SlideShare a Scribd company logo
1 of 34
BACKGROUND • Now a day’s advances have to made to recognize
the symbols that were once meaningful and
understandable only by humans. It is very easy for
humans to understand images, but the same
image is very difficult for computer to comprehend.
Driverless cars read symbols which were once
difficult to understand by computers.
• Experiments results on benchmark database of
MNIST handwritten digit images show that the
performance of our algorithm is remarkable and
demonstrate its superiority over several existing
algorithms.
OBJECTIVE • In the current age of digitization, handwriting
recognition plays an important role in information
processing
• The main objective of the project is to solve the
problem where the computer needs to recognize
the digits in real time.
• With the power of parallel computing, the intention
of the project is to solve the real-world problem of
recognizing digits through 28000 images which
may appear everywhere in our day to day life.
GPU
SPECIFICATION
• Model: Tesla V100-SXM2
• GPU count: 0-4
• GPU Memory: 32510 MB/GPU
CPU
INFORMATION
• Model: Intel(R) Xeon(R) Silver 4114 CPU @
2.20GHz
• Sockets: 2
• Cores/Sockets: 10
• Thread/Core: 2
• CPUs: 40
COMMAND FOR
ENTERING
RESERVATION:
• srun -p reservation --reservation=csye7105-
gpu --gres=gpu:4 --mem=2Gb --export=ALL --
pty /bin/bash
• Command for getting GPU information: nvidia-
smi
• Command for getting CPU information: lscpu
DATASET
SPECIFICATIONS
• Each image is 28 pixels in height and 28 pixels in
width, for a total of 784 pixels in total. Each pixel
has a single pixel-value associated with it,
indicating the lightness or darkness of that pixel,
with higher numbers meaning darker. This pixel-
value is an integer between 0 and 255, inclusive.
• The training data set, (train.csv), has 785 columns.
The first column, called "label", is the digit that was
drawn by the user. The rest of the columns contain
the pixel-values of the associated image
DATA INFORMATION
Data Size – 167 MB Number of columns in
training set – 785
Each image size – 28
pixel(height) * 28
pixel(width) – 784 pixel
total
DATA
PREPROCESSI
NG
• The following steps where performed for data pre-
processing
• Data was normalized
• Random rotation
• Random Shift
DATA PREPROCESSING
WORKING
WITH GPU
• Pytorch has the package that supports for CUDA
tensor types, that implement the same function as
CPU tensors, but they utilize GPUs for
computation.
• PyTorch is an optimized tensor library for deep
learning using GPUs and CPUs.
• Entire Project was supported by the discover
cluster that was offered by Northeastern.
DATA
PARALLELISM
GPU AND
PYTORCH
Data parallelism is parallelization across
multiple processors in parallel computing
environments. It focuses on distributing the data
across different nodes, which operate on the data in
parallel.
CLASStorch.nn.DataParallel(module, device_ids=N
one, output_device=None, dim=0)
Implements data parallelism at the module level.
ENVIRONMENT SETUP ON
DISCOVERY
METHODOLOGY • PyTorch provides a module nn that makes building
networks much simpler. Here I have build the
same with 784 inputs, hidden units with 512, 256,
128, 64 neurons in each hidden layer, 10 output
units as we have 10 classes to classify and a
softmax output for multi-class classification.
PYTORCH
PYTORCH IS A PYTHON
PACKAGE THAT PROVIDES
TWO HIGH-LEVEL
FEATURES:
TENSOR COMPUTATION
(LIKE NUMPY) WITH
STRONG GPU
