SlideShare une entreprise Scribd logo
1  sur  16
TEXT TO IMAGE GENERATION USING
GENERATIVE ADVERSARIAL NETWORKS
CH AAZEEN AHMAD
01-134191-010
INTRODUCTION
 Text-to-image generation is a field with great potential.
 In project, we are programmatically synthesizes one data type into another, generating a photorealist
image based off a phrase.
 Generative Adversarial Networks, or GANs for short, are an approach to generative modeling using
deep learning methods, such as convolutional neural networks.
 Generative modeling is an unsupervised learning task in machine learning that involves automatically
discovering and learning the regularities or patterns in input data in such a way that the model can be
used to generate or output new examples that plausibly could have been drawn from the original
dataset.
 GAN are basically two neural networks fighting against each other. It consists of two networks
Generator and Discriminator . Generator generates specific data and the analyst tries to predict the
weather data from the input database or generator
NETWORK ARCHITECTURE
LITERATURE REVIEW
Year Method / Architecture Problem Description Author
2015 DCGAN
Used deconvolutional layers in
generator and convolutional
layers in discriminator to
generate high-quality images.
Alec Radford and Luke
Metz
2018 StyleGAN
Use adaptive instance
normalization and progressive
growing to generate even higher-
quality images.
Tero Karras and Samuli
Laine
2017 WGAN
Introduced a new objective
function that improved the
stability and convergence of the
GAN training process.
Martin Arjovsky and
Soumith Chintala
Generative Adversarial Networks (GANs) have become a popular research area in deep learning since
their introduction in 2014.
WHY UNSUPERVISED GANS
 This is because the training process of a GAN does not require any labeled data unlike in supervised
learning algorithms.
 In supervised learning, the algorithm is trained on a labeled dataset, where the input data is paired with
the corresponding output label.
 GANs are trained to generate new data that is similar to the training data, without any explicit labels or
annotations. The training process involves two neural networks - the generator network and the
discriminator network - that compete against each other in a zero-sum game.
SO WHY USE GAN FOR IMAGE RESOLUTION
 GANs can generate realistic and high-quality images.
 GANs can handle complex image features, which can be challenging for other neural network
architectures.
 GANs can be combined with other neural network architectures, such as CNNs.The combination allows
GANs to generate high-resolution images from low-resolution inputs, while CNNs can be used to further
refine and enhance the generated images.
 GANs can learn from unlabeled data, which is often available in image super-resolution tasks.
PROJECT AIM
 This project aim is to generate a semantically consistent and visually realistic image conditioned on a
textual description
 Collecting a dataset of low-resolution face images, Preprocessing the dataset, Training a GAN model,
Evaluating the performance of the GAN model
 It is widely used in various fields of likephoto editing, art generation, and computer-aided design
METHODOLOGY
 During the training, A high resolution image is converted into low-resolution image and then Generative
adversarial network upgrade low resolution images to super-resolution then discriminator will distinguish
the high resolution images and backpropagate the adversarial network loss to train both the
discriminator and generator.
METHODOLOGY
SEQUENCE DIAGRAM
HOW TO TRAIN
Training GANs involves the following steps:
 Preparing the Dataset
 Defining the Generator and discriminator Network
 Training the GAN
 Optimizing the GAN
 Evaluating the GAN
TOOLS AND TECHNOLOGIES USED
Language Python 3.7
Framework and libraries Sklearn, OpenCV, Spicy, NumPy,
Pandas, Keras and Pytorch
Notebook Kaggle code and Google collab
SOME RESULTS FROM OUR TRAINED MODEL
This flower is pink in color with oval shaped petals
SOME RESULTS FROM OUR TRAINED MODEL
This flower is yellow in color with oval shaped petals
Thank you

Contenu connexe

Similaire à Face-GAN project report.pptx

Bangla Handwritten Digit Recognition Report.pdf
Bangla Handwritten Digit Recognition  Report.pdfBangla Handwritten Digit Recognition  Report.pdf
Bangla Handwritten Digit Recognition Report.pdfKhondokerAbuNaim
 
