ece6504 deep learning for
play

ECE6504 Deep Learning for Perception Introduction to CAFFE Ashwin - PowerPoint PPT Presentation

Apr 15, 2023 β€’834 likes β€’1.39k views

ECE6504 Deep Learning for Perception Introduction to CAFFE Ashwin Kalyan V (C) Dhruv Batra 2 Logistic Regression as a Cascade (C) Dhruv Batra 3 Slide Credit: Marc'Aurelio Ranzato, Yann LeCun Logistic Regression as a Cascade (C) Dhruv

  1. ECE6504 – Deep Learning for Perception Introduction to CAFFE Ashwin Kalyan V

  2. (C) Dhruv Batra 2

  3. Logistic Regression as a Cascade (C) Dhruv Batra 3 Slide Credit: Marc'Aurelio Ranzato, Yann LeCun

  4. Logistic Regression as a Cascade (C) Dhruv Batra 4 Slide Credit: Marc'Aurelio Ranzato, Yann LeCun

  5. Logistic Regression as a Cascade (C) Dhruv Batra 5 Slide Credit: Marc'Aurelio Ranzato, Yann LeCun

  6. Key Computation: Forward-Prop (C) Dhruv Batra 6 Slide Credit: Marc'Aurelio Ranzato, Yann LeCun

  7. Key Computation: Back-Prop (C) Dhruv Batra 7 Slide Credit: Marc'Aurelio Ranzato, Yann LeCun

  8. Training using Stochastic Gradient Descent 𝑋 ≔ 𝑋 βˆ’ πœˆπ›Όπ‘€

  9. Training using Stochastic Gradient Descent Loss functions of NN are almost always non-convex 𝑋 ≔ 𝑋 βˆ’ πœˆπ›ΌL

  10. Training using Stochastic Gradient Descent Loss functions of NN are almost always non-convex 𝑋 ≔ 𝑋 βˆ’ πœˆπ›Όπ‘€ which makes training a little tricky. Many methods to find the optimum, like momentum update, Nesterov momentum update, Adagrad, RMSPRop, etc

  11. Network β€’ A network is a set of layers and its connections. β€’ Data and gradients move along the connections. β€’ Feed forward networks are Directed Acyclic graphs (DAG) i.e. they do not have any recurrent connections.

  12. Main types of deep architectures feed-forward Feed-back Neural nets Hierar. Sparse Coding Conv Nets Deconv Nets input input Bi-directional Recurrent Stacked Recurrent Neural nets Auto-encoders Recursive Nets DBM LISTA input input (C) Dhruv Batra 12 Slide Credit: Marc'Aurelio Ranzato, Yann LeCun

  13. Focus of this course feed-forward Feed-back Neural nets Hierar. Sparse Coding Conv Nets Deconv Nets input input Bi-directional Recurrent Stacked Recurrent Neural nets Auto-encoders Recursive Nets DBM LISTA input input (C) Dhruv Batra 13 Slide Credit: Marc'Aurelio Ranzato, Yann LeCun

  14. Focus of this class feed-forward Feed-back Neural nets Hierar. Sparse Coding Conv Nets Deconv Nets input input Bi-directional Recurrent Stacked Recurrent Neural nets Auto-encoders Recursive Nets DBM LISTA input input (C) Dhruv Batra 14 Slide Credit: Marc'Aurelio Ranzato, Yann LeCun

  15. Focus of this class feed-forward Feed-back Neural nets Hierar. Sparse Coding Why? Conv Nets Deconv Nets Because official CAFFE release supports DAG input input Bi-directional Recurrent Stacked Recurrent Neural nets Auto-encoders Recursive Nets DBM LISTA input input (C) Dhruv Batra 15 Slide Credit: Marc'Aurelio Ranzato, Yann LeCun

  16. Outline β€’ Caffe? β€’ Installation β€’ Key Ingredients β€’ Example: Softmax Classifier β€’ Pycaffe β€’ Roasting β€’ Resources β€’ References 16

  17. What is Caffe? Open framework, models, and worked examples for deep learning - 1.5 years - 450+ citations, 100+ contributors 2,500+ forks, >1 pull request / day average - - focus has been vision, but branching out: sequences, reinforcement learning, speech + text Prototype Train Deploy

  18. What is Caffe? Open framework, models, and worked examples for deep learning Pure C++ / CUDA architecture for deep learning - - Command line, Python, MATLAB interfaces Fast, well-tested code - Tools, reference models, demos, and recipes - - Seamless switch between CPU and GPU Prototype Train Deploy

  19. Installation

  20. Installation

  21. Installation β€’ Strongly recommended that you use Linux (Ubuntu)/ OS X. Windows has some unofficial support though. β€’ Prior to installing look at the installation page and the wiki - the wiki has more info. But all support needs to be taken with a pinch of salt - lots of dependencies β€’ Suggested that you back up your data!

