Hands-On Convolutional Neural Networks with TensorFlow :: Solve Computer Vision Problems with Modeling in TensorFlow and Python.
Convolutional Neural Networks (CNN) are one of the most popular architectures used in computer vision apps. This book is an introduction to CNNs through solving real-world problems in deep learning while teaching you their implementation in popular Python library - TensorFlow. By the end of the book...
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Weitere Verfasser: | , , , |
| Format: | Elektronisch E-Book |
| Sprache: | English |
| Veröffentlicht: |
Birmingham :
Packt Publishing Ltd,
2018.
|
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Zusammenfassung: | Convolutional Neural Networks (CNN) are one of the most popular architectures used in computer vision apps. This book is an introduction to CNNs through solving real-world problems in deep learning while teaching you their implementation in popular Python library - TensorFlow. By the end of the book, you will be training CNNs in no time! |
| Beschreibung: | Substituting the 3x3 convolution |
| Beschreibung: | 1 online resource (264 pages) |
| ISBN: | 9781789132823 1789132827 |
Internformat
MARC
| LEADER | 00000cam a2200000Mi 4500 | ||
|---|---|---|---|
| 001 | ZDB-4-EBA-on1051140562 | ||
| 003 | OCoLC | ||
| 005 | 20241004212047.0 | ||
| 006 | m o d | ||
| 007 | cr cnu---unuuu | ||
| 008 | 180908s2018 enk o 000 0 eng d | ||
| 040 | |a EBLCP |b eng |e pn |c EBLCP |d NLE |d TEFOD |d YDX |d MERUC |d IDB |d OCLCO |d UKMGB |d LVT |d OCLCF |d UKAHL |d N$T |d OCLCQ |d OCLCO |d NZAUC |d OCLCQ |d OCLCO |d OCLCL | ||
| 015 | |a GBB8G6337 |2 bnb | ||
| 016 | 7 | |a 019043217 |2 Uk | |
| 019 | |a 1051137602 | ||
| 020 | |a 9781789132823 |q (electronic bk.) | ||
| 020 | |a 1789132827 |q (electronic bk.) | ||
| 020 | |z 1789130336 | ||
| 020 | |z 9781789130331 | ||
| 035 | |a (OCoLC)1051140562 |z (OCoLC)1051137602 | ||
| 037 | |a 82D3E1C4-A885-4E58-A012-8BC0A045AFA6 |b OverDrive, Inc. |n http://www.overdrive.com | ||
| 050 | 4 | |a QA76.87 |b .Z343 2018eb | |
| 082 | 7 | |a 006.3 |2 23 | |
| 049 | |a MAIN | ||
| 100 | 1 | |a Zafar, Iffat. | |
| 245 | 1 | 0 | |a Hands-On Convolutional Neural Networks with TensorFlow : |b Solve Computer Vision Problems with Modeling in TensorFlow and Python. |
| 260 | |a Birmingham : |b Packt Publishing Ltd, |c 2018. | ||
| 300 | |a 1 online resource (264 pages) | ||
| 336 | |a text |b txt |2 rdacontent | ||
| 337 | |a computer |b c |2 rdamedia | ||
| 338 | |a online resource |b cr |2 rdacarrier | ||
| 588 | 0 | |a Print version record. | |
| 505 | 0 | |a Cover; Title Page; Copyright and Credits; Packt Upsell; Contributors; Table of Contents; Preface; Chapter 1: Setup and Introduction to TensorFlow; The TensorFlow way of thinking; Setting up and installing TensorFlow; Conda environments; Checking whether your installation works; TensorFlow API levels; Eager execution; Building your first TensorFlow model; One-hot vectors; Splitting into training and test sets; Creating TensorFlow graphs; Variables; Operations; Feeding data with placeholders; Initializing variables; Training our model; Loss functions; Optimization; Evaluating a trained model | |
| 505 | 8 | |a The sessionSummary; Chapter 2: Deep Learning and Convolutional Neural Networks; AI and ML; Types of ML; Old versus new ML; Artificial neural networks; Activation functions; The XOR problem; Training neural networks; Backpropagation and the chain rule; Batches; Loss functions; The optimizer and its hyperparameters; Underfitting versus overfitting; Feature scaling; Fully connected layers; A TensorFlow example for the XOR problem; Convolutional neural networks; Convolution; Input padding; Calculating the number of parameters (weights); Calculating the number of operations | |