ACCELERATION
DEEP NEURAL NETWORKS
BUILT ON A TAPE-BASED
AUTOGRAD SYSTEM
METHODOLOGY
(CONTINUE..)
CNN
IMPLEMENTATION
• Activation Function. The function that we pass the
input information through in a neuron. Used
Rectified Linear Unit (ReLU) as activation
function that is zero for negative x values and a
straight line for positive x values. ReLU is used
more frequently than sigmoid and tanh because
it’s more computationally effective
• I have used torch.Conv2d which Applies a 2D
convolution over an input signal composed of
several input planes.
CODE
SNIPPET
CNN
IMPLEMENTATION
• Used torch.Conv2d which Applies a 2D
convolution over an input signal composed of
several input planes.
• The nn.Dropout2d used during training, randomly
zeroes some of the elements of the input tensor
with probability p using samples from a Bernoulli
distribution. Randomly zero out entire channels (a
channel is a 2D feature map, e.g., the jj -th
channel of the ii -th sample in the batched input is
a 2D tensor text{input}[i, j]input[i,j] ).
CNN
IMPLEMENTATION
• The output of previous layer act as the input to the
next layer and we calculate with below formulae-
• Output = ((input – Kernel_size + 2*padding)/strides
+1)
REASON FOR USING CUSTOM ARCHITECTURE
Firstly, because the input is of 786-
pixel rows of data that is to be trained
and state of art models requires
227x227 or 224x224 dimensional
inputs
The pretrained models have very
deep architectures which is not
required for the current dataset that is
used.
They may lead to overfitting and may
cause vanishing gradient problems
DATA PARALLELISM
OUTPUT FOR 1 GPU (NO DATA
PARALLELISM)
USING 4 GPU (DATA PARALLELISM)
ANALYSIS
WE HAVE
IMPLEMENTED-
USED CPU WITH
NO GPU
GPU WITH NO
DATA
PARALLELISM
MULTIPLE GPU
FOR DATA
PARALLELISM
HYPOTHESIS
We assume that using more GPU
power always reduces the
computational time of any model
Larger batch size means better
predicted model output
Keeping number of GPUs constant,
there exists a linear relationship
between number of batches and time
taken.
EXECUTION
TIME TAKEN
FOR
DIFFERENT
BATCHES
VALIDATION ACCURACY FOR DIFFERENT
BATCH
RESULT
ANALYSIS
Using larger batch sizes does
not necessarily improve the
model Accuracy
Due to larger batch size there is
a chance that the generalization
capabilities is lost.
So the Hypothesis that the
greater Batch size results in
better model prediction does not
hold here.
CONCLUSION • If the memory usage is not optimal than using the
GPU, the model performance on more number of
GPU results in decrease in Overall performance
• There should be optimum usage of GPU and batch
size for better performance. Ideally the GPU usage
should be more than 90%, otherwise there won’t be
advantage of using more GPU and less data. Data
Parallelism will show poor result if under-utilized
high number of GPU is used for model parallelism.
• Keeping number of GPUs constant, there exists a
linear relationship between number of batches and
time taken
FUTURE IMPROVEMENTS SCOPE
THE RECOGNITION OF
DIGITS, A SUBFIELD OF
CHARACTER
RECOGNITION, IS SUBJECT
OF MUCH ATTENTION
SINCE THE FIRST YEARS
OF RESEARCH IN THE
FIELD OF HANDWRITING
RECOGNITION.
IMPROVED PERFORMANCE
HAVE BEEN OBSERVED
WHEN
FEATURE SELECTION
MULTIPLE CLASSIFIERS SYNTHETIC DATA
CREATION OF A DATABASE
WITH TOUCHING DIGITS,
SEGMENTATION BASED ON
AN INTELLIGENT PROCESS
IN ORDER TO REDUCE THE
SEGMENTATION PATH
CANDIDATES, POST-
PROCESSING
TECHNIQUES.
THANK YOU!

