Astronomy Image Colorization using Machine Learning (GANs)

سرفصل های دوره

Colorize Black & White Astronomical Images Using Python, PyTorch, and FastAPI

1 - Introduction to Course and Generative Adversarial Networks

1 -What youre going to build

2 -Course Introduction

3 -Prerequisites

4 -Intro to Module 1

5 -Generative Models

6 -Example of GANs

7 -Introduction to GANs

8 -GAN Architecture

9 -Loss Function

10 -Balanced Training

11 -Optimizers

12 -Problem with GANs

13 -Module 1 Conclusion

2 - Generate Galaxies using GAN

1 -Module 2 Introduction

2 -Problem Statement

3 -Setting up Kaggle Notebook

4 -Importing Libraries

5 -Load and Analyse the Image

6 -Function to preprocess the Image

7 -Create Dataset Pipeline

8 -Visualise the Data

9 -Build the Generator Model

10 -Build the Discriminator Model

11 -Define Losses and Optimizers

12 -Setup Checkpoints

13 -Function to generate and save images

14 -Function to define a training step

15 -Function to Train the GAN model

17 -Discuss Final Results

18 -Module 2 Conclusion

3 - WGAN with Losses and Gradient Penalty

1 -Module 3 Intro

2 -Quick Recap on GAN

3 -Introduction to Wasserstein GAN (WGAN)

4 -Lipschitz Constraint

5 -Loss Functions for WGAN

6 -WGAN Algorithm

7 -WGAN-GP Algorithm

8 -Understanding WGAN-GP

9 -Module 3 Conclusion

4 - Generating Galaxies using WGAN-GP

1 -Module 4 Introduction

2 -Importing Dependencies

3 -Setting Memory Growth for each GPU

4 -Project Setup

5 -Dataset Preparation

6 -Building the Generator and the Critic

7 -Learning Rate Setup

8 -Building the Checkpoints

9 -Function to generate and save images

10 -Build the training step for the Generator and the Critic

11 -Training WGAN-GP

12 -Compare the real data with the generated data

13 -Module 4 Conclusion

5 - Image to Image Translation GANs

1 -Module 5 Introduction

2 -Block Diagram of Pix2Pix

3 -UNET Architecture for Generator

4 -PatchGAN for Discriminator

5 -Training of Generator

6 -Training of Discriminator

7 -Quick Paper Walkthrough

8 -Module 5 Conclusion

6 - Colorizing black and white Astronomical Images

1 -Module 6 Introduction

2 -PyTorch for Final Project

3 -Adding Dataset to the Notebook

4 -Unzip the Training Images

5 -Importing Libraries and Modules

6 -Visualizing Images in the Dataset

7 -Understanding LAB color space

8 -DataLoader for Training and Validation Sets

9 -Revisiting UNET

11 -Highly Modular UNET for Generator Implementation

12 -70x70 PatchGAN for Discriminator Implementation

13 -Binary Cross Entropy Loss for Generator and Discriminator

14 -Initializing Weights and Model with those Weights

15 -Main Model Definition for Training

16 -Define Utility Functions for Training

17 -Training Outputs

18 -Human Eye Validation

19 -Calculating PSNR and SSIM on Input Data

20 -Final Outputs and Conclusion

21 -Module 6 Conclusion

7 - Introduction to FastAPI and Streamlit

1 -Module 7 Introduction

2 -Whats an API

3 -RESTful API

4 -FastAPI Introduction

5 -Setting up the Demo for FastAPI

6 -Get Method - App Working

7 -Post Method - Create Mission

8 -Get Method - Retrieve Mission(s)

9 -Streamlit Frontend

10 -Module 7 Conclusion

8 - Image Colorization App

1 -Module 8 Introduction

2 -Download the Project file

3 -Setup the Project

4 -Experience the Webapp

5 -Model file model.py

6 -Main app file

7 -frontend.py using chatGPT

8 -Module 8 Conclusion

9 -Course Conclusion

179,000 تومان

افزودن به سبد خرید

خرید دانلودی فوری

در این روش نیاز به افزودن محصول به سبد خرید و تکمیل اطلاعات نیست و شما پس از وارد کردن ایمیل خود و طی کردن مراحل پرداخت لینک های دریافت محصولات را در ایمیل خود دریافت خواهید کرد.

تولید کننده: Udemy