Deep learning at Microsoft
|
|
- Monica Watts
- 6 years ago
- Views:
Transcription
1
2
3 Deep learning at Services Skype Translator Cortana Bing HoloLens Research
4 Services
5
6 ImageNet: 2015 ResNet ImageNet Classification top-5 error (%) ILSVRC 2010 NEC America ILSVRC 2011 Xerox ILSVRC 2012 AlexNet ILSVRC 2013 Clarifi ILSVRC 2014 VGG ILSVRC 2014 GoogleNet ILSVRC 2015 ResNet had all 5 entries being the 1-st places this year: ImageNet classification, ImageNet localization, ImageNet detection, COCO detection, and COCO segmentation
7
8 Image Similarity Goal: given query image, find similar images. Customer: Anonymous ISV (Azure Partner) Task: given a retail image, find same product on competitor websites (to compare price). Existing solution: solely based on mining text information from the websites of Target, Macy, etc. Customer asked for individual similarity measure (e.g. texture, neck style, etc).
9 Bing / Bing Ads
10 Translator Power point-plug in for translating speech to subtitles
11 s historic speech breakthrough 2016 research system for conversational speech recognition 5.9% word-error rate enabled by CNTK s multi-server scalability [W. Xiong, J. Droppo, X. Huang, F. Seide, M. Seltzer, A. Stolcke, D. Yu, G. Zweig: Achieving Human Parity in Conversational Speech Recognition,
12 Customer Support Agent
13
14 (CNTK) s open-source deep-learning toolkit Created by Speech researchers (Dong Yu et al.) in 2012, Computational Network On GitHub since Jan 2016 under MIT license Python support since Oct 2016 (beta), rebranded as External contributions e.g. from MIT, Stanford and NVidia
15 (CNTK) Over 80% internal DL workload runs CNTK 1st-class on Linux and Windows, docker support Python, C++, C#, Java Internal == External
16 CTNK The Fastest Benchmarking by HKBU, Version 8 Single Tesla K80 GPU, CUDA: 8.0 CUDNN: v5.1 Caffe: 1.0rc5(39f28e4) CNTK: 2.0 Beta10(1ae666d) MXNet: 0.93(32dc3a2) TensorFlow: 1.0(4ac9c09) Torch: 7(748f5e3) Caffe CNTK MxNet TensorFlow Torch FCN5 (1024) ms ms ms ms ms AlexNet (256) ms ms ms ms ms ResNet (32) ms ms ms ms ms LSTM (256) (v7 benchmark) ms (44.917ms) ms ( ms) - ( ms) ms ( ms)
17 CNTK is production-ready: State-of-the-art accuracy, efficient, and scales to multi-gpu/multi-server speed comparison (samples/second), higher = better [note: December 2015] Achieved with 1-bit gradient quantization algorithm Theano only supports 1 GPU CNTK Theano TensorFlow Torch 7 Caffe 1 GPU 1 x 4 GPUs 2 x 4 GPUs (8 GPUs)
18 Superior performance
19 Scalability
20 What is new in CNTK 2.0? has now released a major upgrade of the software and rebranded it as part of the. This release is a major improvement over the initial release. There are two major changes from the first release that you will see when you begin to look at the new release. First is that CNTK now has a very nice Python API and, second, the documentation and examples are excellent. Installing the software from the binary builds is very easy on both Ubuntu Linux and Windows.
21 CNTK Other Advantages Python and C++ API Mostly implemented in C++ Low level + high level Python API Extensibility User functions and learners in pure Python Readers Distributed, highly efficient built-in data readers Internal == External
22
23 The (CNTK) CNTK expresses (nearly) arbitrary neural networks by composing simple building blocks into complex computational networks, supporting relevant network types and applications. CNTK is production-ready: State-of-the-art accuracy, efficient, and scales to multi-gpu/multi-server.
24 MNIST Handwritten Digits (OCR) Handwritten Digits Data set of hand written digits with 60,000 training images 10,000 test images Each image is: 28 x 28 pixels Corresponding Labels
25 .. Multi-layer perceptron 784 pixels (x) Deep Model 28 pix 28 pix D D D i = 784 O= 400 a = relu i = 400 O= 200 a = relu 10 nodes i = 200 O= 10 a = None Weights bias bias bias 200 z0 z1 z2 z3 z4 z5 z6 z7 z8 z9 softmax e z i σ9 j=0 e z j
26 . Loss function Label One-hot encoded (Y) x 28 pix (p) 28 pix Loss function 9 ce = σ j=0 y j log p j Cross entropy error 28 pix Model (w, b) Predicted Probabilities (p)
27 CNTK Model Example: 2-hidden layer feed-forward NN h 1 = s(w 1 x + b 1 ) h1 = sigmoid W1 + b1) h 2 = s(w 2 h 1 + b 2 ) h2 = sigmoid W2 + b2) P = softmax(w out h 2 + b out ) P = softmax Wout + bout) with input x R M and one-hot label y R J and cross-entropy training criterion ce = y T log P ce = cross_entropy (L, P)
28 CNTK Model example: 2-hidden layer feed-forward NN h 1 = s(w 1 x + b 1 ) h1 = sigmoid W1 + b1) h 2 = s(w 2 h 1 + b 2 ) h2 = sigmoid W2 + b2) P = softmax(w out h 2 + b out ) P = softmax Wout + bout) with input x R M and one-hot label y R J and cross-entropy training criterion ce = y T log P ce = cross_entropy (P, y)
29 CNTK Model b out W out b 2 W 2 b 1 W 1 ce cross_entropy P softmax + h 2 s + h 1 s + h1 = sigmoid W1 + b1) h2 = sigmoid W2 + b2) P = softmax Wout + bout) ce = cross_entropy (P, y) x y
30 CNTK Model b out W out b 2 W 2 ce cross_entropy P softmax + h 2 s + h 1 s Nodes: functions (primitives) Can be composed into reusable composites Edges: values Incl. tensors, sparse Automatic differentiation F / in = F / out out / in Deferred computation execution engine Editable, clonable b 1 W 1 + x y LEGO-like composability allows CNTK to support wide range of networks & applications
31 Authoring networks as functions model function features predictions defines the model structure & parameter initialization holds parameters that will be learned by training criterion function (features, labels) (training loss, additional metrics) defines training and evaluation criteria on top of the model function provides gradients w.r.t. training criteria b out W out b 2 W 2 b 1 W 1 ce cross_entropy P softmax + h 2 s + h 1 s + x y
32 Authoring networks as functions CNTK model: neural networks are functions pure functions with special powers : can compute a gradient w.r.t. any of its nodes external deity can update model parameters user specifies network as function objects: formula as a Python function (low level, e.g. LSTM) function composition of smaller sub-networks (layering) higher-order functions (equiv. of scan, fold, unfold) model parameters held by function objects compiled into the static execution graph under the hood