  22. Installation β€’ CUDA (Compute Unified Device Architecture) is a parallel computing platform and application programming interface (API) model created by NVIDIA β€’ Installing CUDA – check if you have a cuda supported Graphics Processing Unit (GPU). If not, go for a cpu only installation of CAFFE. - Do not install the nvidia driver if you do not have a supported GPU

  23. Installation β€’ Clone the repo from here β€’ Depending on the system configuration, make modifications to the Makefile.config file and proceed with the installation instructions. β€’ We suggest that you use Anaconda python for the installation as it comes with the necessary python packages.

  24. Quick Questions?

  25. Key Ingredients

  26. DAG SDS two-stream net Many current deep models have linear structure GoogLeNet Inception Module Caffe nets can have any directed acyclic graph (DAG) structure. LRCN joint vision-sequence model

  27. name : "conv1" Blob type : CONVOLUTION bottom : "data" top : "conv1" … definition … Blobs are N-D arrays for storing and communicating information. top ● hold data, derivatives, and parameters blob ● lazily allocate memory ● shuttle between CPU and GPU Data N umber x K Channel x H eight x W idth 256 x 3 x 227 x 227 for ImageNet train input Parameter: Convolution Weight N Output x K Input x H eight x W idth 96 x 3 x 11 x 11 for CaffeNet conv1 bottom Parameter: Convolution Bias blob 96 x 1 x 1 x 1 for CaffeNet conv1

  28. Layer Protocol Setup : run once for initialization. Forward : make output given input. Backward : make gradient of output - w.r.t. bottom - w.r.t. parameters (if needed) Reshape : set dimensions. Compositional Modeling The Net’s forward and backward passes are Layer Development Checklist composed of the layers’ steps.

  29. Layers β€’ Caffe divides layers into - neuron layers (eg: Inner product), - Vision layers (Convolutional, pooling,etc) - Data layers (to read in input) - Loss layers β€’ You can write your own layers. More development guidelines are here

  30. Loss Classification loss (LOSS_TYPE) What kind of model is this? SoftmaxWithLoss HingeLoss Linear Regression EuclideanLoss Attributes / Multiclassification SigmoidCrossEntropyLoss Others… New Task Define the task by the loss . NewLoss

  31. Protobuf Model Format layer { - Strongly typed format name: "ip" - Auto-generates code type: "InnerProduct" - Developed by Google bottom: "data" top: "ip" - Defines Net / Layer / Solver inner_product_param { schemas in caffe.proto num_output: 2 } message ConvolutionParameter { } // The number of outputs for the layer optional uint32 num_output = 1; // whether to have bias terms optional bool bias_term = 2 [default = true]; }

  32. Softmax Classifier 𝑧 𝑀𝑝𝑑𝑑(π‘ž, 𝑧) π‘ž 𝑦 𝑋𝑦 + 𝑐

  33. Neural Network

  34. Activation function Rectified Linear Unit (ReLU) Activation

  35. Recipe for brewing a net β€’ Convert the data to caffe-supported format LMDB, HDF5, list of images β€’ Define the net β€’ Configure the solver β€’ Start train from supported interface (command line, python, etc)

  36. Layers – Data Layers β€’ Data Layers : gets data into the net - Data: LMDB/LEVELDB efficient way to input data, only for 1-of-k classification tasks - HDF5Data: takes in HDF5 format - easy to create custom non-image datasets but supports only float32/float64 - Data can be written easily in the above formats using python support. ( using lmdb and h5py respectively). We will see how to write hdf5 data shortly - Image Data: Reads in directly from images. Can be a little slow. - All layers (except hdf5) support standard data augmentation tasks

  37. Recipe for brewing a net β€’ Convert the data to caffe-supported format LMDB, HDF5, list of images β€’ Define the network/architecture β€’ Configure the solver β€’ Start train from supported interface (command line, python, etc)