More Related Content

Similar to DigitRecognition.pptx

Mauricio breteernitiz hpc-exascale-iscte
Mauricio breteernitiz hpc-exascale-iscteMauricio breteernitiz hpc-exascale-iscte
Mauricio breteernitiz hpc-exascale-isctembreternitz
 
improve deep learning training and inference performance
improve deep learning training and inference performanceimprove deep learning training and inference performance
improve deep learning training and inference performances.rohit
 
From Hours to Minutes: The Journey of Optimizing Mask-RCNN and BERT Using MXNet
From Hours to Minutes: The Journey of Optimizing Mask-RCNN and BERT Using MXNetFrom Hours to Minutes: The Journey of Optimizing Mask-RCNN and BERT Using MXNet
From Hours to Minutes: The Journey of Optimizing Mask-RCNN and BERT Using MXNetEric Haibin Lin
 
Accelerating Real Time Applications on Heterogeneous Platforms
Accelerating Real Time Applications on Heterogeneous PlatformsAccelerating Real Time Applications on Heterogeneous Platforms
Accelerating Real Time Applications on Heterogeneous PlatformsIJMER
 
Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)DonghyunKang12
 
Deep Learning with Apache Spark: an Introduction
Deep Learning with Apache Spark: an IntroductionDeep Learning with Apache Spark: an Introduction
Deep Learning with Apache Spark: an IntroductionEmanuele Bezzi
 
Handwritten Digit Recognition(Convolutional Neural Network) PPT
Handwritten Digit Recognition(Convolutional Neural Network) PPTHandwritten Digit Recognition(Convolutional Neural Network) PPT
Handwritten Digit Recognition(Convolutional Neural Network) PPTRishabhTyagi48
 
Beyond data and model parallelism for deep neural networks
Beyond data and model parallelism for deep neural networksBeyond data and model parallelism for deep neural networks
Beyond data and model parallelism for deep neural networksJunKudo2
 
04 accelerating dl inference with (open)capi and posit numbers
04 accelerating dl inference with (open)capi and posit numbers04 accelerating dl inference with (open)capi and posit numbers
04 accelerating dl inference with (open)capi and posit numbersYutaka Kawai
 
The Rise of Parallel Computing
The Rise of Parallel ComputingThe Rise of Parallel Computing
The Rise of Parallel Computingbakers84
 
Approximation techniques used for general purpose algorithms
Approximation techniques used for general purpose algorithmsApproximation techniques used for general purpose algorithms
Approximation techniques used for general purpose algorithmsSabidur Rahman
 
DeepLearningAlgorithmAccelerationOnHardwarePlatforms_V2.0
DeepLearningAlgorithmAccelerationOnHardwarePlatforms_V2.0DeepLearningAlgorithmAccelerationOnHardwarePlatforms_V2.0
DeepLearningAlgorithmAccelerationOnHardwarePlatforms_V2.0Sahil Kaw
 
SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY
SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY
SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY cscpconf
 
2018 03 25 system ml ai and openpower meetup
2018 03 25 system ml ai and openpower meetup2018 03 25 system ml ai and openpower meetup
2018 03 25 system ml ai and openpower meetupGanesan Narayanasamy
 
"Quantizing Deep Networks for Efficient Inference at the Edge," a Presentatio...
"Quantizing Deep Networks for Efficient Inference at the Edge," a Presentatio..."Quantizing Deep Networks for Efficient Inference at the Edge," a Presentatio...
"Quantizing Deep Networks for Efficient Inference at the Edge," a Presentatio...Edge AI and Vision Alliance
 
GPU Computing: A brief overview
GPU Computing: A brief overviewGPU Computing: A brief overview
GPU Computing: A brief overviewRajiv Kumar
 
Early Application experiences on Summit
Early Application experiences on Summit Early Application experiences on Summit
Early Application experiences on Summit Ganesan Narayanasamy
 
Accelerating stochastic gradient descent using adaptive mini batch size3
Accelerating stochastic gradient descent using adaptive mini batch size3Accelerating stochastic gradient descent using adaptive mini batch size3
Accelerating stochastic gradient descent using adaptive mini batch size3muayyad alsadi
 

Similar to DigitRecognition.pptx (20)

Mauricio breteernitiz hpc-exascale-iscte
Mauricio breteernitiz hpc-exascale-iscteMauricio breteernitiz hpc-exascale-iscte
Mauricio breteernitiz hpc-exascale-iscte
 
improve deep learning training and inference performance
improve deep learning training and inference performanceimprove deep learning training and inference performance
improve deep learning training and inference performance
 
Tensor Processing Unit (TPU)
Tensor Processing Unit (TPU)Tensor Processing Unit (TPU)
Tensor Processing Unit (TPU)
 
From Hours to Minutes: The Journey of Optimizing Mask-RCNN and BERT Using MXNet
From Hours to Minutes: The Journey of Optimizing Mask-RCNN and BERT Using MXNetFrom Hours to Minutes: The Journey of Optimizing Mask-RCNN and BERT Using MXNet
From Hours to Minutes: The Journey of Optimizing Mask-RCNN and BERT Using MXNet
 