Let's paint a Picasso - A Look at Generative Adversarial Networks (GAN) and i...
Let's paint a Picasso - A Look at Generative Adversarial Networks (GAN) and i...Let's paint a Picasso - A Look at Generative Adversarial Networks (GAN) and i...
Let's paint a Picasso - A Look at Generative Adversarial Networks (GAN) and i...Catalina Arango
 
Image super resolution using Generative Adversarial Network.
Image super resolution using Generative Adversarial Network.Image super resolution using Generative Adversarial Network.
Image super resolution using Generative Adversarial Network.IRJET Journal
 
Introduction to Generative Adversarial Networks (GANs)
Introduction to Generative Adversarial Networks (GANs)Introduction to Generative Adversarial Networks (GANs)
Introduction to Generative Adversarial Networks (GANs)Appsilon Data Science
 
Generative adversarial deep learning in images using Nash equilibrium game th...
Generative adversarial deep learning in images using Nash equilibrium game th...Generative adversarial deep learning in images using Nash equilibrium game th...
Generative adversarial deep learning in images using Nash equilibrium game th...IJECEIAES
 
Fashion AI Literature
Fashion AI LiteratureFashion AI Literature
Fashion AI Literatureijtsrd
 
Generative Adversarial Network (GAN)
Generative Adversarial Network (GAN)Generative Adversarial Network (GAN)
Generative Adversarial Network (GAN)Prakhar Rastogi
 
IRJET- A Study of Generative Adversarial Networks in 3D Modelling
IRJET- A Study of Generative Adversarial Networks in 3D ModellingIRJET- A Study of Generative Adversarial Networks in 3D Modelling
IRJET- A Study of Generative Adversarial Networks in 3D ModellingIRJET Journal
 
IRJET- Generating 3D Models Using 3D Generative Adversarial Network
IRJET- Generating 3D Models Using 3D Generative Adversarial NetworkIRJET- Generating 3D Models Using 3D Generative Adversarial Network
IRJET- Generating 3D Models Using 3D Generative Adversarial NetworkIRJET Journal
 
Decomposing image generation into layout priction and conditional synthesis
Decomposing image generation into layout priction and conditional synthesisDecomposing image generation into layout priction and conditional synthesis
Decomposing image generation into layout priction and conditional synthesisNaeem Shehzad
 
An Intelligent approach to Pic to Cartoon Conversion using White-box-cartooni...
An Intelligent approach to Pic to Cartoon Conversion using White-box-cartooni...An Intelligent approach to Pic to Cartoon Conversion using White-box-cartooni...
An Intelligent approach to Pic to Cartoon Conversion using White-box-cartooni...IRJET Journal
 
ATTENTION BASED IMAGE CAPTIONING USING DEEP LEARNING
ATTENTION BASED IMAGE CAPTIONING USING DEEP LEARNINGATTENTION BASED IMAGE CAPTIONING USING DEEP LEARNING
ATTENTION BASED IMAGE CAPTIONING USING DEEP LEARNINGNathan Mathis
 
Devanagari Digit and Character Recognition Using Convolutional Neural Network
Devanagari Digit and Character Recognition Using Convolutional Neural NetworkDevanagari Digit and Character Recognition Using Convolutional Neural Network
Devanagari Digit and Character Recognition Using Convolutional Neural NetworkIRJET Journal
 
IMAGE CAPTION GENERATOR USING DEEP LEARNING
IMAGE CAPTION GENERATOR USING DEEP LEARNINGIMAGE CAPTION GENERATOR USING DEEP LEARNING
IMAGE CAPTION GENERATOR USING DEEP LEARNINGIRJET Journal
 
SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY
SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHYSPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY
SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHYcsandit
 
Enhance your java applications with deep learning using deep netts
Enhance your java applications with deep learning using deep nettsEnhance your java applications with deep learning using deep netts
Enhance your java applications with deep learning using deep nettsZoran Sevarac, PhD
 