  38. Example: Softmax Classifier Architecture file name: "LogReg" layer { name: "mnist" type: "Data" top: "data" top: "label" data_param { source: "input_leveldb" batch_size: 64 } }

  39. Example: Softmax Classifier Architecture file name: "LogReg" layer { name: "mnist" type: "Data" top: "data" top: "label" data_param { source: "input_leveldb" batch_size: 64 } } layer { name: "ip" type: "InnerProduct" bottom: "data" top: "ip" inner_product_param { num_output: 2 } }

  40. Example: Softmax Classifier Architecture file name: "LogReg" layer { name: "mnist" type: "Data" top: "data" top: "label" data_param { source: "input_leveldb" batch_size: 64 } } layer { name: "ip" type: "InnerProduct" bottom: "data" top: "ip" inner_product_param { num_output: 2 } } layer { name: "loss" type: "SoftmaxWithLoss" bottom: "ip" bottom: "label" top: "loss" }

  41. Recipe for brewing a net β€’ Convert the data to caffe-supported format LMDB, HDF5, list of images β€’ Define the net β€’ Configure the solver β€’ Start train from supported interface (command line, python, etc)

Recommend

Hao Su July 6, 2017 Outline Overview of 3D deep learning 3D deep learning algorithms

Hao Su July 6, 2017 Outline Overview of 3D deep learning 3D deep learning algorithms

Deep 3D Representation Learning for Visual Computing Hao Su July 6, 2017 Outline Overview of 3D deep learning 3D deep learning algorithms Conclusion 2 Outline Overview of 3D deep learning Background 3D deep learning tasks 3D deep

1.66k views β€’ 122 slides
ACCELERATE DEEP LEARNING WITH NVIDIA'S DEEP LEARNING PLATFORM | STEPHEN JONES | GTC16 DEEP

ACCELERATE DEEP LEARNING WITH NVIDIA'S DEEP LEARNING PLATFORM | STEPHEN JONES | GTC16 DEEP

ACCELERATE DEEP LEARNING WITH NVIDIA'S DEEP LEARNING PLATFORM | STEPHEN JONES | GTC16 DEEP LEARNING EVERYWHERE INTERNET & CLOUD MEDICINE & BIOLOGY MEDIA & ENTERTAINMENT SECURITY & DEFENSE AUTONOMOUS MACHINES Image

307 views β€’ 26 slides
Deep Learning on GPUs March 2016 What is Deep Learning? GPUs and DL AGENDA DL in practice

Deep Learning on GPUs March 2016 What is Deep Learning? GPUs and DL AGENDA DL in practice

Deep Learning on GPUs March 2016 What is Deep Learning? GPUs and DL AGENDA DL in practice Scaling up DL 2 What is Deep Learning? 3 DEEP LEARNING EVERYWHERE INTERNET & CLOUD MEDICINE & BIOLOGY SECURITY & DEFENSE MEDIA &

1.45k views β€’ 39 slides
Reproducibility and Replicability in Deep Reinforcement Learning (and Other Deep Learning

Reproducibility and Replicability in Deep Reinforcement Learning (and Other Deep Learning

Reproducibility and Replicability in Deep Reinforcement Learning (and Other Deep Learning Methods) Peter Henderson Statistical Society of Canada Annual Meeting 2018 Contributors Riashat Islam Phil Bachman Doina Precup David Meger Joelle

850 views β€’ 37 slides
Image Classification with DIGITS NVIDIA Deep Learning Institute 1 DEEP LEARNING INSTITUTE DLI

Image Classification with DIGITS NVIDIA Deep Learning Institute 1 DEEP LEARNING INSTITUTE DLI

Image Classification with DIGITS NVIDIA Deep Learning Institute 1 DEEP LEARNING INSTITUTE DLI Mission Helping people solve challenging problems using AI and deep learning. Developers, data scientists and engineers Self-driving cars,

1.44k views β€’ 72 slides
Deep Neural Networks and Deep Reinforcement Learning Deep Learning, Goodfellow, Bengio and

Deep Neural Networks and Deep Reinforcement Learning Deep Learning, Goodfellow, Bengio and

Deep Neural Networks and Deep Reinforcement Learning Deep Neural Networks and Deep Reinforcement Learning Deep Learning, Goodfellow, Bengio and Courville [chapt. 6,7,8]; AIMA [sect. 21.1-21.3]; Sutton and Barto, Reinforcement Learning: an