Sp19_P2.pptx
Sp19_P2.pptxSp19_P2.pptx
Sp19_P2.pptx
 
Accelerating Real Time Applications on Heterogeneous Platforms
Accelerating Real Time Applications on Heterogeneous PlatformsAccelerating Real Time Applications on Heterogeneous Platforms
Accelerating Real Time Applications on Heterogeneous Platforms
 
Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)
 
Deep Learning with Apache Spark: an Introduction
Deep Learning with Apache Spark: an IntroductionDeep Learning with Apache Spark: an Introduction
Deep Learning with Apache Spark: an Introduction
 
Handwritten Digit Recognition(Convolutional Neural Network) PPT
Handwritten Digit Recognition(Convolutional Neural Network) PPTHandwritten Digit Recognition(Convolutional Neural Network) PPT
Handwritten Digit Recognition(Convolutional Neural Network) PPT
 
Beyond data and model parallelism for deep neural networks
Beyond data and model parallelism for deep neural networksBeyond data and model parallelism for deep neural networks
Beyond data and model parallelism for deep neural networks
 
04 accelerating dl inference with (open)capi and posit numbers
04 accelerating dl inference with (open)capi and posit numbers04 accelerating dl inference with (open)capi and posit numbers
04 accelerating dl inference with (open)capi and posit numbers
 
The Rise of Parallel Computing
The Rise of Parallel ComputingThe Rise of Parallel Computing
The Rise of Parallel Computing
 
Approximation techniques used for general purpose algorithms
Approximation techniques used for general purpose algorithmsApproximation techniques used for general purpose algorithms
Approximation techniques used for general purpose algorithms
 
DeepLearningAlgorithmAccelerationOnHardwarePlatforms_V2.0
DeepLearningAlgorithmAccelerationOnHardwarePlatforms_V2.0DeepLearningAlgorithmAccelerationOnHardwarePlatforms_V2.0
DeepLearningAlgorithmAccelerationOnHardwarePlatforms_V2.0
 
SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY
SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY
SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY
 
2018 03 25 system ml ai and openpower meetup
2018 03 25 system ml ai and openpower meetup2018 03 25 system ml ai and openpower meetup
2018 03 25 system ml ai and openpower meetup
 
"Quantizing Deep Networks for Efficient Inference at the Edge," a Presentatio...
"Quantizing Deep Networks for Efficient Inference at the Edge," a Presentatio..."Quantizing Deep Networks for Efficient Inference at the Edge," a Presentatio...
"Quantizing Deep Networks for Efficient Inference at the Edge," a Presentatio...
 
GPU Computing: A brief overview
GPU Computing: A brief overviewGPU Computing: A brief overview
GPU Computing: A brief overview
 
Early Application experiences on Summit
Early Application experiences on Summit Early Application experiences on Summit
Early Application experiences on Summit
 
Accelerating stochastic gradient descent using adaptive mini batch size3
Accelerating stochastic gradient descent using adaptive mini batch size3Accelerating stochastic gradient descent using adaptive mini batch size3
Accelerating stochastic gradient descent using adaptive mini batch size3
 

Recently uploaded

SPICE PARK APR2024 ( 6,793 SPICE Models )
SPICE PARK APR2024 ( 6,793 SPICE Models )SPICE PARK APR2024 ( 6,793 SPICE Models )
SPICE PARK APR2024 ( 6,793 SPICE Models )Tsuyoshi Horigome
 
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfCCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfAsst.prof M.Gokilavani
 
GDSC ASEB Gen AI study jams presentation
GDSC ASEB Gen AI study jams presentationGDSC ASEB Gen AI study jams presentation
GDSC ASEB Gen AI study jams presentationGDSCAESB
 
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort serviceGurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort servicejennyeacort
 
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdfCCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdfAsst.prof M.Gokilavani
 
Biology for Computer Engineers Course Handout.pptx
Biology for Computer Engineers Course Handout.pptxBiology for Computer Engineers Course Handout.pptx
Biology for Computer Engineers Course Handout.pptxDeepakSakkari2
 