33 Layers lib: full list of layers/blocks layers/blocks.py: LSTM(), GRU(), RNNUnit() Stabilizer(), identity ForwardDeclaration(), Tensor[], SparseTensor[], Sequence[], SequenceOver[] layers/layers.py: Dense(), Embedding() Convolution(), Convolution1D(), Convolution2D(), Convolution3D(), Deconvolution() MaxPooling(), AveragePooling(), GlobalMaxPooling(), GlobalAveragePooling(), MaxUnpooling() BatchNormalization(), LayerNormalization() Dropout(), Activation() Label() layers/higher_order_layers.py: Sequential(), For(), operator >>, (function tuples) ResNetBlock(), SequentialClique() layers/sequence.py: Delay(), PastValueWindow() Recurrence(), RecurrenceFrom(), Fold(), UnfoldFrom() models/models.py: AttentionModel()
34 CNTK workflow Script configure and executes through CNTK Python APIs corpus reader minibatch source task-specific deserializer automatic randomization distributed reading network model function criterion function CPU/GPU execution engine packing, padding trainer SGD (momentum, Adam, ) minibatching model
35 As easy as from cntk import * # reader def create_reader(path, is_training):... # network def create_model_function():... def create_criterion_function(model):... # trainer (and evaluator) def train(reader, model):... def evaluate(reader, model):... # main function model = create_model_function() reader = create_reader(..., is_training=true) train(reader, model) reader = create_reader(..., is_training=false) evaluate(reader, model)
36 Workflow prepare data configure reader, network, learner (Python) train: mpiexec --np 16 --hosts server1,server2,server3,server4 \ python my_cntk_script.py
37 Prepare data: reader def create_reader(map_file, mean_file, is_training): # image preprocessing pipeline transforms = [ ImageDeserializer.crop(crop_type='Random', ratio=0.8, jitter_type='uniratio') ImageDeserializer.scale(width=image_width, height=image_height, channels=num_channels, interpolations='linear'), ImageDeserializer.mean(mean_file) ] # deserializer return MinibatchSource(ImageDeserializer(map_file, StreamDefs( features = StreamDef(field='image', transforms=transforms), ' labels = StreamDef(field='label', shape=num_classes) )), randomize=is_training, epoch_size = INFINITELY_REPEAT if is_training else FULL_DATA_SWEEP)
38 Prepare data: reader def create_reader(map_file, mean_file, is_training): # image preprocessing pipeline transforms = [ ImageDeserializer.crop(crop_type='Random', ratio=0.8, jitter_type='uniratio') ImageDeserializer.scale(width=image_width, height=image_height, channels=num_channels, interpolations='linear'), ImageDeserializer.mean(mean_file) ] # deserializer return MinibatchSource(ImageDeserializer(map_file, StreamDefs( features = StreamDef(field='image', transforms=transforms), ' labels = StreamDef(field='label', shape=num_classes) )), randomize=is_training, epoch_size = INFINITELY_REPEAT if is_training else FULL_DATA_SWEEP) automatic on-the-fly randomization important for large data sets readers compose, e.g. image text caption
39 Distributed training prepare data configure reader, network, learner (Python) train: --distributed! mpiexec --np 16 --hosts server1,server2,server3,server4 \ python my_cntk_script.py
40 Workflow prepare data configure reader, network, learner (Python) train: mpiexec --np 16 --hosts server1,server2,server3,server4 \ python my_cntk_script.py deploy offline (Python): apply model file-to-file your code: embed model through C++ API online: web service wrapper through C#/Java API
41
42 CNTK Unique Features Symbolic loops over sequences with dynamic scheduling Turn graph into parallel program through minibatching Unique parallel training algorithms (1-bit SGD, Block Momentum)
43 Symbolic Loops over Sequential Data extend our example to a recurrent network (RNN) h 1 (t) = s(w 1 x(t) + H 1 h 1 (t-1) + b 1 ) h1 = W1 + past_value(h1) + b1) h 2 (t) = s(w 2 h 1 (t) + H 2 h 2 (t-1) + b 2 ) h2 = W2 + H2 + b2) P(t) = softmax(w out h 2 (t) + b out ) P = Wout + bout) ce(t) = L T (t) log P(t) ce = cross_entropy(p, L) = max Scorpus ce(t) no explicit notion of time
44 Symbolic Loops over Sequential Data extend our example to a recurrent network (RNN) h 1 (t) = s(w 1 x(t) + H 1 h 1 (t-1) + b 1 ) h1 = W1 + past_value(h1) + b1) h 2 (t) = s(w 2 h 1 (t) + H 2 h 2 (t-1) + b 2 ) h2 = W2 + H2 + b2) P(t) = softmax(w out h 2 (t) + b out ) P = Wout + bout) ce(t) = L T (t) log P(t) ce = cross_entropy(p, L) = max Scorpus ce(t) no explicit notion of time
45 Symbolic Loops over Sequential Data extend our example to a recurrent network (RNN) h 1 (t) = s(w 1 x(t) + H 1 h 1 (t-1) + b 1 ) h1 = W1 + past_value(h1) + b1) h 2 (t) = s(w 2 h 1 (t) + H 2 h 2 (t-1) + b 2 ) h2 = W2 + H2 + b2) P(t) = softmax(w out h 2 (t) + b out ) P = Wout + bout) ce(t) = L T (t) log P(t) ce = cross_entropy(p, L) = max Scorpus ce(t) no explicit notion of time
46 Symbolic Loops over Sequential Data extend our example to a recurrent network (RNN) h 1 (t) = s(w 1 x(t) + H 1 h 1 (t-1) + b 1 ) h1 = W1 + H1 + b1) h 2 (t) = s(w 2 h 1 (t) + H 2 h 2 (t-1) + b 2 ) h2 = W2 + H2 + b2) P(t) = softmax(w out h 2 (t) + b out ) P = Wout + bout) ce(t) = L T (t) log P(t) ce = cross_entropy(p, L) = max Scorpus ce(t)
47 Symbolic Loops over Sequential Data b out W out b 2 W 2 b 1 W 1 ce cross_entropy P softmax + h 2 s + h 1 s + + z -1 + H 2 z -1 H 1 h1 = W1 + H1 + b1) h2 = W2 + H2 + b2) P = Wout + bout) ce = cross_entropy(p, L) CNTK automatically unrolls cycles deferred computation Efficient and composable x y
48 parallel sequences Batch-Scheduling of Variable-Length Sequences minibatches containing sequences of different lengths are automatically packed and padded time steps computed in parallel sequence 1 sequence 2 sequence 3 sequence 4 sequence 7 padding sequence 5 sequence 6 CNTK handles the special cases: past_value operation correctly resets state and gradient at sequence boundaries non-recurrent operations just pretend there is no padding ( garbage-in/garbage-out ) sequence reductions
49 parallel sequences Batch-Scheduling of Variable-Length Sequences minibatches containing sequences of different lengths are automatically packed and padded time steps computed in parallel sequence 1 sequence 2 sequence 3 sequence 4 sequence 7 padding sequence 5 sequence 6 CNTK handles the special cases: past_value operation correctly resets state and gradient at sequence boundaries non-recurrent operations just pretend there is no padding ( garbage-in/garbage-out ) sequence reductions