527 views β€’ 35 slides
Natural Language Processing with Deep Learning CS224N The Future of Deep Learning + NLP Kevin

Natural Language Processing with Deep Learning CS224N The Future of Deep Learning + NLP Kevin

Natural Language Processing with Deep Learning CS224N The Future of Deep Learning + NLP Kevin Clark Deep Learning for NLP 5 years ago No Seq2Seq No Attention No large-scale QA/reading comprehension datasets No TensorFlow or

1.41k views β€’ 92 slides
An Overview of Deep Residual Learning Semih Yagcioglu 01.03.2016 Deep Residual Learning

An Overview of Deep Residual Learning Semih Yagcioglu 01.03.2016 Deep Residual Learning

An Overview of Deep Residual Learning Semih Yagcioglu 01.03.2016 Deep Residual Learning Microsoft Research Asia (MSRA) Kaiming He, Xiangyu Zhang, Shaoqing Ren, & Jian Sun. Deep Residual Learning for Image Recognition. arXiv

1.32k views β€’ 54 slides
Deep Reinforcement Learning [Mastering the Game of Go with Deep Reinforcement Learning and Tree

Deep Reinforcement Learning [Mastering the Game of Go with Deep Reinforcement Learning and Tree

Deep Reinforcement Learning [Mastering the Game of Go with Deep Reinforcement Learning and Tree Search, Nature 2016] CS 486/686 University of Waterloo Lecture 21: July 12, 2017 Outline AlphaGo Supervised Learning of Policy Networks

540 views β€’ 15 slides
Mocha.jl Deep Learning in Julia Chiyuan Zhang (@pluskid) CSAIL, MIT Deep Learning Learning

Mocha.jl Deep Learning in Julia Chiyuan Zhang (@pluskid) CSAIL, MIT Deep Learning Learning

Mocha.jl Deep Learning in Julia Chiyuan Zhang (@pluskid) CSAIL, MIT Deep Learning Learning with multi-layer (3~30) neural networks, on a huge training set. State-of-the-art on many AI tasks Computer Vision : Image Classification,

1.53k views β€’ 23 slides
Minjie Wang Deep Learning Deep Learning trend in the past 10 years Caffe State-of-art DL

Minjie Wang Deep Learning Deep Learning trend in the past 10 years Caffe State-of-art DL

Tofu: Parallelizing Deep Learning Systems with Automatic Tiling Minjie Wang Deep Learning Deep Learning trend in the past 10 years Caffe State-of-art DL system is based on dataflow GPU#0 w1 w2 data g1 g2 Forward propagation

405 views β€’ 38 slides
Deep Learning: Theory and Practice Deep Learning - Practical 02-04-2020 Considerations

Deep Learning: Theory and Practice Deep Learning - Practical 02-04-2020 Considerations

Deep Learning: Theory and Practice Deep Learning - Practical 02-04-2020 Considerations deeplearning.cce2020@gmail.com Deep Networks Intuition Neural networks with multiple hidden layers - Deep networks [Hinton, 2006] Deep Networks Intuition

1.33k views β€’ 28 slides
Deep Learning: State of the Art (2020) Deep Learning Lecture Series https://deeplearning.mit.edu

Deep Learning: State of the Art (2020) Deep Learning Lecture Series https://deeplearning.mit.edu

Deep Learning: State of the Art (2020) Deep Learning Lecture Series https://deeplearning.mit.edu 2020 For the full list of references visit: http://bit.ly/deeplearn-sota-2020 Outline Deep Learning Growth, Celebrations, and Limitations

1.1k views β€’ 87 slides
12. Unsupervised Deep Learning CS 535 Deep Learning, Winter 2018 Fuxin Li With materials from

12. Unsupervised Deep Learning CS 535 Deep Learning, Winter 2018 Fuxin Li With materials from

12. Unsupervised Deep Learning CS 535 Deep Learning, Winter 2018 Fuxin Li With materials from Wanli Ouyang, Zsolt Kira, Lawrence Neal, Raymond Yeh, Junting Lou and Teck-Yian Lim Unsupervised Learning in General Unsupervised learning is

1.48k views β€’ 115 slides
Regularization for Deep Learning Lecture slides for Chapter 7 of Deep Learning