| 505 | 8 | |a Converting convolution layers into fully connected layersThe pooling layer; 1x1 Convolution; Calculating the receptive field; Building a CNN model in TensorFlow; TensorBoard; Other types of convolutions; Summary; Chapter 3: Image Classification in TensorFlow; CNN model architecture; Cross-entropy loss (log loss); Multi-class cross entropy loss; The train/test dataset split; Datasets; ImageNet; CIFAR; Loading CIFAR; Image classification with TensorFlow; Building the CNN graph; Learning rate scheduling; Introduction to the tf.data API; The main training loop; Model Initialization | |
| 505 | 8 | |a Do not initialize all weights with zerosInitializing with a mean zero distribution; Xavier-Bengio and the Initializer; Improving generalization by regularizing; L2 and L1 regularization; Dropout; The batch norm layer; Summary; Chapter 4: Object Detection and Segmentation; Image classification with localization; Localization as regression; TensorFlow implementation; Other applications of localization; Object detection as classification -- Sliding window; Using heuristics to guide us (R-CNN); Problems; Fast R-CNN; Faster R-CNN; Region Proposal Network; RoI Pooling layer | |
| 505 | 8 | |a Conversion from traditional CNN to Fully ConvnetsSingle Shot Detectors -- You Only Look Once; Creating training set for Yolo object detection; Evaluating detection (Intersection Over Union); Filtering output; Anchor Box; Testing/Predicting in Yolo; Detector Loss function (YOLO loss); Loss Part 1; Loss Part 2; Loss Part 3; Semantic segmentation; Max Unpooling; Deconvolution layer (Transposed convolution); The loss function; Labels; Improving results; Instance segmentation; Mask R-CNN; Summary; Chapter 5: VGG, Inception Modules, Residuals, and MobileNets; Substituting big convolutions | |
| 500 | |a Substituting the 3x3 convolution | ||
| 520 | |a Convolutional Neural Networks (CNN) are one of the most popular architectures used in computer vision apps. This book is an introduction to CNNs through solving real-world problems in deep learning while teaching you their implementation in popular Python library - TensorFlow. By the end of the book, you will be training CNNs in no time! | ||
| 650 | 0 | |a Neural networks (Computer science) |x Computer simulation. | |
| 650 | 6 | |a Réseaux neuronaux (Informatique) |x Simulation par ordinateur. | |
| 650 | 7 | |a Neural networks (Computer science) |x Computer simulation |2 fast | |
| 700 | 1 | |a Tzanidou, Giounona. | |
| 700 | 1 | |a Burton, Richard. | |
| 700 | 1 | |a Patel, Nimesh. | |
| 700 | 1 | |a Araujo, Leonardo. | |
| 758 | |i has work: |a Hands-On Convolutional Neural Networks with TensorFlow (Text) |1 https://id.oclc.org/worldcat/entity/E39PCFy94gTqWBjxbxdKkdB8wd |4 https://id.oclc.org/worldcat/ontology/hasWork | ||
| 776 | 0 | 8 | |i Print version: |a Zafar, Iffat. |t Hands-On Convolutional Neural Networks with TensorFlow : Solve Computer Vision Problems with Modeling in TensorFlow and Python. |d Birmingham : Packt Publishing Ltd, ©2018 |z 9781789130331 |
| 856 | 4 | 0 | |l FWS01 |p ZDB-4-EBA |q FWS_PDA_EBA |u https://search.ebscohost.com/login.aspx?direct=true&scope=site&db=nlebk&AN=1881049 |3 Volltext |
| 938 | |a Askews and Holts Library Services |b ASKH |n AH35074140 | ||
| 938 | |a ProQuest Ebook Central |b EBLB |n EBL5504396 | ||
| 938 | |a EBSCOhost |b EBSC |n 1881049 | ||
| 938 | |a YBP Library Services |b YANK |n 15689471 | ||
| 994 | |a 92 |b GEBAY | ||
| 912 | |a ZDB-4-EBA | ||
| 049 | |a DE-863 | ||
Datensatz im Suchindex
| DE-BY-FWS_katkey | ZDB-4-EBA-on1051140562 |
|---|---|
| _version_ | 1816882470826541056 |
| adam_text | |
| any_adam_object | |
| author | Zafar, Iffat |
| author2 | Tzanidou, Giounona Burton, Richard Patel, Nimesh Araujo, Leonardo |
| author2_role | |
| author2_variant | g t gt r b rb n p np l a la |
| author_facet | Zafar, Iffat Tzanidou, Giounona Burton, Richard Patel, Nimesh Araujo, Leonardo |
| author_role | |
| author_sort | Zafar, Iffat |
| author_variant | i z iz |
| building | Verbundindex |
| bvnumber | localFWS |
| callnumber-first | Q - Science |
| callnumber-label | QA76 |
