Scribd
Upload
30 views19 pages

Slides 4

Uploaded by

carlosbarroscarlos
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
30 views19 pages

Slides 4

Uploaded by

carlosbarroscarlos
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 19

Fundamentals of

Deep Learning
Part 4: Data Augmentation and Deployment
Agenda
• Part 1: An Introduction to Deep Learning

• Part 2: How a Neural Network Trains

• Part 3: Convolutional Neural Networks

• Part 4: Data Augmentation and Deployment

• Part 5: Pre-Trained Models

• Part 6: Advanced Architectures


Recap of the Exercise

Analysis

• CNN increased validation


accuracy
• Still seeing training accuracy
higher than validation
Recap of the Exercise

Analysis Solution

• CNN increased validation • Clean data provides better


accuracy examples
• Still seeing training accuracy • Dataset variety helps the
higher than validation model generalize
Data Augmentation
Data Augmentation
Image Flipping
Horizontal
Flip

Vertical Flip
Rotation

0⁰

31 45
5⁰ ⁰

270⁰
90⁰

⁰
⁰
5
5
2
3
2
1
180⁰
Zooming
Width And Height
Shifting
Homography
Brightness
Channel
Shifting
Model Deployment
Model Deployment

…
…

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

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


Kernels Kernels Linear Linear
(1, 28, 28) (1568)
Image Input Flattened Image (10)
Vector Output Prediction
Model Deployment

Training
Batch Input

Convolution

Max Pooling

…
Model Deployment

(3, 220, (1, 220,


155) 155) (1, 1, 220,
155)
(3, 287, 433)
Greyscal
Resize “Batch”
e
Let’s Try It Out!

You might also like