HARMONY IN THE NATURE AND EXISTENCE - Unit-IV
HARMONY IN THE NATURE AND EXISTENCE - Unit-IVHARMONY IN THE NATURE AND EXISTENCE - Unit-IV
HARMONY IN THE NATURE AND EXISTENCE - Unit-IVRajaP95
 
Introduction to Microprocesso programming and interfacing.pptx
Introduction to Microprocesso programming and interfacing.pptxIntroduction to Microprocesso programming and interfacing.pptx
Introduction to Microprocesso programming and interfacing.pptxvipinkmenon1
 
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...srsj9000
 
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...Soham Mondal
 
IVE Industry Focused Event - Defence Sector 2024
IVE Industry Focused Event - Defence Sector 2024IVE Industry Focused Event - Defence Sector 2024
IVE Industry Focused Event - Defence Sector 2024Mark Billinghurst
 
Sachpazis Costas: Geotechnical Engineering: A student's Perspective Introduction
Sachpazis Costas: Geotechnical Engineering: A student's Perspective IntroductionSachpazis Costas: Geotechnical Engineering: A student's Perspective Introduction
Sachpazis Costas: Geotechnical Engineering: A student's Perspective IntroductionDr.Costas Sachpazis
 
Oxy acetylene welding presentation note.
Oxy acetylene welding presentation note.Oxy acetylene welding presentation note.
Oxy acetylene welding presentation note.eptoze12
 
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube ExchangerStudy on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube ExchangerAnamika Sarkar
 
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETEINFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETEroselinkalist12
 
Call Us ≽ 8377877756 ≼ Call Girls In Shastri Nagar (Delhi)
Call Us ≽ 8377877756 ≼ Call Girls In Shastri Nagar (Delhi)Call Us ≽ 8377877756 ≼ Call Girls In Shastri Nagar (Delhi)
Call Us ≽ 8377877756 ≼ Call Girls In Shastri Nagar (Delhi)dollysharma2066
 
What are the advantages and disadvantages of membrane structures.pptx
What are the advantages and disadvantages of membrane structures.pptxWhat are the advantages and disadvantages of membrane structures.pptx
What are the advantages and disadvantages of membrane structures.pptxwendy cai
 

Recently uploaded (20)

SPICE PARK APR2024 ( 6,793 SPICE Models )
SPICE PARK APR2024 ( 6,793 SPICE Models )SPICE PARK APR2024 ( 6,793 SPICE Models )
SPICE PARK APR2024 ( 6,793 SPICE Models )
 
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfCCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
 
GDSC ASEB Gen AI study jams presentation
GDSC ASEB Gen AI study jams presentationGDSC ASEB Gen AI study jams presentation
GDSC ASEB Gen AI study jams presentation
 
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort serviceGurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
 
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdfCCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
 
Biology for Computer Engineers Course Handout.pptx
Biology for Computer Engineers Course Handout.pptxBiology for Computer Engineers Course Handout.pptx
Biology for Computer Engineers Course Handout.pptx
 
HARMONY IN THE NATURE AND EXISTENCE - Unit-IV
HARMONY IN THE NATURE AND EXISTENCE - Unit-IVHARMONY IN THE NATURE AND EXISTENCE - Unit-IV
HARMONY IN THE NATURE AND EXISTENCE - Unit-IV
 
Introduction to Microprocesso programming and interfacing.pptx
Introduction to Microprocesso programming and interfacing.pptxIntroduction to Microprocesso programming and interfacing.pptx
Introduction to Microprocesso programming and interfacing.pptx
 
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
 
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
 
IVE Industry Focused Event - Defence Sector 2024
IVE Industry Focused Event - Defence Sector 2024IVE Industry Focused Event - Defence Sector 2024
IVE Industry Focused Event - Defence Sector 2024
 
Sachpazis Costas: Geotechnical Engineering: A student's Perspective Introduction
Sachpazis Costas: Geotechnical Engineering: A student's Perspective IntroductionSachpazis Costas: Geotechnical Engineering: A student's Perspective Introduction
Sachpazis Costas: Geotechnical Engineering: A student's Perspective Introduction
 
Oxy acetylene welding presentation note.
Oxy acetylene welding presentation note.Oxy acetylene welding presentation note.
Oxy acetylene welding presentation note.
 
