SlideShare a Scribd company logo
1 of 16
INDIANINSTITUTE OF TECHNOLOGY KHARAGPUR
TOPIC:-IMAGE SEGMENTATION USING U-Net
INTRODUCTION
Image segmentation is the task of partitioning an image based on the
objects present and their semantic importance. This makes it a whole lot
easier to analyze the given image, because instead of getting an
approximate location from a rectangular box. We can get the exact
pixel-wise location of the objects.
WHAT IS SEMANTIC SEGMENTATION
Image classification
CLASSIFICATION WITH LOCALIZATION
In localization along with the discrete label, we also expect the compute
to localize where exactly the object is present in the image.
OBJECT DETECTION
Object detection extends localization to the next level, where images are no longer
constrained to have a single object, but can contain multiple objects. The task is to
classify and locate all the objects in the image.
SEMANTIC SEGMENTATION
The goal of semantic image segmentation is to label each pixel of an image with a
corresponding class of what is being represented. Because we’re predicting for
every pixel in the image, this task is commonly referred to as dense prediction.
2D-CONVOLUTION
POOLING LAYER
UN-POOLING
There are three method 1) max un-pool 2) nearest neighbour 3) bed and nails. I
discuss only max un-pool because (nn.ConvTranspose2d)un-pool
use max operation.
MAX-UN POOL AND CONVOLUTION COMBINE OPERATION
U-NET ARCHITECTURE
SEG-NET ARCHITECTURE
1) Conv 3*3 ReLU 2) Max-Pool 2*2 3) up_conv 2*2
IMPLEMENTATION USING PYTHON
COMPARE BETWEENU-NET ANDSEGNET
Here discuss two different compare 1) efficiency (FLOPS) 2) accuracy (loss)
 1) FLOPS:- Convolutions - FLOPs = 2x Number of Kernel x Kernel Shape x Output Shape
=2* c* w* h* ((n-w+2*p)/s+1) * ((m-h+2*p)/s+1)
 Pooling Layers - FLOPs = Height x Depth x Width of an image
= 2 * n * m * c
So the FLOPS for U-Net is=2,251,171,840 and FLOPS for SegNet is= 5,412,076,480
2) accuracy (loss):-- U-Net:- Epoch 1/3 : Training loss: 0.1033
Epoch 2/3 : Training loss: 0.0973
SegNet:- Epoch 1/3 : Training loss: 0.0215
Epoch 2/3 : Training loss: 0.0215
CONCLUSION
The U-Net architecture is one of the most significant and
revolutionary landmarks in the field of deep learning.
While the initial research paper that introduced the U-Net
architecture was to solve the task of Biomedical Image
Segmentation, it was not limited to this single
application. The model could and can still solve the most
complex problems in deep learning. Although some of the
elements in the original architecture are outdated, there
are several variations of this architecture. These include
LadderNet, U-Net with attention, the recurrent and
residual convolutional U-Net (R2-UNet), and other similar
networks which are derived successfully from the original
U-Net Models.
THANK YOU

More Related Content

Similar to image_segmentation_ppt.pptx

Different Image Fusion Techniques –A Critical Review
Different Image Fusion Techniques –A Critical ReviewDifferent Image Fusion Techniques –A Critical Review
Different Image Fusion Techniques –A Critical ReviewIJMER
 
dilating and eroding in open cv
dilating and eroding in open cvdilating and eroding in open cv
dilating and eroding in open cvSaeed Ullah
 
Object Shape Representation by Kernel Density Feature Points Estimator
Object Shape Representation by Kernel Density Feature Points Estimator Object Shape Representation by Kernel Density Feature Points Estimator
Object Shape Representation by Kernel Density Feature Points Estimator cscpconf
 
A robust combination of dwt and chaotic function for image watermarking
A robust combination of dwt and chaotic function for image watermarkingA robust combination of dwt and chaotic function for image watermarking
A robust combination of dwt and chaotic function for image watermarkingijctet
 