小數據如何實現電腦視覺,微軟AI研究首席剖析關鍵
小數據如何實現電腦視覺,微軟AI研究首席剖析關鍵小數據如何實現電腦視覺,微軟AI研究首席剖析關鍵
小數據如何實現電腦視覺,微軟AI研究首席剖析關鍵CHENHuiMei
 
Using GANs to improve generalization in a semi-supervised setting - trying it...
Using GANs to improve generalization in a semi-supervised setting - trying it...Using GANs to improve generalization in a semi-supervised setting - trying it...
Using GANs to improve generalization in a semi-supervised setting - trying it...PyData
 

Similaire à Face-GAN project report.pptx (20)

Bangla Handwritten Digit Recognition Report.pdf
Bangla Handwritten Digit Recognition  Report.pdfBangla Handwritten Digit Recognition  Report.pdf
Bangla Handwritten Digit Recognition Report.pdf
 
Let's paint a Picasso - A Look at Generative Adversarial Networks (GAN) and i...
Let's paint a Picasso - A Look at Generative Adversarial Networks (GAN) and i...Let's paint a Picasso - A Look at Generative Adversarial Networks (GAN) and i...
Let's paint a Picasso - A Look at Generative Adversarial Networks (GAN) and i...
 
Image super resolution using Generative Adversarial Network.
Image super resolution using Generative Adversarial Network.Image super resolution using Generative Adversarial Network.
Image super resolution using Generative Adversarial Network.
 
Introduction to Generative Adversarial Networks (GANs)
Introduction to Generative Adversarial Networks (GANs)Introduction to Generative Adversarial Networks (GANs)
Introduction to Generative Adversarial Networks (GANs)
 
Generative adversarial deep learning in images using Nash equilibrium game th...
Generative adversarial deep learning in images using Nash equilibrium game th...Generative adversarial deep learning in images using Nash equilibrium game th...
Generative adversarial deep learning in images using Nash equilibrium game th...
 
Fashion AI Literature
Fashion AI LiteratureFashion AI Literature
Fashion AI Literature
 
Generative Adversarial Network (GAN)
Generative Adversarial Network (GAN)Generative Adversarial Network (GAN)
Generative Adversarial Network (GAN)
 
Fashion AI
Fashion AIFashion AI
Fashion AI
 
IRJET- A Study of Generative Adversarial Networks in 3D Modelling
IRJET- A Study of Generative Adversarial Networks in 3D ModellingIRJET- A Study of Generative Adversarial Networks in 3D Modelling
IRJET- A Study of Generative Adversarial Networks in 3D Modelling
 
IRJET- Generating 3D Models Using 3D Generative Adversarial Network
IRJET- Generating 3D Models Using 3D Generative Adversarial NetworkIRJET- Generating 3D Models Using 3D Generative Adversarial Network
IRJET- Generating 3D Models Using 3D Generative Adversarial Network
 
Decomposing image generation into layout priction and conditional synthesis
Decomposing image generation into layout priction and conditional synthesisDecomposing image generation into layout priction and conditional synthesis
Decomposing image generation into layout priction and conditional synthesis
 
An Intelligent approach to Pic to Cartoon Conversion using White-box-cartooni...
An Intelligent approach to Pic to Cartoon Conversion using White-box-cartooni...An Intelligent approach to Pic to Cartoon Conversion using White-box-cartooni...
An Intelligent approach to Pic to Cartoon Conversion using White-box-cartooni...
 