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube ExchangerStudy on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
 
young call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Service
young call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Serviceyoung call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Service
young call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Service
 
★ CALL US 9953330565 ( HOT Young Call Girls In Badarpur delhi NCR
★ CALL US 9953330565 ( HOT Young Call Girls In Badarpur delhi NCR★ CALL US 9953330565 ( HOT Young Call Girls In Badarpur delhi NCR
★ CALL US 9953330565 ( HOT Young Call Girls In Badarpur delhi NCR
 
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETEINFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
 
Call Us ≽ 8377877756 ≼ Call Girls In Shastri Nagar (Delhi)
Call Us ≽ 8377877756 ≼ Call Girls In Shastri Nagar (Delhi)Call Us ≽ 8377877756 ≼ Call Girls In Shastri Nagar (Delhi)
Call Us ≽ 8377877756 ≼ Call Girls In Shastri Nagar (Delhi)
 
Exploring_Network_Security_with_JA3_by_Rakesh Seal.pptx
Exploring_Network_Security_with_JA3_by_Rakesh Seal.pptxExploring_Network_Security_with_JA3_by_Rakesh Seal.pptx
Exploring_Network_Security_with_JA3_by_Rakesh Seal.pptx
 
What are the advantages and disadvantages of membrane structures.pptx
What are the advantages and disadvantages of membrane structures.pptxWhat are the advantages and disadvantages of membrane structures.pptx
What are the advantages and disadvantages of membrane structures.pptx
 

