Deep Learning For Vision Analytics. SAS User Group Malaysia 3 rd May, 2018

Similar documents
Transcription:

Deep Learning For Vision Analytics SAS User Group Malaysia 3 rd May, 2018

Agenda Preface Machine Learning vs Deep Learning Create/train/score Machine Learning model using SAS VDMML Deep Learning What? Use cases How? Image classification Basic CNN architecture Layer explanation (convolution/pooling/fully connected) Deploy Create/train/score/deploy Deep Learning model using Jupyter Notebook

Preface

Machine Learning vs Deep Learning Machine Learning For structured data: Information with high degree of organization. Deep Learning For unstructured data such as: Strings of texts, images and sounds. Most experts agree that structured data accounts for about 20% of the data that is out there.

SAS Platform Visual Data Mining & Machine Learning (VDMML) Interactive programming in a web-based development environment. Highly scalable, distributed in-memory analytical processing. Model development with modern machine learning algorithms. Random forests, gradient boosting, neural networks, support vector machines, factorization machines, Bayesian networks. Automatic intelligent tuning. Analytical data preparation. Data exploration, feature binning and dimension reduction. Integrated text analytics. Model assessment. Model scoring.

SAS Platform Discovery - Basic

SAS Platform Discovery - Advanced

What? Vision Analytics Use Cases in Oil & Gas

Health, Safety & Environment Oil & Gas

Health, Safety & Environment Oil & Gas

Workplace Safety Leveraging on cameras placed around workplace Identify employee by name and authorization. Where is the power drill? Is the employee certified to handle a power drill? Is the power drill stored safely at the original location? Is employee equipped with the necessary PPE? Monitor if employee is trespassing. Early warning for incidents and hazardous situations. Monitor integrity of assets.

Workplace safety: Deep Learning on Sound

Vision Analytics Use Cases Oil & Gas Upstream Analyze seabed for oil seeps, which may serve as an indicator of hydrocarbon presence and for the purpose of protecting the ecosystem. Midstream Monitor hard-to-reach pipelines using bots for early signs which indicates the need for maintenance or replacements. Downstream Smarter retail experience for increased customer satisfaction.

Workplace Safety Example: Hard hat image detection

Image Classification For us, identifying whether someone is wearing a hard hat or not is effortless How do we create and train a machine to do the same???

How?

Image Classification using Deep Learning Convolutional Neural Network (CNN) Convolutional neural network to analyse images. Why? Powerful (analyse and classify images very well) Efficient (less parameters than previous methods) Source: http://sww.sas.com/saspedia/future_documentation_of_deep_learning CNN takes image (volume of pixels of varying values) and outputs probability

Types of CNN Architecture LeNet-5 VGG16 AlexNet Etc

Example CNN architecture Convolution Layer Source: https://www.packtpub.com/mapt/book/big_data_and_business_intelligence/9781788397872/6/ch06lvl1sec69/common-cnn-architecture---lenet

Convolution Layer Enables parameter sharing in a CNN https://www.analyticsvidhya.com/blog/2017/06/architecture-of-convolutional-neural-networks-simplified-demystified/

Convolution Layer How is it done? SWAT.deeplearn.addlayer(layer={ type : convo, nfilters :1, height :3, width :3, stride :1 } Source: https://hackernoon.com/visualizingparts-of-convolutional-neural-networksusing-keras-and-cats-5cc01b214e59

Feature Detector & Feature Maps Video example: https://www.youtube.com/watch?v=gu0mkmynwkw Source: https://adeshpande3.github.io/adeshpande3.github.io/a-beginner's-guide-to-understanding-convolutional-neural-networks/

Example CNN architecture Pooling Layer Source: https://www.packtpub.com/mapt/book/big_data_and_business_intelligence/9781788397872/6/ch06lvl1sec69/common-cnn-architecture---lenet

Pooling Layer Reduces the number of trainable parameters in a CNN https://www.analyticsvidhya.com/blog/2017/06/architecture-of-convolutional-neural-networks-simplified-demystified/

Pooling Layer How is it done? SWAT.deeplearn.addlayer(layer={ type : pool, height :2, width :2, stride :2, pool : MAX } Source: https://en.wikipedia.org/wiki/convolutional_neural_network Video example: https://www.youtube.com/watch?v=mw3kyfzdniq

Example CNN architecture Fully Connected Layer Source: https://www.packtpub.com/mapt/book/big_data_and_business_intelligence/9781788397872/6/ch06lvl1sec69/common-cnn-architecture---lenet

Fully Connected Layer Enables high-level reasoning Neurons in a fully connected layer have connections to all activations in the previous layer(s), as seen in regular neural networks. Information flows through a neural network in 2 ways: Normal (Feedforward) Learning (Backpropogation) https://www.youtube.com/watch?v=airc AruvnKk

Deployment SAS VDMML (Model studio) Operational Training SAS ESP (Event streaming)

Creating/training/scoring/deploying a CNN Using deeplearn action sets in Jupyter Notebook on SAS Viya 3.3

Useful Links What s New In SAS Deep Learning (Documentation) http://go.documentation.sas.com/?docsetid=casdlpg&docsettarget=p0uhs 7ywfs6e4kn160kru9w97fyz.htm&docsetVersion=8.2&locale=en Understanding Convolutional Neural Networks https://adeshpande3.github.io/a-beginner%27s-guide-to-understanding- Convolutional-Neural-Networks/ CS231n Convolutional Neural Networks for Visual Recognition http://cs231n.github.io/