One shot learning
One shot learningOne shot learning
One shot learning
 
ATTENTION BASED IMAGE CAPTIONING USING DEEP LEARNING
ATTENTION BASED IMAGE CAPTIONING USING DEEP LEARNINGATTENTION BASED IMAGE CAPTIONING USING DEEP LEARNING
ATTENTION BASED IMAGE CAPTIONING USING DEEP LEARNING
 
Devanagari Digit and Character Recognition Using Convolutional Neural Network
Devanagari Digit and Character Recognition Using Convolutional Neural NetworkDevanagari Digit and Character Recognition Using Convolutional Neural Network
Devanagari Digit and Character Recognition Using Convolutional Neural Network
 
IMAGE CAPTION GENERATOR USING DEEP LEARNING
IMAGE CAPTION GENERATOR USING DEEP LEARNINGIMAGE CAPTION GENERATOR USING DEEP LEARNING
IMAGE CAPTION GENERATOR USING DEEP LEARNING
 
SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY
SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHYSPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY
SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY
 
Enhance your java applications with deep learning using deep netts
Enhance your java applications with deep learning using deep nettsEnhance your java applications with deep learning using deep netts
Enhance your java applications with deep learning using deep netts
 
小數據如何實現電腦視覺,微軟AI研究首席剖析關鍵
小數據如何實現電腦視覺,微軟AI研究首席剖析關鍵小數據如何實現電腦視覺,微軟AI研究首席剖析關鍵
小數據如何實現電腦視覺,微軟AI研究首席剖析關鍵
 
Using GANs to improve generalization in a semi-supervised setting - trying it...
Using GANs to improve generalization in a semi-supervised setting - trying it...Using GANs to improve generalization in a semi-supervised setting - trying it...
Using GANs to improve generalization in a semi-supervised setting - trying it...
 

Dernier

Call Girl Nashik Khushi 7001305949 Independent Escort Service Nashik
Call Girl Nashik Khushi 7001305949 Independent Escort Service NashikCall Girl Nashik Khushi 7001305949 Independent Escort Service Nashik
Call Girl Nashik Khushi 7001305949 Independent Escort Service Nashikranjana rawat
 
(ANJALI) Shikrapur Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune ...
(ANJALI) Shikrapur Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune ...(ANJALI) Shikrapur Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune ...
(ANJALI) Shikrapur Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune ...ranjana rawat
 
Pesticide Calculation Review 2013 post.pptx
Pesticide Calculation Review 2013 post.pptxPesticide Calculation Review 2013 post.pptx
Pesticide Calculation Review 2013 post.pptxalfordglenn
 
(MAYA) Baner Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MAYA) Baner Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts(MAYA) Baner Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MAYA) Baner Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escortsranjana rawat
 
The Most Attractive Pune Call Girls Tingre Nagar 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Tingre Nagar 8250192130 Will You Miss Thi...The Most Attractive Pune Call Girls Tingre Nagar 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Tingre Nagar 8250192130 Will You Miss Thi...ranjana rawat
 
(ISHITA) Call Girls Manchar ( 7001035870 ) HI-Fi Pune Escorts Service
(ISHITA) Call Girls Manchar ( 7001035870 ) HI-Fi Pune Escorts Service(ISHITA) Call Girls Manchar ( 7001035870 ) HI-Fi Pune Escorts Service
(ISHITA) Call Girls Manchar ( 7001035870 ) HI-Fi Pune Escorts Serviceranjana rawat
 
VIP Russian Call Girls Gorakhpur Chhaya 8250192130 Independent Escort Service...
VIP Russian Call Girls Gorakhpur Chhaya 8250192130 Independent Escort Service...VIP Russian Call Girls Gorakhpur Chhaya 8250192130 Independent Escort Service...
VIP Russian Call Girls Gorakhpur Chhaya 8250192130 Independent Escort Service...Suhani Kapoor
 
ΦΑΓΗΤΟ ΤΕΛΕΙΟ ΞΞΞΞΞΞΞ ΞΞΞΞΞΞ ΞΞΞΞ ΞΞΞΞ Ξ
ΦΑΓΗΤΟ ΤΕΛΕΙΟ ΞΞΞΞΞΞΞ ΞΞΞΞΞΞ ΞΞΞΞ ΞΞΞΞ ΞΦΑΓΗΤΟ ΤΕΛΕΙΟ ΞΞΞΞΞΞΞ ΞΞΞΞΞΞ ΞΞΞΞ ΞΞΞΞ Ξ
ΦΑΓΗΤΟ ΤΕΛΕΙΟ ΞΞΞΞΞΞΞ ΞΞΞΞΞΞ ΞΞΞΞ ΞΞΞΞ Ξlialiaskou00
 