Multiresolution SVD based Image Fusion
Multiresolution SVD based Image FusionMultiresolution SVD based Image Fusion
Multiresolution SVD based Image FusionIOSRJVSP
 
An Approach for Image Deblurring: Based on Sparse Representation and Regulari...
An Approach for Image Deblurring: Based on Sparse Representation and Regulari...An Approach for Image Deblurring: Based on Sparse Representation and Regulari...
An Approach for Image Deblurring: Based on Sparse Representation and Regulari...IRJET Journal
 
Low Light Image Enhancement Using Zero-DCE algorithm
Low Light Image Enhancement Using Zero-DCE algorithmLow Light Image Enhancement Using Zero-DCE algorithm
Low Light Image Enhancement Using Zero-DCE algorithmIRJET Journal
 
Enhanced target tracking based on mean shift algorithm for satellite imagery
Enhanced target tracking based on mean shift algorithm for satellite imageryEnhanced target tracking based on mean shift algorithm for satellite imagery
Enhanced target tracking based on mean shift algorithm for satellite imageryeSAT Journals
 
Enhanced target tracking based on mean shift
Enhanced target tracking based on mean shiftEnhanced target tracking based on mean shift
Enhanced target tracking based on mean shifteSAT Publishing House
 
VARIATION-FREE WATERMARKING TECHNIQUE BASED ON SCALE RELATIONSHIP
VARIATION-FREE WATERMARKING TECHNIQUE BASED ON SCALE RELATIONSHIPVARIATION-FREE WATERMARKING TECHNIQUE BASED ON SCALE RELATIONSHIP
VARIATION-FREE WATERMARKING TECHNIQUE BASED ON SCALE RELATIONSHIPcsandit
 
IMPACT OF ERROR FILTERS ON SHARES IN HALFTONE VISUAL CRYPTOGRAPHY
IMPACT OF ERROR FILTERS ON SHARES IN HALFTONE VISUAL CRYPTOGRAPHYIMPACT OF ERROR FILTERS ON SHARES IN HALFTONE VISUAL CRYPTOGRAPHY
IMPACT OF ERROR FILTERS ON SHARES IN HALFTONE VISUAL CRYPTOGRAPHYcscpconf
 
Review-image-segmentation-by-deep-learning
Review-image-segmentation-by-deep-learningReview-image-segmentation-by-deep-learning
Review-image-segmentation-by-deep-learningTrong-An Bui
 
IMAGE SEGMENTATION AND ITS TECHNIQUES
IMAGE SEGMENTATION AND ITS TECHNIQUESIMAGE SEGMENTATION AND ITS TECHNIQUES
IMAGE SEGMENTATION AND ITS TECHNIQUESIRJET Journal
 
E0333021025
E0333021025E0333021025
E0333021025theijes
 
U-Netpresentation.pptx
U-Netpresentation.pptxU-Netpresentation.pptx
U-Netpresentation.pptxNoorUlHaq47
 
From Pixels to Understanding: Deep Learning's Impact on Image Classification ...
From Pixels to Understanding: Deep Learning's Impact on Image Classification ...From Pixels to Understanding: Deep Learning's Impact on Image Classification ...
From Pixels to Understanding: Deep Learning's Impact on Image Classification ...IRJET Journal
 
Unsupervised Object Detection
Unsupervised Object DetectionUnsupervised Object Detection
Unsupervised Object DetectionMahan Fathi
 
IRJET- Real-Time Object Detection using Deep Learning: A Survey
IRJET- Real-Time Object Detection using Deep Learning: A SurveyIRJET- Real-Time Object Detection using Deep Learning: A Survey
IRJET- Real-Time Object Detection using Deep Learning: A SurveyIRJET Journal
 

Similar to image_segmentation_ppt.pptx (20)