50 parallel sequences Batch-Scheduling of Variable-Length Sequences minibatches containing sequences of different lengths are automatically packed and padded time steps computed in parallel sequence 1 sequence 2 sequence 3 sequence 3 sequence 7 padding sequence 5 sequence 6 CNTK handles the special cases: past_value operation correctly resets state and gradient at sequence boundaries non-recurrent operations just pretend there is no padding ( garbage-in/garbage-out ) sequence reductions
51 parallel sequences Batch-Scheduling of Variable-Length Sequences minibatches containing sequences of different lengths are automatically packed and padded time steps computed in parallel sequence 1 sequence 2 sequence 3 sequence 4 sequence 7 padding sequence 5 sequence 6 CNTK handles the special cases: past_value operation correctly resets state and gradient at sequence boundaries non-recurrent operations just pretend there is no padding ( garbage-in/garbage-out ) sequence reductions
52 parallel sequences Batch-Scheduling of Variable-Length Sequences minibatches containing sequences of different lengths are automatically packed and padded time steps computed in parallel sequence 1 sequence 2 sequence 3 sequence 4 sequence 7 padding sequence 5 sequence 6 CNTK handles the special cases: past_value operation correctly resets state and gradient at sequence boundaries non-recurrent operations just pretend there is no padding ( garbage-in/garbage-out ) sequence reductions
53 parallel sequences Batch-Scheduling of Variable-Length Sequences minibatches containing sequences of different lengths are automatically packed and padded time steps computed in parallel sequence 1 sequence 2 sequence 3 sequence 4 sequence 7 padding sequence 5 sequence 6 CNTK handles the special cases: past_value operation correctly resets state and gradient at sequence boundaries non-recurrent operations just pretend there is no padding ( garbage-in/garbage-out ) sequence reductions
54 parallel sequences Batch-Scheduling of Variable-Length Sequences minibatches containing sequences of different lengths are automatically packed and padded time steps computed in parallel sequence 1 sequence 2 sequence 3 sequence 4 sequence 7 padding sequence 5 sequence 6 CNTK handles the special cases: past_value operation correctly resets state and gradient at sequence boundaries non-recurrent operations just pretend there is no padding ( garbage-in/garbage-out ) sequence reductions
55 parallel sequences Batch-Scheduling of Variable-Length Sequences minibatches containing sequences of different lengths are automatically packed and padded time steps computed in parallel sequence 1 sequence 2 sequence 3 sequence 4 sequence 7 padding sequence 5 sequence 6 CNTK handles the special cases: past_value operation correctly resets state and gradient at sequence boundaries non-recurrent operations just pretend there is no padding ( garbage-in/garbage-out ) sequence reductions
56 parallel sequences Batch-Scheduling of Variable-Length Sequences minibatches containing sequences of different lengths are automatically packed and padded time steps computed in parallel sequence 1 sequence 2 sequence 3 sequence 4 sequence 7 padding speed-up is automatic: sequence 5 sequence 6 Speed comparison on RNNs Optimized Naïve Naïve, Single Sequence, 1 Optimized, multi sequence >
57 Data-Parallel Training Data-parallelism: distribute minibatch over workers, all-reduce partial gradients node 1 node 2 node 3 S all-reduce
58 Data-parallel training Data-parallelism: distribute minibatch over workers, all-reduce partial gradients node 1 node 2 node 3 ring algorithm O(2 (K-1)/K M) O(1) w.r.t. K
59 Data-parallel training how to reduce communication cost: communicate less each time 1-bit SGD: [F. Seide, H. Fu, J. Droppo, G. Li, D. Yu: 1-Bit Stochastic Gradient Descent... Distributed Training of Speech DNNs, Interspeech 2014] quantize gradients to 1 bit per value trick: carry over quantization error to next minibatch 1-bit quantized with residual minibatch GPU 1 GPU 2 GPU 3 1-bit quantized with residual
60 Data-Parallel Training How to reduce communication cost: communicate less each time 1-bit SGD: [F. Seide, H. Fu, J. Droppo, G. Li, D. Yu: 1-Bit Stochastic Gradient Descent...Distributed Training of Speech DNNs, Interspeech 2014] quantize gradients to 1 bit per value trick: carry over quantization error to next minibatch communicate less often Automatic MB sizing [F. Seide, H. Fu, J. Droppo, G. Li, D. Yu: ON Parallelizability of Stochastic Gradient Descent..., ICASSP 2014] Block momentum [K. Chen, Q. Huo: Scalable training of deep learning machines by incremental block training, ICASSP 2016] Very recent, very effective parallelization method Combines model averaging with error-residual idea
61 Benchmark Result of Parallel Training on CNTK Training data: 2,670-hour speech from real traffics of VS, SMD, and Cortana About 16 and 20 days to train DNN and LSTM on 1-GPU, respectively 1bit/BMUF Speedup Factors in LSTM Training bit-average 1bit-peak BMUF-average BMUF-peak GPUs 8 GPUs 16 GPUs 32 GPUs 64 GPUs Credit: Yongqiang Wang, Kai Chen, Qiang Huo
62 Results Achievement Almost linear speedup without degradation of model quality Verified for training DNN, CNN, LSTM up to 64 GPUs for speech recognition, image classification, OCR, and click prediction tasks Released in CNTK as a critical differentiator Used for enterprise scale production data loads Production tools in other companies such as iflytek and Alibaba
63 Where to begin? On GitHub: Tutorials: (latest release) (latest) Azure Notebooks: Try for free pre-hosted Seek help on Stack Overflow: (please add cntk tag) Seek help on Stack Overflow: (please add cntk tag)
64 Where to begin? Tutorials: (latest release) (latest)
65 Where to begin? Azure Notebooks: Try for free pre-hosted
66
67 Where to begin? On GitHub: Tutorials: (latest release) (latest) Azure Notebooks: Try for free pre-hosted Seek help on Stack Overflow: (please add cntk tag) Seek help on Stack Overflow: (please add cntk tag)
Sayan Pathak Principal ML Scientist. Chris Basoglu Partner Dev Manager
Sayan Pathak Principal ML Scientist Chris Basoglu Partner Dev Manager With many contributors: A. Agarwal, E. Akchurin, E. Barsoum, C. Basoglu, G. Chen, S. Cyphers, W. Darling, J. Droppo, K. Deng, A. Eversole,
More informationWith many contributors: A. Agarwal, E. Akchurin, C. Basoglu, G. Chen, S. Cyphers, W. Darling, J. Droppo, A. Eversole, B. Guenter, P. He, M.