| callnumber-raw | QA76.87 .Z343 2018eb |
| callnumber-search | QA76.87 .Z343 2018eb |
| callnumber-sort | QA 276.87 Z343 42018EB |
| callnumber-subject | QA - Mathematics |
| collection | ZDB-4-EBA |
| contents | Cover; Title Page; Copyright and Credits; Packt Upsell; Contributors; Table of Contents; Preface; Chapter 1: Setup and Introduction to TensorFlow; The TensorFlow way of thinking; Setting up and installing TensorFlow; Conda environments; Checking whether your installation works; TensorFlow API levels; Eager execution; Building your first TensorFlow model; One-hot vectors; Splitting into training and test sets; Creating TensorFlow graphs; Variables; Operations; Feeding data with placeholders; Initializing variables; Training our model; Loss functions; Optimization; Evaluating a trained model The sessionSummary; Chapter 2: Deep Learning and Convolutional Neural Networks; AI and ML; Types of ML; Old versus new ML; Artificial neural networks; Activation functions; The XOR problem; Training neural networks; Backpropagation and the chain rule; Batches; Loss functions; The optimizer and its hyperparameters; Underfitting versus overfitting; Feature scaling; Fully connected layers; A TensorFlow example for the XOR problem; Convolutional neural networks; Convolution; Input padding; Calculating the number of parameters (weights); Calculating the number of operations Converting convolution layers into fully connected layersThe pooling layer; 1x1 Convolution; Calculating the receptive field; Building a CNN model in TensorFlow; TensorBoard; Other types of convolutions; Summary; Chapter 3: Image Classification in TensorFlow; CNN model architecture; Cross-entropy loss (log loss); Multi-class cross entropy loss; The train/test dataset split; Datasets; ImageNet; CIFAR; Loading CIFAR; Image classification with TensorFlow; Building the CNN graph; Learning rate scheduling; Introduction to the tf.data API; The main training loop; Model Initialization Do not initialize all weights with zerosInitializing with a mean zero distribution; Xavier-Bengio and the Initializer; Improving generalization by regularizing; L2 and L1 regularization; Dropout; The batch norm layer; Summary; Chapter 4: Object Detection and Segmentation; Image classification with localization; Localization as regression; TensorFlow implementation; Other applications of localization; Object detection as classification -- Sliding window; Using heuristics to guide us (R-CNN); Problems; Fast R-CNN; Faster R-CNN; Region Proposal Network; RoI Pooling layer Conversion from traditional CNN to Fully ConvnetsSingle Shot Detectors -- You Only Look Once; Creating training set for Yolo object detection; Evaluating detection (Intersection Over Union); Filtering output; Anchor Box; Testing/Predicting in Yolo; Detector Loss function (YOLO loss); Loss Part 1; Loss Part 2; Loss Part 3; Semantic segmentation; Max Unpooling; Deconvolution layer (Transposed convolution); The loss function; Labels; Improving results; Instance segmentation; Mask R-CNN; Summary; Chapter 5: VGG, Inception Modules, Residuals, and MobileNets; Substituting big convolutions |
| ctrlnum | (OCoLC)1051140562 |
| dewey-full | 006.3 |
| dewey-hundreds | 000 - Computer science, information, general works |
| dewey-ones | 006 - Special computer methods |
| dewey-raw | 006.3 |
| dewey-search | 006.3 |
| dewey-sort | 16.3 |
| dewey-tens | 000 - Computer science, information, general works |
| discipline | Informatik |