Different Image Fusion Techniques –A Critical Review
Different Image Fusion Techniques –A Critical ReviewDifferent Image Fusion Techniques –A Critical Review
Different Image Fusion Techniques –A Critical Review
 
dilating and eroding in open cv
dilating and eroding in open cvdilating and eroding in open cv
dilating and eroding in open cv
 
Object Shape Representation by Kernel Density Feature Points Estimator
Object Shape Representation by Kernel Density Feature Points Estimator Object Shape Representation by Kernel Density Feature Points Estimator
Object Shape Representation by Kernel Density Feature Points Estimator
 
A robust combination of dwt and chaotic function for image watermarking
A robust combination of dwt and chaotic function for image watermarkingA robust combination of dwt and chaotic function for image watermarking
A robust combination of dwt and chaotic function for image watermarking
 
Multiresolution SVD based Image Fusion
Multiresolution SVD based Image FusionMultiresolution SVD based Image Fusion
Multiresolution SVD based Image Fusion
 
An Approach for Image Deblurring: Based on Sparse Representation and Regulari...
An Approach for Image Deblurring: Based on Sparse Representation and Regulari...An Approach for Image Deblurring: Based on Sparse Representation and Regulari...
An Approach for Image Deblurring: Based on Sparse Representation and Regulari...
 
Low Light Image Enhancement Using Zero-DCE algorithm
Low Light Image Enhancement Using Zero-DCE algorithmLow Light Image Enhancement Using Zero-DCE algorithm
Low Light Image Enhancement Using Zero-DCE algorithm
 
Enhanced target tracking based on mean shift algorithm for satellite imagery
Enhanced target tracking based on mean shift algorithm for satellite imageryEnhanced target tracking based on mean shift algorithm for satellite imagery
Enhanced target tracking based on mean shift algorithm for satellite imagery
 
Enhanced target tracking based on mean shift
Enhanced target tracking based on mean shiftEnhanced target tracking based on mean shift
Enhanced target tracking based on mean shift
 
VARIATION-FREE WATERMARKING TECHNIQUE BASED ON SCALE RELATIONSHIP
VARIATION-FREE WATERMARKING TECHNIQUE BASED ON SCALE RELATIONSHIPVARIATION-FREE WATERMARKING TECHNIQUE BASED ON SCALE RELATIONSHIP
VARIATION-FREE WATERMARKING TECHNIQUE BASED ON SCALE RELATIONSHIP
 
IMPACT OF ERROR FILTERS ON SHARES IN HALFTONE VISUAL CRYPTOGRAPHY
IMPACT OF ERROR FILTERS ON SHARES IN HALFTONE VISUAL CRYPTOGRAPHYIMPACT OF ERROR FILTERS ON SHARES IN HALFTONE VISUAL CRYPTOGRAPHY
IMPACT OF ERROR FILTERS ON SHARES IN HALFTONE VISUAL CRYPTOGRAPHY
 
Review-image-segmentation-by-deep-learning
Review-image-segmentation-by-deep-learningReview-image-segmentation-by-deep-learning
Review-image-segmentation-by-deep-learning
 
Medial axis transformation based skeletonzation of image patterns using image...
Medial axis transformation based skeletonzation of image patterns using image...Medial axis transformation based skeletonzation of image patterns using image...
Medial axis transformation based skeletonzation of image patterns using image...
 
IMAGE SEGMENTATION AND ITS TECHNIQUES
IMAGE SEGMENTATION AND ITS TECHNIQUESIMAGE SEGMENTATION AND ITS TECHNIQUES
IMAGE SEGMENTATION AND ITS TECHNIQUES
 
GRUPO 2 : convolution separable
GRUPO 2 :  convolution separableGRUPO 2 :  convolution separable
GRUPO 2 : convolution separable
 
E0333021025
E0333021025E0333021025
E0333021025
 
U-Netpresentation.pptx
U-Netpresentation.pptxU-Netpresentation.pptx
U-Netpresentation.pptx
 
From Pixels to Understanding: Deep Learning's Impact on Image Classification ...
From Pixels to Understanding: Deep Learning's Impact on Image Classification ...From Pixels to Understanding: Deep Learning's Impact on Image Classification ...
From Pixels to Understanding: Deep Learning's Impact on Image Classification ...
 