With many contributors: A. Agarwal, E. Akchurin, C. Basoglu, G. Chen, S. Cyphers, W. Darling, J. Droppo, A. Eversole, B. Guenter, P. He, M. Hillebrand, X. Huang, Z. Huang, R. Hoens, V. Ivanov, A. Kamenev,
More informationS6843 Deep Learning in Microsoft with CNTK
S6843 Deep Learning in Microsoft with CNTK Alexey Kamenev Microsoft Research Deep Learning in the company Bing Cortana Ads Relevance Multimedia Skype HoloLens Research Speech, image, text 2 2015 System
More informationEmad Barsoum, Prin. Software Dev. Engineer Sayan Pathak, Prin. ML Scientist Cha Zhang, Prin. Researcher. With 140+ contributors
Emad Barsoum, Prin. Software Dev. Engineer Sayan Pathak, Prin. ML Scientist Cha Zhang, Prin. Researcher With 140+ contributors Agenda Introduction (30 min) What is toolkit Why use Basic operations (25
More informationDeep Learning Explained Module 4: Convolution Neural Networks (CNN or Conv Nets)
Deep Learning Explained Module 4: Convolution Neural Networks (CNN or Conv Nets) Sayan D. Pathak, Ph.D., Principal ML Scientist, Microsoft Roland Fernandez, Senior Researcher, Microsoft Module Outline
More informationTutorial on Keras CAP ADVANCED COMPUTER VISION SPRING 2018 KISHAN S ATHREY
Tutorial on Keras CAP 6412 - ADVANCED COMPUTER VISION SPRING 2018 KISHAN S ATHREY Deep learning packages TensorFlow Google PyTorch Facebook AI research Keras Francois Chollet (now at Google) Chainer Company
More informationNVIDIA GPU CLOUD DEEP LEARNING FRAMEWORKS
TECHNICAL OVERVIEW NVIDIA GPU CLOUD DEEP LEARNING FRAMEWORKS A Guide to the Optimized Framework Containers on NVIDIA GPU Cloud Introduction Artificial intelligence is helping to solve some of the most
More informationKeras: Handwritten Digit Recognition using MNIST Dataset
Keras: Handwritten Digit Recognition using MNIST Dataset IIT PATNA January 31, 2018 1 / 30 OUTLINE 1 Keras: Introduction 2 Installing Keras 3 Keras: Building, Testing, Improving A Simple Network 2 / 30
More informationCafeGPI. Single-Sided Communication for Scalable Deep Learning
CafeGPI Single-Sided Communication for Scalable Deep Learning Janis Keuper itwm.fraunhofer.de/ml Competence Center High Performance Computing Fraunhofer ITWM, Kaiserslautern, Germany Deep Neural Networks
More informationDEEP NEURAL NETWORKS AND GPUS. Julie Bernauer
DEEP NEURAL NETWORKS AND GPUS Julie Bernauer GPU Computing GPU Computing Run Computations on GPUs x86 CUDA Framework to Program NVIDIA GPUs A simple sum of two vectors (arrays) in C void vector_add(int
More informationA Quick Guide on Training a neural network using Keras.
A Quick Guide on Training a neural network using Keras. TensorFlow and Keras Keras Open source High level, less flexible Easy to learn Perfect for quick implementations Starts by François Chollet from
More informationVinnie Saini Cloud Solution Architect Big Data & AI
Vinnie Saini Cloud Solution Architect Big Data & AI vasaini@microsoft.com data intelligence cloud Data + Intelligence + Cloud Extensible Applications Easy to consume Artificial Intelligence Most comprehensive
More informationEFFICIENT INFERENCE WITH TENSORRT. Han Vanholder
EFFICIENT INFERENCE WITH TENSORRT Han Vanholder AI INFERENCING IS EXPLODING 2 Trillion Messages Per Day On LinkedIn 500M Daily active users of iflytek 140 Billion Words Per Day Translated by Google 60
More informationMIXED PRECISION TRAINING OF NEURAL NETWORKS. Carl Case, Senior Architect, NVIDIA
MIXED PRECISION TRAINING OF NEURAL NETWORKS Carl Case, Senior Architect, NVIDIA OUTLINE 1. What is mixed precision training with FP16? 2. Considerations and methodology for mixed precision training 3.