| format | Electronic eBook |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>05819cam a2200613Mi 4500</leader><controlfield tag="001">ZDB-4-EBA-on1051140562</controlfield><controlfield tag="003">OCoLC</controlfield><controlfield tag="005">20241004212047.0</controlfield><controlfield tag="006">m o d </controlfield><controlfield tag="007">cr cnu---unuuu</controlfield><controlfield tag="008">180908s2018 enk o 000 0 eng d</controlfield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">EBLCP</subfield><subfield code="b">eng</subfield><subfield code="e">pn</subfield><subfield code="c">EBLCP</subfield><subfield code="d">NLE</subfield><subfield code="d">TEFOD</subfield><subfield code="d">YDX</subfield><subfield code="d">MERUC</subfield><subfield code="d">IDB</subfield><subfield code="d">OCLCO</subfield><subfield code="d">UKMGB</subfield><subfield code="d">LVT</subfield><subfield code="d">OCLCF</subfield><subfield code="d">UKAHL</subfield><subfield code="d">N$T</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">OCLCO</subfield><subfield code="d">NZAUC</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">OCLCO</subfield><subfield code="d">OCLCL</subfield></datafield><datafield tag="015" ind1=" " ind2=" "><subfield code="a">GBB8G6337</subfield><subfield code="2">bnb</subfield></datafield><datafield tag="016" ind1="7" ind2=" "><subfield code="a">019043217</subfield><subfield code="2">Uk</subfield></datafield><datafield tag="019" ind1=" " ind2=" "><subfield code="a">1051137602</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9781789132823</subfield><subfield code="q">(electronic bk.)</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">1789132827</subfield><subfield code="q">(electronic bk.)</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="z">1789130336</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="z">9781789130331</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)1051140562</subfield><subfield code="z">(OCoLC)1051137602</subfield></datafield><datafield tag="037" ind1=" " ind2=" "><subfield code="a">82D3E1C4-A885-4E58-A012-8BC0A045AFA6</subfield><subfield code="b">OverDrive, Inc.</subfield><subfield code="n">http://www.overdrive.com</subfield></datafield><datafield tag="050" ind1=" " ind2="4"><subfield code="a">QA76.87</subfield><subfield code="b">.Z343 2018eb</subfield></datafield><datafield tag="082" ind1="7" ind2=" "><subfield code="a">006.3</subfield><subfield code="2">23</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">MAIN</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Zafar, Iffat.</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Hands-On Convolutional Neural Networks with TensorFlow :</subfield><subfield code="b">Solve Computer Vision Problems with Modeling in TensorFlow and Python.</subfield></datafield><datafield tag="260" ind1=" " ind2=" "><subfield code="a">Birmingham :</subfield><subfield code="b">Packt Publishing Ltd,</subfield><subfield code="c">2018.</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">1 online resource (264 pages)</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">computer</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">online resource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="588" ind1="0" ind2=" "><subfield code="a">Print version record.</subfield></datafield><datafield tag="505" ind1="0" ind2=" "><subfield code="a">Cover; Title Page; Copyright and Credits; Packt Upsell; Contributors; Table of Contents; Preface; Chapter 1: Setup and Introduction to TensorFlow; The TensorFlow way of thinking; Setting up and installing TensorFlow; Conda environments; Checking whether your installation works; TensorFlow API levels; Eager execution; Building your first TensorFlow model; One-hot vectors; Splitting into training and test sets; Creating TensorFlow graphs; Variables; Operations; Feeding data with placeholders; Initializing variables; Training our model; Loss functions; Optimization; Evaluating a trained model</subfield></datafield><datafield tag="505" ind1="8" ind2=" "><subfield code="a">The sessionSummary; Chapter 2: Deep Learning and Convolutional Neural Networks; AI and ML; Types of ML; Old versus new ML; Artificial neural networks; Activation functions; The XOR problem; Training neural networks; Backpropagation and the chain rule; Batches; Loss functions; The optimizer and its hyperparameters; Underfitting versus overfitting; Feature scaling; Fully connected layers; A TensorFlow example for