Artistic Style Transfer

[smaranjitghose]

Task

Take input a content image,style image and ]output a image that transfers the style into the content image

Guidelines:

• Experiment building this using a Jupyter notebook locally or on Google Colab
• Once its giving desired results put it inside the artistic_style_transfer directory
• Build a script for the task inside the bw_to_c directory
• Inside the artistic_style_transfer 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 to run the script in the same directory
• Push the changes and 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) and 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 make some contributions of your own into it. If you strongly use a code from someone else,please credit them properly in the README file.

[Shweta0002]

Hi , I want to do this one , but can you provide a bit more details?

[ghost]

can you specify what do you need??

[Shweta0002]

the artistic style transfer code is already there in repo , so what we are expected to do? do we have to implement it in some other way ?

[smaranjitghose]

Actually, that was provided as a sample for you all to get started with For starters, you can build a script out of it Also do some digging on some better methods for the same.. See:https://github.com/smaranjitghose/DeepHoli Here we took NVIDIA's State of the Art Approach and implemented it

[SrishtiSinghD]

We have run the existing code on Google Colab and have obtained the desired output. You mention that the next step is to "Build a script for the task inside the bw_to_c directory". Is this a typo from the Black and White to Color task? Shall we build a script in artistic_style_transfer directory?

[smaranjitghose]

Yes, please build it in artistic_style_transfer directory. Sorry, my bad it was a typo

[SrishtiSinghD]

Thank You

On Sat, Mar 28, 2020 at 8:03 PM Smaranjit Ghose notifications@github.com wrote:

Yes, please build it in artistic_style_transfer directory. Sorry, my bad it was a typo

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/smaranjitghose/DeepPixel/issues/7#issuecomment-605455269, or unsubscribe https://github.com/notifications/unsubscribe-auth/ALHCBX6RJ7ML34ERKAHRCU3RJYDCFANCNFSM4LD43FAA .

[SrishtiSinghD]

We would like you to assign this issue to me and @RupaliBhati

[smaranjitghose]

Please ask her to comment so that I can assign

[RupaliBhati]

Hi Smaranjit, kindly assign this problem to me. Thanks!

[Prachi-Agr]

I would like to work on this issue. Kindly assign it to me.

[smaranjitghose]

Its already being assigned to two participants for now,could you please instead work on photorealistic style transition?

[Prachi-Agr]

Yes. I can do that.