Jp Nagar Call Girls Bangalore WhatsApp 8250192130 High Profile Service
Jp Nagar Call Girls Bangalore WhatsApp 8250192130 High Profile ServiceJp Nagar Call Girls Bangalore WhatsApp 8250192130 High Profile Service
Jp Nagar Call Girls Bangalore WhatsApp 8250192130 High Profile ServiceHigh Profile Call Girls
 
Russian Call Girls in Nagpur Devyani Call 7001035870 Meet With Nagpur Escorts
Russian Call Girls in Nagpur Devyani Call 7001035870 Meet With Nagpur EscortsRussian Call Girls in Nagpur Devyani Call 7001035870 Meet With Nagpur Escorts
Russian Call Girls in Nagpur Devyani Call 7001035870 Meet With Nagpur EscortsCall Girls in Nagpur High Profile
 
Vikas Nagar #Dating Call Girls Lucknow Get 50% Off On VIP Escorts Service 🍇 8...
Vikas Nagar #Dating Call Girls Lucknow Get 50% Off On VIP Escorts Service 🍇 8...Vikas Nagar #Dating Call Girls Lucknow Get 50% Off On VIP Escorts Service 🍇 8...
Vikas Nagar #Dating Call Girls Lucknow Get 50% Off On VIP Escorts Service 🍇 8...akbard9823
 
Call Girls Dubai &ubble O525547819 Call Girls In Dubai Blastcum
Call Girls Dubai &ubble O525547819 Call Girls In Dubai BlastcumCall Girls Dubai &ubble O525547819 Call Girls In Dubai Blastcum
Call Girls Dubai &ubble O525547819 Call Girls In Dubai Blastcumkojalkojal131
 
4th QT WEEK 2 Cook Meat Cuts part 2.pptx
4th QT WEEK 2 Cook Meat Cuts part 2.pptx4th QT WEEK 2 Cook Meat Cuts part 2.pptx
4th QT WEEK 2 Cook Meat Cuts part 2.pptxKattieAlisonMacatugg1
 
VVIP Pune Call Girls Viman Nagar (7001035870) Pune Escorts Nearby with Comple...
VVIP Pune Call Girls Viman Nagar (7001035870) Pune Escorts Nearby with Comple...VVIP Pune Call Girls Viman Nagar (7001035870) Pune Escorts Nearby with Comple...
VVIP Pune Call Girls Viman Nagar (7001035870) Pune Escorts Nearby with Comple...Call Girls in Nagpur High Profile
 
Food & Nutrition Strategy Baseline (FNS.pdf)
Food & Nutrition Strategy Baseline (FNS.pdf)Food & Nutrition Strategy Baseline (FNS.pdf)
Food & Nutrition Strategy Baseline (FNS.pdf)Mohamed Miyir
 
VIP Call Girls Service Shamshabad Hyderabad Call +91-8250192130
VIP Call Girls Service Shamshabad Hyderabad Call +91-8250192130VIP Call Girls Service Shamshabad Hyderabad Call +91-8250192130
VIP Call Girls Service Shamshabad Hyderabad Call +91-8250192130Suhani Kapoor
 
Ho Sexy Call Girl in Mira Road Bhayandar | ₹,7500 With Free Delivery, Kashimi...
Ho Sexy Call Girl in Mira Road Bhayandar | ₹,7500 With Free Delivery, Kashimi...Ho Sexy Call Girl in Mira Road Bhayandar | ₹,7500 With Free Delivery, Kashimi...
Ho Sexy Call Girl in Mira Road Bhayandar | ₹,7500 With Free Delivery, Kashimi...Pooja Nehwal
 