the XOR problem; Convolutional neural networks; Convolution; Input padding; Calculating the number of parameters (weights); Calculating the number of operations</subfield></datafield><datafield tag="505" ind1="8" ind2=" "><subfield code="a">Converting convolution layers into fully connected layersThe pooling layer; 1x1 Convolution; Calculating the receptive field; Building a CNN model in TensorFlow; TensorBoard; Other types of convolutions; Summary; Chapter 3: Image Classification in TensorFlow; CNN model architecture; Cross-entropy loss (log loss); Multi-class cross entropy loss; The train/test dataset split; Datasets; ImageNet; CIFAR; Loading CIFAR; Image classification with TensorFlow; Building the CNN graph; Learning rate scheduling; Introduction to the tf.data API; The main training loop; Model Initialization</subfield></datafield><datafield tag="505" ind1="8" ind2=" "><subfield code="a">Do not initialize all weights with zerosInitializing with a mean zero distribution; Xavier-Bengio and the Initializer; Improving generalization by regularizing; L2 and L1 regularization; Dropout; The batch norm layer; Summary; Chapter 4: Object Detection and Segmentation; Image classification with localization; Localization as regression; TensorFlow implementation; Other applications of localization; Object detection as classification -- Sliding window; Using heuristics to guide us (R-CNN); Problems; Fast R-CNN; Faster R-CNN; Region Proposal Network; RoI Pooling layer</subfield></datafield><datafield tag="505" ind1="8" ind2=" "><subfield code="a">Conversion from traditional CNN to Fully ConvnetsSingle Shot Detectors -- You Only Look Once; Creating training set for Yolo object detection; Evaluating detection (Intersection Over Union); Filtering output; Anchor Box; Testing/Predicting in Yolo; Detector Loss function (YOLO loss); Loss Part 1; Loss Part 2; Loss Part 3; Semantic segmentation; Max Unpooling; Deconvolution layer (Transposed convolution); The loss function; Labels; Improving results; Instance segmentation; Mask R-CNN; Summary; Chapter 5: VGG, Inception Modules, Residuals, and MobileNets; Substituting big convolutions</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">Substituting the 3x3 convolution</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Convolutional Neural Networks (CNN) are one of the most popular architectures used in computer vision apps. This book is an introduction to CNNs through solving real-world problems in deep learning while teaching you their implementation in popular Python library - TensorFlow. By the end of the book, you will be training CNNs in no time!</subfield></datafield><datafield tag="650" ind1=" " ind2="0"><subfield code="a">Neural networks (Computer science)</subfield><subfield code="x">Computer simulation.</subfield></datafield><datafield tag="650" ind1=" " ind2="6"><subfield code="a">Réseaux neuronaux (Informatique)</subfield><subfield code="x">Simulation par ordinateur.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Neural networks (Computer science)</subfield><subfield code="x">Computer simulation</subfield><subfield code="2">fast</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Tzanidou, Giounona.</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Burton, Richard.</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Patel, Nimesh.</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Araujo, Leonardo.</subfield></datafield><datafield tag="758" ind1=" " ind2=" "><subfield code="i">has work:</subfield><subfield code="a">Hands-On Convolutional Neural Networks with TensorFlow (Text)</subfield><subfield code="1">https://id.oclc.org/worldcat/entity/E39PCFy94gTqWBjxbxdKkdB8wd</subfield><subfield code="4">https://id.oclc.org/worldcat/ontology/hasWork</subfield></datafield><datafield tag="776" ind1="0" ind2="8"><subfield code="i">Print version:</subfield><subfield code="a">Zafar, Iffat.