Regularization for Deep Learning Lecture slides for Chapter 7 of Deep Learning

Regularization for Deep Learning Lecture slides for Chapter 7 of Deep Learning www.deeplearningbook.org Ian Goodfellow 2016-09-27 Definition Regularization is any modification we make to a learning algorithm that is intended to reduce

179 views β€’ 13 slides
Introduction to Deep Learning Outline Deep Learning RNN CNN Attention

Introduction to Deep Learning Outline Deep Learning RNN CNN Attention

Introduction to Deep Learning Outline Deep Learning RNN CNN Attention Transformer Pytorch Introduction Basics Examples RNNs Some slides borrowed from Fei-Fei Li & Justin Johnson &

1.1k views β€’ 55 slides
Deep learning for NLP: Introduction CS 6956: Deep Learning for NLP Words are a very fantastical

Deep learning for NLP: Introduction CS 6956: Deep Learning for NLP Words are a very fantastical

Deep learning for NLP: Introduction CS 6956: Deep Learning for NLP Words are a very fantastical banquet, just so many strange dishes And yet, we seem to do fine We can understand and generate language effortlessly. Almost 1 Wouldnt it be

1.62k views β€’ 52 slides
Deep Reinforcement Learning and Complex Environments Raia Hadsell End-to-end Deep Learning

Deep Reinforcement Learning and Complex Environments Raia Hadsell End-to-end Deep Learning

Deep Reinforcement Learning and Complex Environments Raia Hadsell End-to-end Deep Learning for robots? slide from V. Vanhoucke End-to-end Deep Learning for robots? 2010 : Speech Recognition Audio Acoustic Model Phonetic Model

1.05k views β€’ 65 slides
Bayesian Deep Learning Mohd Adnan Problems With Deep Learning What does a model not know?

Bayesian Deep Learning Mohd Adnan Problems With Deep Learning What does a model not know?

Bayesian Deep Learning Mohd Adnan Problems With Deep Learning What does a model not know? Uninterpretable black-boxes Easily fooled (AI safety) Lacks solid mathematical foundation Crucially relies on big dat Why

297 views β€’ 15 slides
Deep Learning on Massively Parallel Processing Databases Frank McQuillan Feb 2019 2 A Brief

Deep Learning on Massively Parallel Processing Databases Frank McQuillan Feb 2019 2 A Brief

Deep Learning on Massively Parallel Processing Databases Frank McQuillan Feb 2019 2 A Brief Introduction to Deep Learning Artificial Intelligence Landscape Deep Learning 4 Example Deep Learning Algorithms Multilayer Recurrent

651 views β€’ 44 slides
Deep Learning with Neural Networks The Structure and Optimization of Deep Neural Networks Allan

Deep Learning with Neural Networks The Structure and Optimization of Deep Neural Networks Allan

Deep Learning with Neural Networks The Structure and Optimization of Deep Neural Networks Allan Zelener Machine Learning Reading Group January 7 th 2016 The Graduate Center, CUNY Objectives Explain some of the trends of deep learning and

680 views β€’ 44 slides
DSSTNE: Deep Learning At Scale For Large Sparse Datasets

DSSTNE: Deep Learning At Scale For Large Sparse Datasets

DSSTNE: Deep Learning At Scale For Large Sparse Datasets https://github.com/amznlabs/amazon-dsstne Scott Le Grand Senior Scientist Teza Technologies varelse2005@gmail.com Outline What's Deep Learning? Why GPUs? Deep Learning for

1.55k views β€’ 76 slides
Deep Learning With Differential Privacy Presenter: Xiaojun Xu Deep Learning Framework

Deep Learning With Differential Privacy Presenter: Xiaojun Xu Deep Learning Framework

Deep Learning With Differential Privacy Presenter: Xiaojun Xu Deep Learning Framework Autonomous Driving Gaming Face Recognition Healthcare Deep Learning Framework Dataset Server Model Privacy Issues of Training Data Dataset Server

366 views β€’ 33 slides
Presentation about Deep Learning --- Zhongwu xie Contents 1.Brief introduction of Deep learning.

Presentation about Deep Learning --- Zhongwu xie Contents 1.Brief introduction of Deep learning.

Presentation about Deep Learning --- Zhongwu xie Contents 1.Brief introduction of Deep learning. 2.Brief introduction of Backpropagation. 3.Brief introduction of Convolutional Neural Networks. Deep learning I . Introduction to Deep Learning

609 views β€’ 22 slides

More recommend