Deep Pixel

MentorSmaranjit Ghose (smaranjitghose)
Project Websitehttps://github.com/smaranjitghose/DeepPixel
Project Repositoryhttps://github.com/smaranjitghose/DeepPixel
Suitable for Beginners?no
Tagspython tensorflow pytorch tensorflow.js flask html css javascript
Stateaccepted
Applications (1st Choice)13 (12 submitted | 1 in-progress)
Applications (2nd Choice)9 (8 submitted | 1 in-progress)
Code of Conducthttps://github.com/smaranjitghose/DeepPixel/blob/master/CODE_OF_CONDUCT.md
LicenseMIT license (MIT)

Project Description

Issues
Pull Requests
Forks
Stars
License
Join the chat at https://gitter.im/opendeeppixel/community

Background: πŸ”

Deep Neural networks have already surpassed human level performance in tasks such as object recognition and detection. However, deep networks were lagging far behind in tasks like generating artistic artefacts having high perceptual quality until recent times. Creating better quality art using machine learning techniques is imperative for reaching human-like capabilities, as well as opens up a new spectrum of possibilities. And with the advancement of computer hardware as well as the proliferation of deep learning, deep learning is right now being used to create art. For example, an AI generated art won’t be sold at an auction for a whopping $432,500.

Project's Requirements

Skills Required: πŸ’ͺ

  • Python(Mandatory)
  • Git(Mandatorty)
  • Linux Command Line(Mandatory)
  • Elementary Knowledge of Deep Learning or Computer Vision (Mandatory)
  • Ability to use TensorFlow 2.0/PyTorch/Keras/fast.ai (any one is suggested)
  • OpenCV(Required)
  • HTML,CSS,JavaScript(can be picked up on the go)
  • TensorFlow.JS

And above all the willingness to learn and contribute!

Tasks And Features

Tasks: πŸ“πŸ“‹

  • Implement different image processing scripts(using opencv)that can used to enhancing pictures,obtaining information and transforming it for desired purposes
  • Use deep learning for the same. Eg: Neural Style Transfer,BlackandWhitetoColor
  • Reimplement State-of-the-Art(SOTA) Research papers for the this
  • Suggestion: Use Tranfer Learning
  • For the image processing tasks make custom datasets...use tools like CVAT
  • Repeat the same for the deep learning tasks
  • Convert the work done in Jupyter Notebooks into executable scripts
  • Use TensorFlow.JS to build end to end models for showcase
  • Build a website for this project
  • Extend the work for some of the sripts to make a Flutter app using TensorFlow Lite
  • Improve the documentation (ReadME)

Guidelines to Contribute : 🀚 πŸ—

  • Don't push anything to the root directory.Always use specific subdirectories inside the deeppixel directory

For each of the tasks:

  • Experiment building this using a Jupyter notebook locally or on Google Colab
  • Build a script for the task inside the respective directory
  • Inside the bw_to_c directory, create two folders input and output to be used for the input and output images
  • Use argparse library so that the input image and output path can be given as arguments in the terminal while running the script
  • Create a requirements.txt file and specify the modules used
  • Try your script/notebook with multiple images and store the results in output folder
  • Comment your script/notebook well
  • Create/Update the ReadME.MD file:
    • Name of the task
    • A small description
    • Approach used
    • Input and Output Images
  • Make sure you have the model weight or any related files like haarcascades to run the script in the same direcorty
  • Give a Pull Request
  • In your PR, please try to give a link to a Colab Notebook(if applicable) as a comment.
  • In your PR, put a reference to the issue it is for
  • once your model/script works, curate your own dataset and get the outputs..(Try 10 images) adn give a second PR about your own Dataset
  • Try out other methods to implement the above

__Please do not use a code from someone else's repo or a blog like PyImageSearch directly..You can definitely refer to others' code. But make sure you have some contributions of your own into it. If you strongly use a code from someone else,please credit them properly in the README file of the respective directory.

How to contribute:

RGSOC'20

1. Fork this repository.

2. Clone the forked repository.
terminal
git clone https://github.com/<your-github-username>/DeepPixel

3. Navigate to the project directory.
terminal
cd DeepPixel

4. Create a new branch.
terminal
git checkout -b <your_branch_name>

5. Make changes in source code.

6. Commit your changes.

terminal
git add .
git commit -m "<your_commit_message>"

7. Push your local branch to the remote repository.
terminal
git push -u origin <your_branch_name>

8. Create a Pull Request!

Congratulations! You have just made your contribution to DeepPixel project.

Comments

You must be logged in to comment on this project.


Siddhant Pathak, Friday, March 27, 18:08 UTC

Hello Team 'DeepPixel' . I am a data scientist at a leading gaming industry based in India. The skills required for this project match with my domain. So I would like to coach / mentor your team. Feel free to DM me through linkedin at linkedin/siddhant96


tea-n-biccies RGSoC, Friday, March 20, 13:39 UTC

Dear RGSoC applicants - we have added a new FAQ page to the website. Please check this out before asking mentors your questions, as we may already have an answer for you :)
https://railsgirlssummerofcode.org/students/faq

Further details of how to apply to RGSoC (by 23:00 UTC on 30 March 2020) can be found at https://railsgirlssummerofcode.org/students


jhalak27, Friday, March 20, 13:33 UTC

Hi, This is Jhalak. My teammate is Najma and we are from team ShowThem. We would love to contribute to this project. We both have work experience in research and open-source. We both have been working with deep learning in python for quite a few time now and we are proficient in most of the tech stack mentioned. We fancy this project because it lies in our domain of interest and will help boost my knowledge towards the same.
Could you let us know how should we proceed?


Smaranjit Ghose, Thursday, March 19, 11:14 UTC

Please checkout the README and join the gitter channel


Divija Palleti, Thursday, March 19, 06:12 UTC

Hi! I'm Divija. My teammate Niharika and I would love to contribute. We both have experience working in research, industry and in the open-source before. We're familiar with most of the tech mentioned. Please do let us know what further information you'd like to know about our past experience and how we can get started?


tea-n-biccies RGSoC, Monday, March 9, 11:13 UTC

Hi everyone - the RGSoC team here :)
Just a reminder that student applications are open until 23:00 UTC on 30 March 2020.
For information on how to apply as a student so you can work on this project with RGSoC, please read the guidance at https://railsgirlssummerofcode.org/students


suhrid datta, Tuesday, March 3, 15:56 UTC

Hey all!..the mentors are gonna assign some issues soon..Meanwhile please go through the updated Tasks on the GitHub Repo for getting started with something you are comfortable with


Shweta Shukla, Monday, March 2, 19:28 UTC

Hi , @suhrid datta I am Shweta Shukla , I have good knowledge in ML and Deep learning , I would love to contribute in this project along with my team mate Kritika Gupta from team Warriors .


kritika12298, Monday, March 2, 19:12 UTC

Hello, I am Kritika Gupta , my teammate is Shweta Shukla and we are from team Warriors. We are interested to apply for this project , so how get started with this project . We have read the README.md for this repository but there are no issues regarding this project.


Ching Lam Choi , Thursday, February 20, 21:46 UTC

Hello! Is it also alright to do this with Pytorch? Thanks!