(PRIYA) Call Girls Budhwar Peth ( 7001035870 ) HI-Fi Pune Escorts Service
(PRIYA) Call Girls Budhwar Peth ( 7001035870 ) HI-Fi Pune Escorts Service(PRIYA) Call Girls Budhwar Peth ( 7001035870 ) HI-Fi Pune Escorts Service
(PRIYA) Call Girls Budhwar Peth ( 7001035870 ) HI-Fi Pune Escorts Serviceranjana rawat
 
The Billo Photo Gallery - Cultivated Cuisine T1
The Billo Photo Gallery - Cultivated Cuisine T1The Billo Photo Gallery - Cultivated Cuisine T1
The Billo Photo Gallery - Cultivated Cuisine T1davew9
 
VIP Kolkata Call Girl Jadavpur 👉 8250192130 Available With Room
VIP Kolkata Call Girl Jadavpur 👉 8250192130  Available With RoomVIP Kolkata Call Girl Jadavpur 👉 8250192130  Available With Room
VIP Kolkata Call Girl Jadavpur 👉 8250192130 Available With Roomdivyansh0kumar0
 

Dernier (20)

Call Girl Nashik Khushi 7001305949 Independent Escort Service Nashik
Call Girl Nashik Khushi 7001305949 Independent Escort Service NashikCall Girl Nashik Khushi 7001305949 Independent Escort Service Nashik
Call Girl Nashik Khushi 7001305949 Independent Escort Service Nashik
 
(ANJALI) Shikrapur Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune ...
(ANJALI) Shikrapur Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune ...(ANJALI) Shikrapur Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune ...
(ANJALI) Shikrapur Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune ...
 
Pesticide Calculation Review 2013 post.pptx
Pesticide Calculation Review 2013 post.pptxPesticide Calculation Review 2013 post.pptx
Pesticide Calculation Review 2013 post.pptx
 
(MAYA) Baner Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MAYA) Baner Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts(MAYA) Baner Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MAYA) Baner Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
 
The Most Attractive Pune Call Girls Tingre Nagar 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Tingre Nagar 8250192130 Will You Miss Thi...The Most Attractive Pune Call Girls Tingre Nagar 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Tingre Nagar 8250192130 Will You Miss Thi...
 
(ISHITA) Call Girls Manchar ( 7001035870 ) HI-Fi Pune Escorts Service
(ISHITA) Call Girls Manchar ( 7001035870 ) HI-Fi Pune Escorts Service(ISHITA) Call Girls Manchar ( 7001035870 ) HI-Fi Pune Escorts Service
(ISHITA) Call Girls Manchar ( 7001035870 ) HI-Fi Pune Escorts Service
 
VIP Russian Call Girls Gorakhpur Chhaya 8250192130 Independent Escort Service...
VIP Russian Call Girls Gorakhpur Chhaya 8250192130 Independent Escort Service...VIP Russian Call Girls Gorakhpur Chhaya 8250192130 Independent Escort Service...
VIP Russian Call Girls Gorakhpur Chhaya 8250192130 Independent Escort Service...
 
ΦΑΓΗΤΟ ΤΕΛΕΙΟ ΞΞΞΞΞΞΞ ΞΞΞΞΞΞ ΞΞΞΞ ΞΞΞΞ Ξ
ΦΑΓΗΤΟ ΤΕΛΕΙΟ ΞΞΞΞΞΞΞ ΞΞΞΞΞΞ ΞΞΞΞ ΞΞΞΞ ΞΦΑΓΗΤΟ ΤΕΛΕΙΟ ΞΞΞΞΞΞΞ ΞΞΞΞΞΞ ΞΞΞΞ ΞΞΞΞ Ξ
ΦΑΓΗΤΟ ΤΕΛΕΙΟ ΞΞΞΞΞΞΞ ΞΞΞΞΞΞ ΞΞΞΞ ΞΞΞΞ Ξ
 