Unsupervised Object Detection
Unsupervised Object DetectionUnsupervised Object Detection
Unsupervised Object Detection
 
IRJET- Real-Time Object Detection using Deep Learning: A Survey
IRJET- Real-Time Object Detection using Deep Learning: A SurveyIRJET- Real-Time Object Detection using Deep Learning: A Survey
IRJET- Real-Time Object Detection using Deep Learning: A Survey
 

Recently uploaded

Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz1
 
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...soniya singh
 
Unveiling Insights: The Role of a Data Analyst
Unveiling Insights: The Role of a Data AnalystUnveiling Insights: The Role of a Data Analyst
Unveiling Insights: The Role of a Data AnalystSamantha Rae Coolbeth
 
Schema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfSchema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfLars Albertsson
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxEmmanuel Dauda
 
Industrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfIndustrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfLars Albertsson
 
04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationshipsccctableauusergroup
 
Log Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxLog Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxJohnnyPlasten
 
Aminabad Call Girl Agent 9548273370 , Call Girls Service Lucknow
Aminabad Call Girl Agent 9548273370 , Call Girls Service LucknowAminabad Call Girl Agent 9548273370 , Call Girls Service Lucknow
Aminabad Call Girl Agent 9548273370 , Call Girls Service Lucknowmakika9823
 
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Jack DiGiovanna
 
Predicting Employee Churn: A Data-Driven Approach Project Presentation
Predicting Employee Churn: A Data-Driven Approach Project PresentationPredicting Employee Churn: A Data-Driven Approach Project Presentation
Predicting Employee Churn: A Data-Driven Approach Project PresentationBoston Institute of Analytics
 
RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998YohFuh
 
Full night 🥵 Call Girls Delhi New Friends Colony {9711199171} Sanya Reddy ✌️o...
Full night 🥵 Call Girls Delhi New Friends Colony {9711199171} Sanya Reddy ✌️o...Full night 🥵 Call Girls Delhi New Friends Colony {9711199171} Sanya Reddy ✌️o...
Full night 🥵 Call Girls Delhi New Friends Colony {9711199171} Sanya Reddy ✌️o...shivangimorya083
 
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130Suhani Kapoor
 
Ukraine War presentation: KNOW THE BASICS
Ukraine War presentation: KNOW THE BASICSUkraine War presentation: KNOW THE BASICS
Ukraine War presentation: KNOW THE BASICSAishani27
 
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Serviceranjana rawat
 
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsappssapnasaifi408
 

Recently uploaded (20)

Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signals
 
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
 
Unveiling Insights: The Role of a Data Analyst
Unveiling Insights: The Role of a Data AnalystUnveiling Insights: The Role of a Data Analyst
Unveiling Insights: The Role of a Data Analyst
 
Schema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfSchema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdf
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptx
 
Industrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfIndustrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdf
 
04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships
 
Log Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxLog Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptx
 
Aminabad Call Girl Agent 9548273370 , Call Girls Service Lucknow
Aminabad Call Girl Agent 9548273370 , Call Girls Service LucknowAminabad Call Girl Agent 9548273370 , Call Girls Service Lucknow
Aminabad Call Girl Agent 9548273370 , Call Girls Service Lucknow
 
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
 
Predicting Employee Churn: A Data-Driven Approach Project Presentation
Predicting Employee Churn: A Data-Driven Approach Project PresentationPredicting Employee Churn: A Data-Driven Approach Project Presentation
Predicting Employee Churn: A Data-Driven Approach Project Presentation
 
RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998
 
Full night 🥵 Call Girls Delhi New Friends Colony {9711199171} Sanya Reddy ✌️o...
Full night 🥵 Call Girls Delhi New Friends Colony {9711199171} Sanya Reddy ✌️o...Full night 🥵 Call Girls Delhi New Friends Colony {9711199171} Sanya Reddy ✌️o...
Full night 🥵 Call Girls Delhi New Friends Colony {9711199171} Sanya Reddy ✌️o...
 