More informationReview: The best frameworks for machine learning and deep learning
Review: The best frameworks for machine learning and deep learning infoworld.com/article/3163525/analytics/review-the-best-frameworks-for-machine-learning-and-deep-learning.html By Martin Heller Over the
More informationMoonRiver: Deep Neural Network in C++
MoonRiver: Deep Neural Network in C++ Chung-Yi Weng Computer Science & Engineering University of Washington chungyi@cs.washington.edu Abstract Artificial intelligence resurges with its dramatic improvement
More informationMIXED PRECISION TRAINING: THEORY AND PRACTICE Paulius Micikevicius
MIXED PRECISION TRAINING: THEORY AND PRACTICE Paulius Micikevicius What is Mixed Precision Training? Reduced precision tensor math with FP32 accumulation, FP16 storage Successfully used to train a variety
More informationAdvanced Video Analysis & Imaging
Advanced Video Analysis & Imaging (5LSH0), Module 09B Machine Learning with Convolutional Neural Networks (CNNs) - Workout Farhad G. Zanjani, Clint Sebastian, Egor Bondarev, Peter H.N. de With ( p.h.n.de.with@tue.nl
More informationInference Optimization Using TensorRT with Use Cases. Jack Han / 한재근 Solutions Architect NVIDIA
Inference Optimization Using TensorRT with Use Cases Jack Han / 한재근 Solutions Architect NVIDIA Search Image NLP Maps TensorRT 4 Adoption Use Cases Speech Video AI Inference is exploding 1 Billion Videos
More informationConvolutional Neural Networks
NPFL114, Lecture 4 Convolutional Neural Networks Milan Straka March 25, 2019 Charles University in Prague Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics unless otherwise
More informationXilinx ML Suite Overview
Xilinx ML Suite Overview Yao Fu System Architect Data Center Acceleration Xilinx Accelerated Computing Workloads Machine Learning Inference Image classification and object detection Video Streaming Frame
More informationCOMP9444 Neural Networks and Deep Learning 7. Image Processing. COMP9444 c Alan Blair, 2017
COMP9444 Neural Networks and Deep Learning 7. Image Processing COMP9444 17s2 Image Processing 1 Outline Image Datasets and Tasks Convolution in Detail AlexNet Weight Initialization Batch Normalization
More informationHPE Deep Learning Cookbook: Recipes to Run Deep Learning Workloads. Natalia Vassilieva, Sergey Serebryakov
HPE Deep Learning Cookbook: Recipes to Run Deep Learning Workloads Natalia Vassilieva, Sergey Serebryakov Deep learning ecosystem today Software Hardware 2 HPE s portfolio for deep learning Government,
More informationRNN LSTM and Deep Learning Libraries
RNN LSTM and Deep Learning Libraries UDRC Summer School Muhammad Awais m.a.rana@surrey.ac.uk Outline Recurrent Neural Network Application of RNN LSTM Caffe Torch Theano TensorFlow Flexibility of Recurrent
More informationA performance comparison of Deep Learning frameworks on KNL
A performance comparison of Deep Learning frameworks on KNL R. Zanella, G. Fiameni, M. Rorro Middleware, Data Management - SCAI - CINECA IXPUG Bologna, March 5, 2018 Table of Contents 1. Problem description
More informationKeras: Handwritten Digit Recognition using MNIST Dataset
Keras: Handwritten Digit Recognition using MNIST Dataset IIT PATNA February 9, 2017 1 / 24 OUTLINE 1 Introduction Keras: Deep Learning library for Theano and TensorFlow 2 Installing Keras Installation
More informationSEMANTIC COMPUTING. Lecture 8: Introduction to Deep Learning. TU Dresden, 7 December Dagmar Gromann International Center For Computational Logic
SEMANTIC COMPUTING Lecture 8: Introduction to Deep Learning Dagmar Gromann International Center For Computational Logic TU Dresden, 7 December 2018 Overview Introduction Deep Learning General Neural Networks
More informationINTRODUCTION TO DEEP LEARNING
INTRODUCTION TO DEEP LEARNING CONTENTS Introduction to deep learning Contents 1. Examples 2. Machine learning 3. Neural networks 4. Deep learning 5. Convolutional neural networks 6. Conclusion 7. Additional
More informationFrameworks in Python for Numeric Computation / ML
Frameworks in Python for Numeric Computation / ML Why use a framework? Why not use the built-in data structures? Why not write our own matrix multiplication function? Frameworks are needed not only because
More informationFei-Fei Li & Justin Johnson & Serena Yeung
Lecture 9-1 Administrative A2 due Wed May 2 Midterm: In-class Tue May 8. Covers material through Lecture 10 (Thu May 3). Sample midterm released on piazza. Midterm review session: Fri May 4 discussion
More informationUnified Deep Learning with CPU, GPU, and FPGA Technologies
Unified Deep Learning with CPU, GPU, and FPGA Technologies Allen Rush 1, Ashish Sirasao 2, Mike Ignatowski 1 1: Advanced Micro Devices, Inc., 2: Xilinx, Inc. Abstract Deep learning and complex machine
More informationCode Mania Artificial Intelligence: a. Module - 1: Introduction to Artificial intelligence and Python:
Code Mania 2019 Artificial Intelligence: a. Module - 1: Introduction to Artificial intelligence and Python: 1. Introduction to Artificial Intelligence 2. Introduction to python programming and Environment
More informationIndex. Umberto Michelucci 2018 U. Michelucci, Applied Deep Learning,
A Acquisition function, 298, 301 Adam optimizer, 175 178 Anaconda navigator conda command, 3 Create button, 5 download and install, 1 installing packages, 8 Jupyter Notebook, 11 13 left navigation pane,
More informationDeep Learning and Its Applications
Convolutional Neural Network and Its Application in Image Recognition Oct 28, 2016 Outline 1 A Motivating Example 2 The Convolutional Neural Network (CNN) Model 3 Training the CNN Model 4 Issues and Recent
More informationNVIDIA FOR DEEP LEARNING. Bill Veenhuis
NVIDIA FOR DEEP LEARNING Bill Veenhuis bveenhuis@nvidia.com Nvidia is the world s leading ai platform ONE ARCHITECTURE CUDA 2 GPU: Perfect Companion for Accelerating Apps & A.I. CPU GPU 3 Intro to AI AGENDA
More informationDeep Learning with Tensorflow AlexNet
Machine Learning and Computer Vision Group Deep Learning with Tensorflow http://cvml.ist.ac.at/courses/dlwt_w17/ AlexNet Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton, "Imagenet classification
More informationInception and Residual Networks. Hantao Zhang. Deep Learning with Python.
