Style Transfer for Custom Images

[anushkasaxena07]

Deep Learning Simplified Repository (Proposing new issue)

🔴 Project Title : Style Transfer for Custom Images

🔴 Aim : To apply the artistic style of one image to the content of another image using various style transfer algorithms and determine the most effective method through comparative analysis.

🔴 Dataset : Custom images collected from diverse sources to ensure a variety of styles and contents for comprehensive testing.

🔴 Approach : Perform exploratory data analysis (EDA) to understand the characteristics and distribution of the custom images.
Implement and compare multiple style transfer algorithms:
Neural Style Transfer using VGG-19
Fast Style Transfer
Adaptive Instance Normalization (AdaIN)
StyleGAN-based approach
Evaluate the performance of each algorithm by comparing the visual quality and accuracy scores of the styled images.
Determine the best-fitting algorithm based on the comparative analysis results.

---

📍 Follow the Guidelines to Contribute in the Project :

• You need to create a separate folder named as the Project Title.
• Inside that folder, there will be four main components.
  • Images - To store the required images.
  • Dataset - To store the dataset or, information/source about the dataset.
  • Model - To store the machine learning model you've created using the dataset.
  • requirements.txt - This file will contain the required packages/libraries to run the project in other machines.
• Inside the Model folder, the README.md file must be filled up properly, with proper visualizations and conclusions.

---

🔴🟡 Points to Note :

• The issues will be assigned on a first come first serve basis, 1 Issue == 1 PR.
• "Issue Title" and "PR Title should be the same. Include issue number along with it.
• Follow Contributing Guidelines & Code of Conduct before start Contributing.

---

✅ To be Mentioned while taking the issue :

• Full name : Anushka Saxena
• GitHub Profile Link : anushkasaxena07
• Email ID :[email protected]
• Participant ID (if applicable):
• Approach for this Project :Perform exploratory data analysis (EDA) to understand the characteristics and distribution of the custom images.
  Implement and compare multiple style transfer algorithms:
  Neural Style Transfer using VGG-19
  Fast Style Transfer
  Adaptive Instance Normalization (AdaIN)
  StyleGAN-based approach
  Evaluate the performance of each algorithm by comparing the visual quality and accuracy scores of the styled images.
  Determine the best-fitting algorithm based on the comparative analysis results.
• What is your participant role? (Mention the Open Source program)

---

Happy Contributing 🚀

All the best. Enjoy your open source journey ahead. 😎

[github-actions]

Thank you for creating this issue! We'll look into it as soon as possible. Your contributions are highly appreciated! 😊

[anushkasaxena07]

@abhisheks008 plz assign me this issue

[abhisheks008]

• Neural Style Transfer using VGG-19
• Fast Style Transfer
• Adaptive Instance Normalization (AdaIN)
• StyleGAN-based approach

All the four above mentioned models will going to be implemented for the problem statement right?
Also can you ensure the source of the dataset?