$.7عWo@ll*9i:G j9 w!Q0DBO6{za ÍmHa/0 Vgڝ?|tţO^s&R~yuِwa:߁WIW #)i-y:'JݐPϣN_5S*TH=('t"a %lAb/ 1|z7߼PxJYF/j~X>W!1m})Y#HgƖUG7 =܃VL TlInX5Tf1$C3t~O<,FƸp|Fp'%dP>kŐU+#^ ޤ{fZ!;$ V[pr M!SSpRjKy!lՇAXE"u}#oN$,!ACt sk?ۚu\pll7)Phu-: ^AN"::= FXO *MF Uqg1>x$o-עy I˛HP#OZ̔d1z e!B?+qL7<〟K97֔5ȚZ0KꕚMb)306aВ~'<4y=rB{5͚-Oo[{yO\4yhbTRN#%3)kjMl(^޵VnB[LfA sY{LWps'9G-(G\E()HMY aG,"&[G&IG*H/dbB_S}Z'op(#xfHrnD0?ҌGΨWΏ2  'MۖuEN&mgɇpF֢F̥K-03Xa-9C]ׁWd#rƯ9CkH+nn@h}5sP2%Q!aq< ޫC0z.h;43`xv"X$ ϥ che"I/Atœ]((hF2+꣺^f|lOI~Vg8WpS/yAY34@N KdA&<""RJF,L }g 9;>GȎeh|vkAL2aH5T,DК CԮVdt$ޞ@8~~ k .wr$>"G͸9Hk7_PJ7FH`7q|,vX;DC+5C^cvr "\Rx"䑌 6ԉr%NpP}`{.1(#PFd\X `/Gr){j e3<ȁ# .yx4b,?`m`r t릢*`mσvlj<Xm .^ybn'\;7B[OUQHhLZn]UBYGlCuIppvíq7;ۂqƚ2x煤Lg)l̝ v޾0+!1c(sI֓\H5iϵOt&E4u2<d1)"G}\\ߴ"oM?tʧkBҔ0|I$Mo':E:Aa~/`'wFY շC9N # f)3xq渘0\x,0#K !D{:!\n;PL~3 gPI* ^!%k 紇;j6=e.s"pgmWj^3fb `G@nw8jݯ<,4iw5| %Zc!uJn̕|7Xp$7VٷZ@k#qN#ƒ}R\-Ã\@ cPwV$9hK$Y:S2g@'!bᅥǣ' ,et{p܀%iu3POQ$8Xһ1D4 .Kz#2J#ib8p: Nnj."ExI~½hD} R}35Wx4-̺U'}I >xI8 h/rw9si%qq&t3275g៣o/,w GcO ;Id86i;i-iW[43N&: /k(efu{[ӝI}O "2, o2$.Ԕlx y<:tq_=0_E bmwC1n n*&0l\w)prBՇ ˍJTN7,g= p/w<ڐB]zIxi1Ohx=cs vwh~4=y{}2X_ACS-Xr*؁d$M28_]x]$ceUNj  $2ك& |q(X!PP7Tax9h-@[Jbr a\d4v9jc!<<95<9f78S|+t8SqW b㣻랾qsgAW4QknC^As)0`v9r\hcw2-x6܈%#Oޅ_GĻ 3JCQZ/coz?7&~tX-`SJe}fA'7y+Y6vkp+0[\U`*'Dfgҿ -̖@
    Enjoying the preview?
    Page 1 of 1