Deep Learning for Developers (January 2018)
Download as PPTX, PDF3 likes330 views
The document discusses deep learning for developers, particularly focusing on common neural network architectures, use cases, and the introduction to Apache MXNet. It highlights the computational power of AWS EC2 instances, comparing performance metrics, and shares real-world applications of AI like image recognition and child exploitation detection. Additionally, it provides resources and links to further explore deep learning technologies.
Deep Learning for Developers (January 2018)
- 1. Deep Learning for Developers Julien Simon, AI Evangelist, EMEA @julsimon
- 2. What to expect • AI ? • Common neural network architectures and use cases • An introduction to Apache MXNet • Demos • Resources
- 3. Myth: AI is dark magic aka « You’re not smart enough »
- 4. Fact: AI is math, code and chips A bit of Science, a lot of Engineering
- 6. Amazon EC2 P3 Instances • Up to eight NVIDIA Tesla V100 GPUs • 1 PetaFLOPs of computational performance – 14x better than P2 • 300 GB/s GPU-to-GPU communication (NVLink) – 9X better than P2 • 16GB GPU memory with 900 GB/sec peak GPU memory bandwidth T h e f a s t e s t , m o s t p o w e r f u l G P U i n s t a n c e s i n t h e c l o u d
- 7. Amazon EC2 C5 with Intel® Xeon® Scalable Processor AVX 512 72 vCPUs “Skylake” 144 GiB memory C5 12 Gbps to EBS 2X vCPUs 2X performance 3X throughput 2.4X memory C4 36 vCPUs “Haswell” 4 Gbps to EBS 60 GiB memory C5: Nex t Ge ne rat ion Compute - Opt imize d Insta nc e s wit h Inte l® Xe on® Sca la ble Proc e ssor AWS Compute opt imize d insta nc e s support t he new Inte l® AV X - 512 a dva nc e d inst ruc t ion set , e na bling you to more eff ic ie nt ly run ve c tor proc e ssing work loa ds wit h single a nd double floating point pre c ision, suc h a s AI/ma c hine le a rning or v ide o proc e ssing.
- 8. EU (Ireland) Region Linux On Demand PricingvCPU ECU Memory (GiB) Instance Storage (GB) Linux/UNIX Usage CPU c5.large 2 8 4 EBS Only $0.096 per Hour c5.xlarge 4 16 8 EBS Only $0.192 per Hour c5.2xlarge 8 31 16 EBS Only $0.384 per Hour c5.4xlarge 16 62 32 EBS Only $0.768 per Hour c5.9xlarge 36 139 72 EBS Only $1.728 per Hour c5.18xlarge 72 278 144 EBS Only $3.456 per Hour GPU p2.xlarge 4 12 61 EBS Only $0.972 per Hour p2.8xlarge 32 94 488 EBS Only $7.776 per Hour p2.16xlarge 64 188 732 EBS Only $15.552 per Hour p3.2xlarge 8 23.5 61 EBS Only $3.305 per Hour p3.8xlarge 32 94 244 EBS Only $13.22 per Hour p3.16xlarge 64 188 488 EBS Only $26.44 per Hour Source - https://aws.amazon.com/ec2/pricing/on-demand/?refid=em_67469 As of 19th January 2018
- 9. 9 EC2 Spot instances for training & inference GPU - p3.16xlarge CPU - c5.18xlarge C5 CPU Resources Available for Up to 19.8X cheaper over a 3 Month average As of 19th January 2018 Source – Spot Pricing History Tool in EC2 Console https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/using-spot-instances-history.html
- 10. Common network architectures and use cases
- 11. Convolutional Neural Networks (CNN) Le Cun, 1998: handwritten digit recognition, 32x32 pixels Convolution and pooling reduce dimensionality https://devblogs.nvidia.com/parallelforall/deep-learning-nutshell-core-concepts/
- 12. https://news.developer.nvidia.com/expedia-ranking-hotel-images-with-deep-learning/ • Expedia have over 10 million images from 300,000 hotels • Using great images boosts conversion • Using Keras and EC2 GPU instances, they fine-tuned a pre-trained Convolutional Neural Network using 100,000 images • Hotel descriptions now automatically feature the best available images CNN: Object Classification
- 13. CNN: Object Detection https://github.com/precedenceguo/mx-rcnn https://github.com/zhreshold/mxnet-yolo MXNet
- 15. https://www.oreilly.com/ideas/self-driving-trucks-enter-the-fast-lane-using-deep-learning Last June, tuSimple drove an autonomous truck for 200 miles fromYuma, AZ to San Diego, CA MXNet