Jp Nagar Call Girls Bangalore WhatsApp 8250192130 High Profile Service
Jp Nagar Call Girls Bangalore WhatsApp 8250192130 High Profile ServiceJp Nagar Call Girls Bangalore WhatsApp 8250192130 High Profile Service
Jp Nagar Call Girls Bangalore WhatsApp 8250192130 High Profile Service
 
Russian Call Girls in Nagpur Devyani Call 7001035870 Meet With Nagpur Escorts
Russian Call Girls in Nagpur Devyani Call 7001035870 Meet With Nagpur EscortsRussian Call Girls in Nagpur Devyani Call 7001035870 Meet With Nagpur Escorts
Russian Call Girls in Nagpur Devyani Call 7001035870 Meet With Nagpur Escorts
 
Vikas Nagar #Dating Call Girls Lucknow Get 50% Off On VIP Escorts Service 🍇 8...
Vikas Nagar #Dating Call Girls Lucknow Get 50% Off On VIP Escorts Service 🍇 8...Vikas Nagar #Dating Call Girls Lucknow Get 50% Off On VIP Escorts Service 🍇 8...
Vikas Nagar #Dating Call Girls Lucknow Get 50% Off On VIP Escorts Service 🍇 8...
 
Call Girls Dubai &ubble O525547819 Call Girls In Dubai Blastcum
Call Girls Dubai &ubble O525547819 Call Girls In Dubai BlastcumCall Girls Dubai &ubble O525547819 Call Girls In Dubai Blastcum
Call Girls Dubai &ubble O525547819 Call Girls In Dubai Blastcum
 
4th QT WEEK 2 Cook Meat Cuts part 2.pptx
4th QT WEEK 2 Cook Meat Cuts part 2.pptx4th QT WEEK 2 Cook Meat Cuts part 2.pptx
4th QT WEEK 2 Cook Meat Cuts part 2.pptx
 
VVIP Pune Call Girls Viman Nagar (7001035870) Pune Escorts Nearby with Comple...
VVIP Pune Call Girls Viman Nagar (7001035870) Pune Escorts Nearby with Comple...VVIP Pune Call Girls Viman Nagar (7001035870) Pune Escorts Nearby with Comple...
VVIP Pune Call Girls Viman Nagar (7001035870) Pune Escorts Nearby with Comple...
 
Food & Nutrition Strategy Baseline (FNS.pdf)
Food & Nutrition Strategy Baseline (FNS.pdf)Food & Nutrition Strategy Baseline (FNS.pdf)
Food & Nutrition Strategy Baseline (FNS.pdf)
 
VIP Call Girls Service Shamshabad Hyderabad Call +91-8250192130
VIP Call Girls Service Shamshabad Hyderabad Call +91-8250192130VIP Call Girls Service Shamshabad Hyderabad Call +91-8250192130
VIP Call Girls Service Shamshabad Hyderabad Call +91-8250192130
 
Ho Sexy Call Girl in Mira Road Bhayandar | ₹,7500 With Free Delivery, Kashimi...
Ho Sexy Call Girl in Mira Road Bhayandar | ₹,7500 With Free Delivery, Kashimi...Ho Sexy Call Girl in Mira Road Bhayandar | ₹,7500 With Free Delivery, Kashimi...
Ho Sexy Call Girl in Mira Road Bhayandar | ₹,7500 With Free Delivery, Kashimi...
 
(PRIYA) Call Girls Budhwar Peth ( 7001035870 ) HI-Fi Pune Escorts Service
(PRIYA) Call Girls Budhwar Peth ( 7001035870 ) HI-Fi Pune Escorts Service(PRIYA) Call Girls Budhwar Peth ( 7001035870 ) HI-Fi Pune Escorts Service
(PRIYA) Call Girls Budhwar Peth ( 7001035870 ) HI-Fi Pune Escorts Service
 
The Billo Photo Gallery - Cultivated Cuisine T1
The Billo Photo Gallery - Cultivated Cuisine T1The Billo Photo Gallery - Cultivated Cuisine T1
The Billo Photo Gallery - Cultivated Cuisine T1
 