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130
VIP Call Girls Service Miyapur Hyderabad Call +91-8250192130
 
Ukraine War presentation: KNOW THE BASICS
Ukraine War presentation: KNOW THE BASICSUkraine War presentation: KNOW THE BASICS
Ukraine War presentation: KNOW THE BASICS
 
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
(PARI) Call Girls Wanowrie ( 7001035870 ) HI-Fi Pune Escorts Service
 
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in Kishangarh
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in  KishangarhDelhi 99530 vip 56974 Genuine Escort Service Call Girls in  Kishangarh
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in Kishangarh
 
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
 
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
 
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
 

image_segmentation_ppt.pptx

  • 1. INDIANINSTITUTE OF TECHNOLOGY KHARAGPUR TOPIC:-IMAGE SEGMENTATION USING U-Net
  • 2. INTRODUCTION Image segmentation is the task of partitioning an image based on the objects present and their semantic importance. This makes it a whole lot easier to analyze the given image, because instead of getting an approximate location from a rectangular box. We can get the exact pixel-wise location of the objects.
  • 3. WHAT IS SEMANTIC SEGMENTATION Image classification
  • 4. CLASSIFICATION WITH LOCALIZATION In localization along with the discrete label, we also expect the compute to localize where exactly the object is present in the image.
  • 5. OBJECT DETECTION Object detection extends localization to the next level, where images are no longer constrained to have a single object, but can contain multiple objects. The task is to classify and locate all the objects in the image.
  • 6. SEMANTIC SEGMENTATION The goal of semantic image segmentation is to label each pixel of an image with a corresponding class of what is being represented. Because we’re predicting for every pixel in the image, this task is commonly referred to as dense prediction.
  • 9. UN-POOLING There are three method 1) max un-pool 2) nearest neighbour 3) bed and nails. I discuss only max un-pool because (nn.ConvTranspose2d)un-pool use max operation.
  • 10. MAX-UN POOL AND CONVOLUTION COMBINE OPERATION
  • 12. SEG-NET ARCHITECTURE 1) Conv 3*3 ReLU 2) Max-Pool 2*2 3) up_conv 2*2
  • 14. COMPARE BETWEENU-NET ANDSEGNET Here discuss two different compare 1) efficiency (FLOPS) 2) accuracy (loss)  1) FLOPS:- Convolutions - FLOPs = 2x Number of Kernel x Kernel Shape x Output Shape =2* c* w* h* ((n-w+2*p)/s+1) * ((m-h+2*p)/s+1)  Pooling Layers - FLOPs = Height x Depth x Width of an image = 2 * n * m * c So the FLOPS for U-Net is=2,251,171,840 and FLOPS for SegNet is= 5,412,076,480 2) accuracy (loss):-- U-Net:- Epoch 1/3 : Training loss: 0.1033 Epoch 2/3 : Training loss: 0.0973 SegNet:- Epoch 1/3 : Training loss: 0.0215 Epoch 2/3 : Training loss: 0.0215
  • 15. CONCLUSION The U-Net architecture is one of the most significant and revolutionary landmarks in the field of deep learning. While the initial research paper that introduced the U-Net architecture was to solve the task of Biomedical Image Segmentation, it was not limited to this single application. The model could and can still solve the most complex problems in deep learning. Although some of the elements in the original architecture are outdated, there are several variations of this architecture. These include LadderNet, U-Net with attention, the recurrent and residual convolutional U-Net (R2-UNet), and other similar networks which are derived successfully from the original U-Net Models.