Scribd Logo
Upload

Welcome to Scribd!

  • 191 views

    Nvidia Fundamentals of Deep Learning PPT 4

    Uploaded by

    Ron
    This document discusses data augmentation and model deployment in deep learning. It begins with an agenda that outlines parts 1 through 6 of the fundamentals of deep learning series. It then discusses how data augmentation can help increase validation accuracy by exposing the model to more varied examples. Various image augmentation techniques are presented, including flipping, rotating, zooming, and altering brightness. The document concludes by covering model deployment, from taking batched input images through the network to output predictions, preparing the model for real-world use.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd

    Nvidia Fundamentals of Deep Learning PPT 4

    Uploaded by

    Ron
    191 views19 pages
    This document discusses data augmentation and model deployment in deep learning. It begins with an agenda that outlines parts 1 through 6 of the fundamentals of deep learning series. It then discusses how data augmentation can help increase validation accuracy by exposing the model to more varied examples. Various image augmentation techniques are presented, including flipping, rotating, zooming, and altering brightness. The document concludes by covering model deployment, from taking batched input images through the network to output predictions, preparing the model for real-world use.

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document discusses data augmentation and model deployment in deep learning. It begins with an agenda that outlines parts 1 through 6 of the fundamentals of deep learning series. It then discusses how data augmentation can help increase validation accuracy by exposing the model to more varied examples. Various image augmentation techniques are presented, including flipping, rotating, zooming, and altering brightness. The document concludes by covering model deployment, from taking batched input images through the network to output predictions, preparing the model for real-world use.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    191 views19 pages

    Nvidia Fundamentals of Deep Learning PPT 4

    Uploaded by

    Ron
    This document discusses data augmentation and model deployment in deep learning. It begins with an agenda that outlines parts 1 through 6 of the fundamentals of deep learning series. It then discusses how data augmentation can help increase validation accuracy by exposing the model to more varied examples. Various image augmentation techniques are presented, including flipping, rotating, zooming, and altering brightness. The document concludes by covering model deployment, from taking batched input images through the network to output predictions, preparing the model for real-world use.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    You are on page 1of 19

    FUNDAMENTALS OF

    DEEP LEARNING
    Part 4: Data Augmentation and Deployment

    1
    Part 1: An Introduction to Deep Learning

    Part 2: How a Neural Network Trains

    AGENDA Part 3: Convolutional Neural Networks

    Part 4: Data Augmentation and Deployment

    Part 5: Pre-trained Models

    Part 6: Advanced Architectures


    AGENDA – PART 4
    • Data Augmentation
    • Model Deployment
    RECAP OF THE EXERCISE

    Analysis Solution

    • CNN increased validation • Clean data provides better


    accuracy examples
    • Still seeing training accuracy • Dataset variety helps the model
    higher than validation generalize
    DATA AUGMENTATION
    6
    DATA AUGMENTATION

    7
    IMAGE FLIPPING
    Horizontal Flip
    Horizontal Flip

    Vertical Flip
    Vertical Flip

    8
    ROTATION

    0⁰

    31 45
    5⁰ ⁰

    270⁰
    90⁰

    5⁰
    5⁰
    2
    3
    2
    1
    180⁰

    9
    ZOOMING

    10
    WIDTH AND HEIGHT
    SHIFTING

    11
    HOMOGRAPHY

    12
    BRIGHTNESS

    13
    CHANNEL
    SHIFTING

    14
    MODEL DEPLOYMENT
    15
    MODEL DEPLOYMENT

    …
    …

    …
    (28, 28, 2) (28, 28, 2)
    Stacked Images Stacked Images

    (3, 3, 1, 2) (3, 3, 2, 2) (512) (512)


    Kernels Kernels Dense Dense
    (28, 28,1) (1568)
    Image Input Flattened Image (24)
    Vector Output Prediction
    MODEL DEPLOYMENT

    Training
    Batch Input

    Convolution

    Max Pooling

    …
    MODEL DEPLOYMENT

    (220, 155, 3) (220, 155, 1)


    (1, 220, 155, 1)
    (287, 433, 3)

    Resize Greyscale “Batch”


    18
    LET’S TRY IT OUT!
    19
    20

    You might also like