VIP Kolkata Call Girl Jadavpur 👉 8250192130 Available With Room
VIP Kolkata Call Girl Jadavpur 👉 8250192130  Available With RoomVIP Kolkata Call Girl Jadavpur 👉 8250192130  Available With Room
VIP Kolkata Call Girl Jadavpur 👉 8250192130 Available With Room
 

Face-GAN project report.pptx

  • 1. TEXT TO IMAGE GENERATION USING GENERATIVE ADVERSARIAL NETWORKS CH AAZEEN AHMAD 01-134191-010
  • 2. INTRODUCTION  Text-to-image generation is a field with great potential.  In project, we are programmatically synthesizes one data type into another, generating a photorealist image based off a phrase.  Generative Adversarial Networks, or GANs for short, are an approach to generative modeling using deep learning methods, such as convolutional neural networks.  Generative modeling is an unsupervised learning task in machine learning that involves automatically discovering and learning the regularities or patterns in input data in such a way that the model can be used to generate or output new examples that plausibly could have been drawn from the original dataset.  GAN are basically two neural networks fighting against each other. It consists of two networks Generator and Discriminator . Generator generates specific data and the analyst tries to predict the weather data from the input database or generator
  • 4. LITERATURE REVIEW Year Method / Architecture Problem Description Author 2015 DCGAN Used deconvolutional layers in generator and convolutional layers in discriminator to generate high-quality images. Alec Radford and Luke Metz 2018 StyleGAN Use adaptive instance normalization and progressive growing to generate even higher- quality images. Tero Karras and Samuli Laine 2017 WGAN Introduced a new objective function that improved the stability and convergence of the GAN training process. Martin Arjovsky and Soumith Chintala Generative Adversarial Networks (GANs) have become a popular research area in deep learning since their introduction in 2014.
  • 5. WHY UNSUPERVISED GANS  This is because the training process of a GAN does not require any labeled data unlike in supervised learning algorithms.  In supervised learning, the algorithm is trained on a labeled dataset, where the input data is paired with the corresponding output label.  GANs are trained to generate new data that is similar to the training data, without any explicit labels or annotations. The training process involves two neural networks - the generator network and the discriminator network - that compete against each other in a zero-sum game.
  • 6. SO WHY USE GAN FOR IMAGE RESOLUTION  GANs can generate realistic and high-quality images.  GANs can handle complex image features, which can be challenging for other neural network architectures.  GANs can be combined with other neural network architectures, such as CNNs.The combination allows GANs to generate high-resolution images from low-resolution inputs, while CNNs can be used to further refine and enhance the generated images.  GANs can learn from unlabeled data, which is often available in image super-resolution tasks.
  • 7. PROJECT AIM  This project aim is to generate a semantically consistent and visually realistic image conditioned on a textual description  Collecting a dataset of low-resolution face images, Preprocessing the dataset, Training a GAN model, Evaluating the performance of the GAN model  It is widely used in various fields of likephoto editing, art generation, and computer-aided design
  • 8. METHODOLOGY  During the training, A high resolution image is converted into low-resolution image and then Generative adversarial network upgrade low resolution images to super-resolution then discriminator will distinguish the high resolution images and backpropagate the adversarial network loss to train both the discriminator and generator.
  • 11. HOW TO TRAIN Training GANs involves the following steps:  Preparing the Dataset  Defining the Generator and discriminator Network  Training the GAN  Optimizing the GAN  Evaluating the GAN
  • 12. TOOLS AND TECHNOLOGIES USED Language Python 3.7 Framework and libraries Sklearn, OpenCV, Spicy, NumPy, Pandas, Keras and Pytorch Notebook Kaggle code and Google collab
  • 13.
  • 14. SOME RESULTS FROM OUR TRAINED MODEL This flower is pink in color with oval shaped petals
  • 15. SOME RESULTS FROM OUR TRAINED MODEL This flower is yellow in color with oval shaped petals