DigitRecognition.pptx

  • 1. BACKGROUND • Now a day’s advances have to made to recognize the symbols that were once meaningful and understandable only by humans. It is very easy for humans to understand images, but the same image is very difficult for computer to comprehend. Driverless cars read symbols which were once difficult to understand by computers. • Experiments results on benchmark database of MNIST handwritten digit images show that the performance of our algorithm is remarkable and demonstrate its superiority over several existing algorithms.
  • 2. OBJECTIVE • In the current age of digitization, handwriting recognition plays an important role in information processing • The main objective of the project is to solve the problem where the computer needs to recognize the digits in real time. • With the power of parallel computing, the intention of the project is to solve the real-world problem of recognizing digits through 28000 images which may appear everywhere in our day to day life.
  • 3. GPU SPECIFICATION • Model: Tesla V100-SXM2 • GPU count: 0-4 • GPU Memory: 32510 MB/GPU
  • 4. CPU INFORMATION • Model: Intel(R) Xeon(R) Silver 4114 CPU @ 2.20GHz • Sockets: 2 • Cores/Sockets: 10 • Thread/Core: 2 • CPUs: 40
  • 5. COMMAND FOR ENTERING RESERVATION: • srun -p reservation --reservation=csye7105- gpu --gres=gpu:4 --mem=2Gb --export=ALL -- pty /bin/bash • Command for getting GPU information: nvidia- smi • Command for getting CPU information: lscpu
  • 6. DATASET SPECIFICATIONS • Each image is 28 pixels in height and 28 pixels in width, for a total of 784 pixels in total. Each pixel has a single pixel-value associated with it, indicating the lightness or darkness of that pixel, with higher numbers meaning darker. This pixel- value is an integer between 0 and 255, inclusive. • The training data set, (train.csv), has 785 columns. The first column, called "label", is the digit that was drawn by the user. The rest of the columns contain the pixel-values of the associated image
  • 7. DATA INFORMATION Data Size – 167 MB Number of columns in training set – 785 Each image size – 28 pixel(height) * 28 pixel(width) – 784 pixel total
  • 8. DATA PREPROCESSI NG • The following steps where performed for data pre- processing • Data was normalized • Random rotation • Random Shift
  • 10. WORKING WITH GPU • Pytorch has the package that supports for CUDA tensor types, that implement the same function as CPU tensors, but they utilize GPUs for computation. • PyTorch is an optimized tensor library for deep learning using GPUs and CPUs. • Entire Project was supported by the discover cluster that was offered by Northeastern.
  • 12. GPU AND PYTORCH Data parallelism is parallelization across multiple processors in parallel computing environments. It focuses on distributing the data across different nodes, which operate on the data in parallel. CLASStorch.nn.DataParallel(module, device_ids=N one, output_device=None, dim=0) Implements data parallelism at the module level.
  • 14. METHODOLOGY • PyTorch provides a module nn that makes building networks much simpler. Here I have build the same with 784 inputs, hidden units with 512, 256, 128, 64 neurons in each hidden layer, 10 output units as we have 10 classes to classify and a softmax output for multi-class classification.
  • 15. PYTORCH PYTORCH IS A PYTHON PACKAGE THAT PROVIDES TWO HIGH-LEVEL FEATURES: TENSOR COMPUTATION (LIKE NUMPY) WITH STRONG GPU ACCELERATION DEEP NEURAL NETWORKS BUILT ON A TAPE-BASED AUTOGRAD SYSTEM
  • 17.
  • 18.
  • 19. CNN IMPLEMENTATION • Activation Function. The function that we pass the input information through in a neuron. Used Rectified Linear Unit (ReLU) as activation function that is zero for negative x values and a straight line for positive x values. ReLU is used more frequently than sigmoid and tanh because it’s more computationally effective • I have used torch.Conv2d which Applies a 2D convolution over an input signal composed of several input planes.
  • 21. CNN IMPLEMENTATION • Used torch.Conv2d which Applies a 2D convolution over an input signal composed of several input planes. • The nn.Dropout2d used during training, randomly zeroes some of the elements of the input tensor with probability p using samples from a Bernoulli distribution. Randomly zero out entire channels (a channel is a 2D feature map, e.g., the jj -th channel of the ii -th sample in the batched input is a 2D tensor text{input}[i, j]input[i,j] ).
  • 22. CNN IMPLEMENTATION • The output of previous layer act as the input to the next layer and we calculate with below formulae- • Output = ((input – Kernel_size + 2*padding)/strides +1)
  • 23. REASON FOR USING CUSTOM ARCHITECTURE Firstly, because the input is of 786- pixel rows of data that is to be trained and state of art models requires 227x227 or 224x224 dimensional inputs The pretrained models have very deep architectures which is not required for the current dataset that is used. They may lead to overfitting and may cause vanishing gradient problems
  • 25. OUTPUT FOR 1 GPU (NO DATA PARALLELISM)
  • 26. USING 4 GPU (DATA PARALLELISM)
  • 27. ANALYSIS WE HAVE IMPLEMENTED- USED CPU WITH NO GPU GPU WITH NO DATA PARALLELISM MULTIPLE GPU FOR DATA PARALLELISM
  • 28. HYPOTHESIS We assume that using more GPU power always reduces the computational time of any model Larger batch size means better predicted model output Keeping number of GPUs constant, there exists a linear relationship between number of batches and time taken.
  • 30. VALIDATION ACCURACY FOR DIFFERENT BATCH
  • 31. RESULT ANALYSIS Using larger batch sizes does not necessarily improve the model Accuracy Due to larger batch size there is a chance that the generalization capabilities is lost. So the Hypothesis that the greater Batch size results in better model prediction does not hold here.
  • 32. CONCLUSION • If the memory usage is not optimal than using the GPU, the model performance on more number of GPU results in decrease in Overall performance • There should be optimum usage of GPU and batch size for better performance. Ideally the GPU usage should be more than 90%, otherwise there won’t be advantage of using more GPU and less data. Data Parallelism will show poor result if under-utilized high number of GPU is used for model parallelism. • Keeping number of GPUs constant, there exists a linear relationship between number of batches and time taken
  • 33. FUTURE IMPROVEMENTS SCOPE THE RECOGNITION OF DIGITS, A SUBFIELD OF CHARACTER RECOGNITION, IS SUBJECT OF MUCH ATTENTION SINCE THE FIRST YEARS OF RESEARCH IN THE FIELD OF HANDWRITING RECOGNITION. IMPROVED PERFORMANCE HAVE BEEN OBSERVED WHEN FEATURE SELECTION MULTIPLE CLASSIFIERS SYNTHETIC DATA CREATION OF A DATABASE WITH TOUCHING DIGITS, SEGMENTATION BASED ON AN INTELLIGENT PROCESS IN ORDER TO REDUCE THE SEGMENTATION PATH CANDIDATES, POST- PROCESSING TECHNIQUES.