Inception and Residual Networks Hantao Zhang Deep Learning with Python https://en.wikipedia.org/wiki/residual_neural_network Deep Neural Network Progress from Large Scale Visual Recognition Challenge (ILSVRC)
More informationNVIDIA DLI HANDS-ON TRAINING COURSE CATALOG
NVIDIA DLI HANDS-ON TRAINING COURSE CATALOG Valid Through July 31, 2018 INTRODUCTION The NVIDIA Deep Learning Institute (DLI) trains developers, data scientists, and researchers on how to use artificial
More informationConvolutional Neural Networks. Computer Vision Jia-Bin Huang, Virginia Tech
Convolutional Neural Networks Computer Vision Jia-Bin Huang, Virginia Tech Today s class Overview Convolutional Neural Network (CNN) Training CNN Understanding and Visualizing CNN Image Categorization:
More informationMachine Learning With Python. Bin Chen Nov. 7, 2017 Research Computing Center
Machine Learning With Python Bin Chen Nov. 7, 2017 Research Computing Center Outline Introduction to Machine Learning (ML) Introduction to Neural Network (NN) Introduction to Deep Learning NN Introduction
More informationTutorial on Machine Learning Tools
Tutorial on Machine Learning Tools Yanbing Xue Milos Hauskrecht Why do we need these tools? Widely deployed classical models No need to code from scratch Easy-to-use GUI Outline Matlab Apps Weka 3 UI TensorFlow
More informationAll You Want To Know About CNNs. Yukun Zhu
All You Want To Know About CNNs Yukun Zhu Deep Learning Deep Learning Image from http://imgur.com/ Deep Learning Image from http://imgur.com/ Deep Learning Image from http://imgur.com/ Deep Learning Image
More informationSequence Modeling: Recurrent and Recursive Nets. By Pyry Takala 14 Oct 2015
Sequence Modeling: Recurrent and Recursive Nets By Pyry Takala 14 Oct 2015 Agenda Why Recurrent neural networks? Anatomy and basic training of an RNN (10.2, 10.2.1) Properties of RNNs (10.2.2, 8.2.6) Using
More informationCharacterization and Benchmarking of Deep Learning. Natalia Vassilieva, PhD Sr. Research Manager
Characterization and Benchmarking of Deep Learning Natalia Vassilieva, PhD Sr. Research Manager Deep learning applications Vision Speech Text Other Search & information extraction Security/Video surveillance
More informationNeural Network Exchange Format
Copyright Khronos Group 2017 - Page 1 Neural Network Exchange Format Deploying Trained Networks to Inference Engines Viktor Gyenes, specification editor Copyright Khronos Group 2017 - Page 2 Outlook The
More informationDeep Learning Applications
October 20, 2017 Overview Supervised Learning Feedforward neural network Convolution neural network Recurrent neural network Recursive neural network (Recursive neural tensor network) Unsupervised Learning
More informationMocha.jl. Deep Learning in Julia. Chiyuan Zhang CSAIL, MIT
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:
More informationPOINT CLOUD DEEP LEARNING
POINT CLOUD DEEP LEARNING Innfarn Yoo, 3/29/28 / 57 Introduction AGENDA Previous Work Method Result Conclusion 2 / 57 INTRODUCTION 3 / 57 2D OBJECT CLASSIFICATION Deep Learning for 2D Object Classification
More informationCSC 578 Neural Networks and Deep Learning
CSC 578 Neural Networks and Deep Learning Fall 2018/19 7. Recurrent Neural Networks (Some figures adapted from NNDL book) 1 Recurrent Neural Networks 1. Recurrent Neural Networks (RNNs) 2. RNN Training
More informationDemocratizing Machine Learning on Kubernetes
Democratizing Machine Learning on Kubernetes Joy Qiao, Senior Solution Architect - AI and Research Group, Microsoft Lachlan Evenson - Principal Program Manager AKS/ACS, Microsoft Who are we? The Data Scientist
More informationObject Detection Lecture Introduction to deep learning (CNN) Idar Dyrdal
Object Detection Lecture 10.3 - Introduction to deep learning (CNN) Idar Dyrdal Deep Learning Labels Computational models composed of multiple processing layers (non-linear transformations) Used to learn
More informationFuzzy Set Theory in Computer Vision: Example 3
Fuzzy Set Theory in Computer Vision: Example 3 Derek T. Anderson and James M. Keller FUZZ-IEEE, July 2017 Overview Purpose of these slides are to make you aware of a few of the different CNN architectures
More informationIn-Place Activated BatchNorm for Memory- Optimized Training of DNNs
In-Place Activated BatchNorm for Memory- Optimized Training of DNNs Samuel Rota Bulò, Lorenzo Porzi, Peter Kontschieder Mapillary Research Paper: https://arxiv.org/abs/1712.02616 Code: https://github.com/mapillary/inplace_abn
More informationIndex. Springer Nature Switzerland AG 2019 B. Moons et al., Embedded Deep Learning,
Index A Algorithmic noise tolerance (ANT), 93 94 Application specific instruction set processors (ASIPs), 115 116 Approximate computing application level, 95 circuits-levels, 93 94 DAS and DVAS, 107 110
More informationDeep Learning for Computer Vision II
IIIT Hyderabad Deep Learning for Computer Vision II C. V. Jawahar Paradigm Shift Feature Extraction (SIFT, HoG, ) Part Models / Encoding Classifier Sparrow Feature Learning Classifier Sparrow L 1 L 2 L
More informationAn Introduction to Deep Learning with RapidMiner. Philipp Schlunder - RapidMiner Research
An Introduction to Deep Learning with RapidMiner Philipp Schlunder - RapidMiner Research What s in store for today?. Things to know before getting started 2. What s Deep Learning anyway? 3. How to use
More informationEnd-to-End Training of Acoustic Models for Large Vocabulary Continuous Speech Recognition with TensorFlow
End-to-End Training of Acoustic Models for Large Vocabulary Continuous Speech Recognition with TensorFlow Ehsan Variani, Tom Bagby, Erik McDermott, Michiel Bacchiani Google Inc, Mountain View, CA, USA
More informationLSTM and its variants for visual recognition. Xiaodan Liang Sun Yat-sen University
LSTM and its variants for visual recognition Xiaodan Liang xdliang328@gmail.com Sun Yat-sen University Outline Context Modelling with CNN LSTM and its Variants LSTM Architecture Variants Application in
More informationDeep Learning Benchmarks Mumtaz Vauhkonen, Quaizar Vohra, Saurabh Madaan Collaboration with Adam Coates, Stanford Unviersity