</subfield><subfield code="t">Hands-On Convolutional Neural Networks with TensorFlow : Solve Computer Vision Problems with Modeling in TensorFlow and Python.</subfield><subfield code="d">Birmingham : Packt Publishing Ltd, ©2018</subfield><subfield code="z">9781789130331</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="l">FWS01</subfield><subfield code="p">ZDB-4-EBA</subfield><subfield code="q">FWS_PDA_EBA</subfield><subfield code="u">https://search.ebscohost.com/login.aspx?direct=true&scope=site&db=nlebk&AN=1881049</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="938" ind1=" " ind2=" "><subfield code="a">Askews and Holts Library Services</subfield><subfield code="b">ASKH</subfield><subfield code="n">AH35074140</subfield></datafield><datafield tag="938" ind1=" " ind2=" "><subfield code="a">ProQuest Ebook Central</subfield><subfield code="b">EBLB</subfield><subfield code="n">EBL5504396</subfield></datafield><datafield tag="938" ind1=" " ind2=" "><subfield code="a">EBSCOhost</subfield><subfield code="b">EBSC</subfield><subfield code="n">1881049</subfield></datafield><datafield tag="938" ind1=" " ind2=" "><subfield code="a">YBP Library Services</subfield><subfield code="b">YANK</subfield><subfield code="n">15689471</subfield></datafield><datafield tag="994" ind1=" " ind2=" "><subfield code="a">92</subfield><subfield code="b">GEBAY</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">ZDB-4-EBA</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-863</subfield></datafield></record></collection> |
| id | ZDB-4-EBA-on1051140562 |
| illustrated | Not Illustrated |
| indexdate | 2024-11-27T13:29:07Z |
| institution | BVB |
| isbn | 9781789132823 1789132827 |
| language | English |
| oclc_num | 1051140562 |
| open_access_boolean | |
| owner | MAIN DE-863 DE-BY-FWS |
| owner_facet | MAIN DE-863 DE-BY-FWS |
| physical | 1 online resource (264 pages) |
| psigel | ZDB-4-EBA |
| publishDate | 2018 |
| publishDateSearch | 2018 |
| publishDateSort | 2018 |
| publisher | Packt Publishing Ltd, |
| record_format | marc |
| spelling | Zafar, Iffat. Hands-On Convolutional Neural Networks with TensorFlow : Solve Computer Vision Problems with Modeling in TensorFlow and Python. Birmingham : Packt Publishing Ltd, 2018. 1 online resource (264 pages) text txt rdacontent computer c rdamedia online resource cr rdacarrier Print version record. Cover; Title Page; Copyright and Credits; Packt Upsell; Contributors; Table of Contents; Preface; Chapter 1: Setup and Introduction to TensorFlow; The TensorFlow way of thinking; Setting up and installing TensorFlow; Conda environments; Checking whether your installation works; TensorFlow API levels; Eager execution; Building your first TensorFlow model; One-hot vectors; Splitting into training and test sets; Creating TensorFlow graphs; Variables; Operations; Feeding data with placeholders; Initializing variables; Training our model; Loss functions; Optimization; Evaluating a trained model The sessionSummary; Chapter 2: Deep Learning and Convolutional Neural Networks; AI and ML; Types of ML; Old versus new ML; Artificial neural networks; Activation functions; The XOR problem; Training neural networks; Backpropagation and the chain rule; Batches; Loss functions; The optimizer and its hyperparameters; Underfitting versus overfitting; Feature scaling; Fully connected layers; A TensorFlow example for the XOR problem; Convolutional neural networks; Convolution; Input padding; Calculating the number of parameters (weights); Calculating the number of operations Converting convolution layers into fully connected layersThe pooling layer; 1x1 Convolution; Calculating the receptive field; Building a CNN model in TensorFlow; TensorBoard; Other types of convolutions; Summary; Chapter 3: Image Classification in TensorFlow; CNN model architecture; Cross-entropy loss (log loss); Multi-class cross entropy loss; The train/test dataset split; Datasets; ImageNet; CIFAR; Loading CIFAR; Image classification with TensorFlow; Building the CNN graph; Learning rate