LEADER 00000cam 2200337Ii 4500 001 sky299312019 003 SKY 005 20200602135200.0 008 190821t20202020caua 001 0 eng d 020 9781484253489 020 1484253485 040 YDX|beng|erda|cYDX|dJRZ|dSKYRV|dUtOrBLW 092 006.31|bTEN 2020 100 1 El-Amir, Hisham,|eauthor. 245 10 Deep learning pipeline :|bbuilding a deep learning model with TensorFlow /|cHisham El-Amir, Mahmoud Hamdy 264 1 [California] :|bApress,|c[2020] 264 4 |c©2020 300 xxv, 551 pages :|billustrations ;|c24 cm 336 text|btxt|2rdacontent 336 still image|bsti|2rdacontent 337 unmediated|bn|2rdamedia 338 volume|bnc|2rdacarrier 500 Includes index 505 00 |tPart 1. Introduction. Gentle introduction --|tSetting up your environment --|tA tour through the deep learning pipeline --|tBuild your first toy TensorFlow app --|tPart 2. Data. Defining data --|tData wrangling and preprocessing --|tData resampling --|tFeature selection and feature engineering --|tPart 3. TensorFlow. Deep learning fundamentals --|tImproving deep neural networks - -|tConvolutional neural network --|tSequential models -- |tPart 4. Applying what you've learned. Selected topics in computer vision --|tSelected topics in natural language processing --|tApplications 520 "Build your own pipeline based on modern TensorFlow approaches rather than outdated engineering concepts. This book shows you how to build a deep learning pipeline for real-life TensorFlow projects. You'll learn what a pipeline is and how it works so you can build a full application easily and rapidly. Then troubleshoot and overcome basic Tensorflow obstacles to easily create functional apps and deploy well-trained models. Step-by- step and example-oriented instructions help you understand each step of the deep learning pipeline while you apply the most straightforward and effective tools to demonstrative problems and datasets. You'll also develop a deep learning project by preparing data, choosing the model that fits that data, and debugging your model to get the best fit to data all using Tensorflow techniques. Enhance your skills by accessing some of the most powerful recent trends in data science. If you've ever considered building your own image or text-tagging solution or entering a Kaggle contest, "Deep learning pipeline" is for you!"--|cProvided by publisher 630 00 TensorFlow. 650 0 Machine learning. 650 0 Neural networks (Computer science) 700 1 Hamdy, Mahmoud,|eauthor.
|