- 17. Solution Thorn and AWS-partner, MemSQL, built an age progressed facial recognition service using data analytics and deep learning on AWS compute-optimized C5 to identify missing children by matching images against child abuse material. Using the compute power of Intel® Xeon® Scalable processors in C5, Thorn is able to match thousands of pictures per second, in real time, against a database of pictures that is being constantly updated. The goal is to eventually integrate this capability into Spotlight, Thorn’s trafficking investigations tool that is used by more than 5,300 officers in over 18 countries Outcome Thorn can apply 5,000 data points to a single face and classify, correlate, and match the image to an image in a database. As a result, the organization’s solution can make a positive image match in 200 milliseconds, compared to 20 minutes previously. Spotlight Identifies an average of 5 kids per day. Source: https://itpeernetwork.intel.com/digital-defenders-fight-child-exploitation/ www.wearethorn.org 350 volunteers/members United States Non Profit Organization Thorn, a global nonprofit organization headquartered in Los Angeles, CA joins forces with the sharpest minds from tech, non-profit, government and law enforcement to stop the spread of child sexual exploitation and abuse material and stand up to child traffickers. www.memsql.com Partner MemSQL is a real-time data warehouse for cloud and on-premises that delivers immediate insights across live and historical data. AI helps find missing kids
- 19. Long Short Term Memory Networks (LSTM) • A LSTM neuron computes the output based on the input and a previous state • LSTM networks have memory • They’re great at predicting sequences, e.g. machine translation
- 21. GAN: Welcome to the (un)real world, Neo Generating new ”celebrity” faces https://github.com/tkarras/progressive_growing_of_gans From semantic map to 2048x1024 picture https://tcwang0509.github.io/pix2pixHD/
- 22. Apache MXNet
- 23. Apache MXNet: Open Source library for Deep Learning Programmable Portable High Performance Near linear scaling across hundreds of GPUs Highly efficient models for mobile and IoT Simple syntax, multiple languages Most Open Best On AWS Optimized for Deep Learning on AWS Accepted into the Apache Incubator MXNet 1.0 released on December 4th
- 24. Input Output 1 1 1 1 0 1 0 0 0 3 mx. sym. Convol ut i on( dat a, ker nel =( 5, 5) , num_f i l t er =20) mx. sym. Pool i ng( dat a, pool _t ype=" max" , ker nel =( 2, 2) , st r i de=( 2, 2) l st m. l st m_unr ol l ( num_l st m_l ayer , seq_l en, l en, num_hi dden, num_embed) 4 2 2 0 4=Max 1 3 ... 4 0.2 -0.1 ... 0.7 mx. sym. Ful l yConnect ed( dat a, num_hi dden=128) 2 mx. symbol . Embeddi ng( dat a, i nput _di m, out put _di m = k) 0.2 -0.1 ... 0.7 Queen 4 2 2 0 2=Avg Input Weights cos(w, queen ) = cos(w, k i n g) - cos(w, m an ) + cos(w, w om an ) mx. sym. Act i vat i on( dat a, act _t ype=" xxxx" ) " r el u" " t anh" " si gmoi d" " sof t r el u" Neural Art Face Search Image Segmentation Image Caption “ People Riding Bikes” Bicycle, People, Road, Sport Image Labels Image Video Speech Text “ People Riding Bikes” Machine Translation “ Οι άνθρωποι ιππασίας ποδήλατα” Events mx. model . FeedFor war d model . f i t mx. sym. Sof t maxOut put
- 27. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. The Apache MXNet API • Storing and accessing data in multi-dimensional arrays NDArray API • Building models (layers, weights, activation functions) Symbol API • Serving data during training and validation Iterators • Training and using models Module API
- 28. Demos - Hello World: learn a synthetic data set - Classify images with pre-trained models - Classify MNIST with a MLP and a CNN https://github.com/juliensimon/dlnotebooks
- 29. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Resources https://aws.amazon.com/machine-learning https://aws.amazon.com/blogs/ai https://mxnet.incubator.apache.org https://github.com/apache/incubator-mxnet https://github.com/gluon-api https://medium.com/@julsimon https://medium.com/@julsimon/10-steps-on-the-road-to-deep-learning-part-1- f9e4b5c0a459
- 31. Thank you! Julien Simon, AI Evangelist, EMEA @julsimon
Editor's Notes
- #24: XXX CPU and GPU