scheduling; Introduction to the tf.data API; The main training loop; Model Initialization Do not initialize all weights with zerosInitializing with a mean zero distribution; Xavier-Bengio and the Initializer; Improving generalization by regularizing; L2 and L1 regularization; Dropout; The batch norm layer; Summary; Chapter 4: Object Detection and Segmentation; Image classification with localization; Localization as regression; TensorFlow implementation; Other applications of localization; Object detection as classification -- Sliding window; Using heuristics to guide us (R-CNN); Problems; Fast R-CNN; Faster R-CNN; Region Proposal Network; RoI Pooling layer Conversion from traditional CNN to Fully ConvnetsSingle Shot Detectors -- You Only Look Once; Creating training set for Yolo object detection; Evaluating detection (Intersection Over Union); Filtering output; Anchor Box; Testing/Predicting in Yolo; Detector Loss function (YOLO loss); Loss Part 1; Loss Part 2; Loss Part 3; Semantic segmentation; Max Unpooling; Deconvolution layer (Transposed convolution); The loss function; Labels; Improving results; Instance segmentation; Mask R-CNN; Summary; Chapter 5: VGG, Inception Modules, Residuals, and MobileNets; Substituting big convolutions Substituting the 3x3 convolution Convolutional Neural Networks (CNN) are one of the most popular architectures used in computer vision apps. This book is an introduction to CNNs through solving real-world problems in deep learning while teaching you their implementation in popular Python library - TensorFlow. By the end of the book, you will be training CNNs in no time! Neural networks (Computer science) Computer simulation. Réseaux neuronaux (Informatique) Simulation par ordinateur. Neural networks (Computer science) Computer simulation fast Tzanidou, Giounona. Burton, Richard. Patel, Nimesh. Araujo, Leonardo. has work: Hands-On Convolutional Neural Networks with TensorFlow (Text) https://id.oclc.org/worldcat/entity/E39PCFy94gTqWBjxbxdKkdB8wd https://id.oclc.org/worldcat/ontology/hasWork Print version: Zafar, Iffat. Hands-On Convolutional Neural Networks with TensorFlow : Solve Computer Vision Problems with Modeling in TensorFlow and Python. Birmingham : Packt Publishing Ltd, ©2018 9781789130331 FWS01 ZDB-4-EBA FWS_PDA_EBA https://search.ebscohost.com/login.aspx?direct=true&scope=site&db=nlebk&AN=1881049 Volltext |
| spellingShingle | Zafar, Iffat Hands-On Convolutional Neural Networks with TensorFlow : Solve Computer Vision Problems with Modeling in TensorFlow and Python. Cover; Title Page; Copyright and Credits; Packt Upsell; Contributors; Table of Contents; Preface; Chapter 1: Setup and Introduction to TensorFlow; The TensorFlow way of thinking; Setting up and installing TensorFlow; Conda environments; Checking whether your installation works; TensorFlow API levels; Eager execution; Building your first TensorFlow model; One-hot vectors; Splitting into training and test sets; Creating TensorFlow graphs; Variables; Operations; Feeding data with placeholders; Initializing variables; Training our model; Loss functions; Optimization; Evaluating a trained model The sessionSummary; Chapter 2: Deep Learning and Convolutional Neural Networks; AI and ML; Types of ML; Old versus new ML; Artificial neural networks; Activation functions; The XOR problem; Training neural networks; Backpropagation and the chain rule; Batches; Loss functions; The optimizer and its hyperparameters; Underfitting versus overfitting; Feature scaling; Fully connected layers; A TensorFlow example for the XOR problem; Convolutional neural networks; Convolution; Input padding; Calculating the number of parameters (weights); Calculating the number of operations Converting convolution layers into fully connected layersThe pooling layer; 1x1 Convolution; Calculating the receptive field; Building a CNN model in TensorFlow; TensorBoard; Other types of convolutions; Summary; Chapter 3: Image Classification in TensorFlow; CNN