Deep Learning Benchmarks Mumtaz Vauhkonen, Quaizar Vohra, Saurabh Madaan Collaboration with Adam Coates, Stanford Unviersity Abstract: This project aims at creating a benchmark for Deep Learning (DL) algorithms
More informationCS 2750: Machine Learning. Neural Networks. Prof. Adriana Kovashka University of Pittsburgh April 13, 2016
CS 2750: Machine Learning Neural Networks Prof. Adriana Kovashka University of Pittsburgh April 13, 2016 Plan for today Neural network definition and examples Training neural networks (backprop) Convolutional
More informationEncoding RNNs, 48 End of sentence (EOS) token, 207 Exploding gradient, 131 Exponential function, 42 Exponential Linear Unit (ELU), 44
A Activation potential, 40 Annotated corpus add padding, 162 check versions, 158 create checkpoints, 164, 166 create input, 160 create train and validation datasets, 163 dropout, 163 DRUG-AE.rel file,
More informationCNN optimization. Rassadin A
CNN optimization Rassadin A. 01.2017-02.2017 What to optimize? Training stage time consumption (CPU / GPU) Inference stage time consumption (CPU / GPU) Training stage memory consumption Inference stage
More informationMachine Learning. Deep Learning. Eric Xing (and Pengtao Xie) , Fall Lecture 8, October 6, Eric CMU,
Machine Learning 10-701, Fall 2015 Deep Learning Eric Xing (and Pengtao Xie) Lecture 8, October 6, 2015 Eric Xing @ CMU, 2015 1 A perennial challenge in computer vision: feature engineering SIFT Spin image
More informationDeep Learning. Volker Tresp Summer 2017
Deep Learning Volker Tresp Summer 2017 1 Neural Network Winter and Revival While Machine Learning was flourishing, there was a Neural Network winter (late 1990 s until late 2000 s) Around 2010 there
More informationDistributed Training of Deep Neural Networks: Theoretical and Practical Limits of Parallel Scalability
Distributed Training of Deep Neural Networks: Theoretical and Practical Limits of Parallel Scalability Janis Keuper Itwm.fraunhofer.de/ml Competence Center High Performance Computing Fraunhofer ITWM, Kaiserslautern,
More informationNeural Network Neurons
Neural Networks Neural Network Neurons 1 Receives n inputs (plus a bias term) Multiplies each input by its weight Applies activation function to the sum of results Outputs result Activation Functions Given
More informationNVIDIA DEEP LEARNING INSTITUTE
NVIDIA DEEP LEARNING INSTITUTE TRAINING CATALOG Valid Through July 31, 2018 INTRODUCTION The NVIDIA Deep Learning Institute (DLI) trains developers, data scientists, and researchers on how to use artificial
More informationComo funciona o Deep Learning
Como funciona o Deep Learning Moacir Ponti (com ajuda de Gabriel Paranhos da Costa) ICMC, Universidade de São Paulo Contact: www.icmc.usp.br/~moacir moacir@icmc.usp.br Uberlandia-MG/Brazil October, 2017
More informationMachine Learning 13. week
Machine Learning 13. week Deep Learning Convolutional Neural Network Recurrent Neural Network 1 Why Deep Learning is so Popular? 1. Increase in the amount of data Thanks to the Internet, huge amount of
More informationXuedong Huang Chief Speech Scientist & Distinguished Engineer Microsoft Corporation
Xuedong Huang Chief Speech Scientist & Distinguished Engineer Microsoft Corporation xdh@microsoft.com Cloud-enabled multimodal NUI with speech, gesture, gaze http://cacm.acm.org/magazines/2014/1/170863-ahistorical-perspective-of-speech-recognition
More informationIBM Deep Learning Solutions
IBM Deep Learning Solutions Reference Architecture for Deep Learning on POWER8, P100, and NVLink October, 2016 How do you teach a computer to Perceive? 2 Deep Learning: teaching Siri to recognize a bicycle
More informationGPU FOR DEEP LEARNING. 周国峰 Wuhan University 2017/10/13
GPU FOR DEEP LEARNING chandlerz@nvidia.com 周国峰 Wuhan University 2017/10/13 Why Deep Learning Boost Today? Nvidia SDK for Deep Learning? Agenda CUDA 8.0 cudnn TensorRT (GIE) NCCL DIGITS 2 Why Deep Learning
More informationDefense Data Generation in Distributed Deep Learning System Se-Yoon Oh / ADD-IDAR
Defense Data Generation in Distributed Deep Learning System Se-Yoon Oh / 2017. 10. 31 syoh@add.re.kr Page 1/36 Overview 1. Introduction 2. Data Generation Synthesis 3. Distributed Deep Learning 4. Conclusions
More informationUsing CNN Across Intel Architecture
white paper Artificial Intelligence Object Classification Intel AI Builders Object Classification Using CNN Across Intel Architecture Table of Contents Abstract...1 1. Introduction...1 2. Setting up a
More informationECE 5470 Classification, Machine Learning, and Neural Network Review
ECE 5470 Classification, Machine Learning, and Neural Network Review Due December 1. Solution set Instructions: These questions are to be answered on this document which should be submitted to blackboard
More informationA Survey on Deep Learning Methods for Robot Vision
A Survey on Deep Learning Methods for Robot Vision Javier Ruiz-del-Solar, Patricio Loncomilla, Naiomi Soto Advanced Mining Technology Center & Dept. of Electrical Engineering Universidad de Chile, Chile
More informationTowards Scalable Machine Learning
Towards Scalable Machine Learning Janis Keuper itwm.fraunhofer.de/ml Competence Center High Performance Computing Fraunhofer ITWM, Kaiserslautern, Germany Fraunhofer Center Machnine Larning Outline I Introduction
More informationIntroduction to Deep Learning in Signal Processing & Communications with MATLAB
Introduction to Deep Learning in Signal Processing & Communications with MATLAB Dr. Amod Anandkumar Pallavi Kar Application Engineering Group, Mathworks India 2019 The MathWorks, Inc. 1 Different Types
More informationConvolutional Neural Networks: Applications and a short timeline. 7th Deep Learning Meetup Kornel Kis Vienna,
Convolutional Neural Networks: Applications and a short timeline 7th Deep Learning Meetup Kornel Kis Vienna, 1.12.2016. Introduction Currently a master student Master thesis at BME SmartLab Started deep
More informationLecture 20: Neural Networks for NLP. Zubin Pahuja
Lecture 20: Neural Networks for NLP Zubin Pahuja zpahuja2@illinois.edu courses.engr.illinois.edu/cs447 CS447: Natural Language Processing 1 Today s Lecture Feed-forward neural networks as classifiers simple
More informationTutorial on Deep Learning with Theano and Lasagne. Jan Schlüter Sander Dieleman EMBL-EBI
Tutorial on Deep Learning with Theano and Lasagne Jan Schlüter Sander Dieleman EMBL-EBI 2016-04-21 Tutorial Outline Foundations What are Artificial Neural Networks? Practical part: Theano and Lasagne Learning
More informationDeep Neural Network Hyperparameter Optimization with Genetic Algorithms
Deep Neural Network Hyperparameter Optimization with Genetic Algorithms EvoDevo A Genetic Algorithm Framework Aaron Vose, Jacob Balma, Geert Wenes, and Rangan Sukumar Cray Inc. October 2017 Presenter Vose,
More informationCENG 783. Special topics in. Deep Learning. AlchemyAPI. Week 11. Sinan Kalkan
CENG 783 Special topics in Deep Learning AlchemyAPI Week 11 Sinan Kalkan TRAINING A CNN Fig: http://www.robots.ox.ac.uk/~vgg/practicals/cnn/ Feed-forward pass Note that this is written in terms of the
More informationMulti-dimensional Parallel Training of Winograd Layer on Memory-Centric Architecture
The 51st Annual IEEE/ACM International Symposium on Microarchitecture Multi-dimensional Parallel Training of Winograd Layer on Memory-Centric Architecture Byungchul Hong Yeonju Ro John Kim FuriosaAI Samsung
More informationSnapdragon NPE Overview
March 2018 Linaro Connect Hong Kong Snapdragon NPE Overview Mark Charlebois Director, Engineering Qualcomm Technologies, Inc. Caffe2 Snapdragon Neural Processing Engine Efficient execution on Snapdragon
More informationTENSORRT. RN _v01 January Release Notes
TENSORRT RN-08624-030_v01 January 2018 Release Notes TABLE OF CONTENTS Chapter Chapter Chapter Chapter 1. 2. 3. 4. Overview...1 Release 3.0.2... 2 Release 3.0.1... 4 Release 2.1... 10 RN-08624-030_v01
More informationReal Time Monitoring of CCTV Camera Images Using Object Detectors and Scene Classification for Retail and Surveillance Applications
Real Time Monitoring of CCTV Camera Images Using Object Detectors and Scene Classification for Retail and Surveillance Applications Anand Joshi CS229-Machine Learning, Computer Science, Stanford University,
More informationToward Scalable Deep Learning
한국정보과학회 인공지능소사이어티 머신러닝연구회 두번째딥러닝워크샵 2015.10.16 Toward Scalable Deep Learning 윤성로 Electrical and Computer Engineering Seoul National University http://data.snu.ac.kr Breakthrough: Big Data + Machine Learning
More informationCNN Basics. Chongruo Wu
CNN Basics Chongruo Wu Overview 1. 2. 3. Forward: compute the output of each layer Back propagation: compute gradient Updating: update the parameters with computed gradient Agenda 1. Forward Conv, Fully
More informationResearch Faculty Summit Systems Fueling future disruptions
Research Faculty Summit 2018 Systems Fueling future disruptions Wolong: A Back-end Optimizer for Deep Learning Computation Jilong Xue Researcher, Microsoft Research Asia System Challenge in Deep Learning
More informationLayer-wise Performance Bottleneck Analysis of Deep Neural Networks
Layer-wise Performance Bottleneck Analysis of Deep Neural Networks Hengyu Zhao, Colin Weinshenker*, Mohamed Ibrahim*, Adwait Jog*, Jishen Zhao University of California, Santa Cruz, *The College of William
More informationTensorFlow: A System for Learning-Scale Machine Learning. Google Brain
TensorFlow: A System for Learning-Scale Machine Learning Google Brain The Problem Machine learning is everywhere This is in large part due to: 1. Invention of more sophisticated machine learning models
More informationDeep Learning. Deep Learning provided breakthrough results in speech recognition and image classification. Why?
Data Mining Deep Learning Deep Learning provided breakthrough results in speech recognition and image classification. Why? Because Speech recognition and image classification are two basic examples of
More informationLecture 7: Neural network acoustic models in speech recognition
CS 224S / LINGUIST 285 Spoken Language Processing Andrew Maas Stanford University Spring 2017 Lecture 7: Neural network acoustic models in speech recognition Outline Hybrid acoustic modeling overview Basic
More informationConvolutional Sequence to Sequence Learning. Denis Yarats with Jonas Gehring, Michael Auli, David Grangier, Yann Dauphin Facebook AI Research
Convolutional Sequence to Sequence Learning Denis Yarats with Jonas Gehring, Michael Auli, David Grangier, Yann Dauphin Facebook AI Research Sequence generation Need to model a conditional distribution
More informationPractical Deep Learning
Practical Deep Learning micha.codes / fastforwardlabs.com 1 / 70 deep learning can seem mysterious 2 / 70 let's nd a way to just build a function 3 / 70 Feed Forward Layer # X.shape == (512,) # output.shape
More informationDeep Learning Basic Lecture - Complex Systems & Artificial Intelligence 2017/18 (VO) Asan Agibetov, PhD.
Deep Learning 861.061 Basic Lecture - Complex Systems & Artificial Intelligence 2017/18 (VO) Asan Agibetov, PhD asan.agibetov@meduniwien.ac.at Medical University of Vienna Center for Medical Statistics,
More informationBidirectional Recurrent Convolutional Networks for Video Super-Resolution
Bidirectional Recurrent Convolutional Networks for Video Super-Resolution Qi Zhang & Yan Huang Center for Research on Intelligent Perception and Computing (CRIPAC) National Laboratory of Pattern Recognition
More informationBHNN: a Memory-Efficient Accelerator for Compressing Deep Neural Network with Blocked Hashing Techniques
BHNN: a Memory-Efficient Accelerator for Compressing Deep Neural Network with Blocked Hashing Techniques Jingyang Zhu 1, Zhiliang Qian 2*, and Chi-Ying Tsui 1 1 The Hong Kong University of Science and
More informationA Torch Library for Action Recognition and Detection Using CNNs and LSTMs
A Torch Library for Action Recognition and Detection Using CNNs and LSTMs Gary Thung and Helen Jiang Stanford University {gthung, helennn}@stanford.edu Abstract It is very common now to see deep neural
More information