model architecture; Cross-entropy loss (log loss); Multi-class cross entropy loss; The train/test dataset split; Datasets; ImageNet; CIFAR; Loading CIFAR; Image classification with TensorFlow; Building the CNN graph; Learning rate scheduling; Introduction to the tf.data API; The main training loop; Model Initialization Do not initialize all weights with zerosInitializing with a mean zero distribution; Xavier-Bengio and the Initializer; Improving generalization by regularizing; L2 and L1 regularization; Dropout; The batch norm layer; Summary; Chapter 4: Object Detection and Segmentation; Image classification with localization; Localization as regression; TensorFlow implementation; Other applications of localization; Object detection as classification -- Sliding window; Using heuristics to guide us (R-CNN); Problems; Fast R-CNN; Faster R-CNN; Region Proposal Network; RoI Pooling layer Conversion from traditional CNN to Fully ConvnetsSingle Shot Detectors -- You Only Look Once; Creating training set for Yolo object detection; Evaluating detection (Intersection Over Union); Filtering output; Anchor Box; Testing/Predicting in Yolo; Detector Loss function (YOLO loss); Loss Part 1; Loss Part 2; Loss Part 3; Semantic segmentation; Max Unpooling; Deconvolution layer (Transposed convolution); The loss function; Labels; Improving results; Instance segmentation; Mask R-CNN; Summary; Chapter 5: VGG, Inception Modules, Residuals, and MobileNets; Substituting big convolutions Neural networks (Computer science) Computer simulation. Réseaux neuronaux (Informatique) Simulation par ordinateur. Neural networks (Computer science) Computer simulation fast |
| title | Hands-On Convolutional Neural Networks with TensorFlow : Solve Computer Vision Problems with Modeling in TensorFlow and Python. |
| title_auth | Hands-On Convolutional Neural Networks with TensorFlow : Solve Computer Vision Problems with Modeling in TensorFlow and Python. |
| title_exact_search | Hands-On Convolutional Neural Networks with TensorFlow : Solve Computer Vision Problems with Modeling in TensorFlow and Python. |
| title_full | Hands-On Convolutional Neural Networks with TensorFlow : Solve Computer Vision Problems with Modeling in TensorFlow and Python. |
| title_fullStr | Hands-On Convolutional Neural Networks with TensorFlow : Solve Computer Vision Problems with Modeling in TensorFlow and Python. |
| title_full_unstemmed | Hands-On Convolutional Neural Networks with TensorFlow : Solve Computer Vision Problems with Modeling in TensorFlow and Python. |
| title_short | Hands-On Convolutional Neural Networks with TensorFlow : |
| title_sort | hands on convolutional neural networks with tensorflow solve computer vision problems with modeling in tensorflow and python |
| title_sub | Solve Computer Vision Problems with Modeling in TensorFlow and Python. |
| topic | Neural networks (Computer science) Computer simulation. Réseaux neuronaux (Informatique) Simulation par ordinateur. Neural networks (Computer science) Computer simulation fast |
| topic_facet | Neural networks (Computer science) Computer simulation. Réseaux neuronaux (Informatique) Simulation par ordinateur. Neural networks (Computer science) Computer simulation |
| url | https://search.ebscohost.com/login.aspx?direct=true&scope=site&db=nlebk&AN=1881049 |
| work_keys_str_mv | AT zafariffat handsonconvolutionalneuralnetworkswithtensorflowsolvecomputervisionproblemswithmodelingintensorflowandpython AT tzanidougiounona handsonconvolutionalneuralnetworkswithtensorflowsolvecomputervisionproblemswithmodelingintensorflowandpython AT burtonrichard handsonconvolutionalneuralnetworkswithtensorflowsolvecomputervisionproblemswithmodelingintensorflowandpython AT patelnimesh handsonconvolutionalneuralnetworkswithtensorflowsolvecomputervisionproblemswithmodelingintensorflowandpython AT araujoleonardo handsonconvolutionalneuralnetworkswithtensorflowsolvecomputervisionproblemswithmodelingintensorflowandpython |