Where communities thrive


  • Join over 1.5M+ people
  • Join over 100K+ communities
  • Free without limits
  • Create your own community
People
Activity
    Shobhit Patel
    @shobhitpatel101
    ok, thank you
    Shobhit Patel
    @shobhitpatel101
    Sir, I am working on GAN generator and reconstructing it, can you suggest some article for making it more efficient and fast.
    Vicente González Ruiz
    @vicente-gonzalez-ruiz
    Don't worry about optimizations at this moment. Anyway, I can't help you about this. GANs are new for me. I can only recommend what you already probably know ... Google Scholar and read as much as possible.
    Shobhit Patel
    @shobhitpatel101
    @vicente-gonzalez-ruiz thank you.
    Vicente González Ruiz
    @vicente-gonzalez-ruiz
    Hi @shobhitpatel101. Do you have a repository with the experiments and the code you are developing?
    Shobhit Patel
    @shobhitpatel101
    Yes https://github.com/shobhitpatel101/image-enhancement , but I am working on reconstructing it which is in my local machine.
    Shobhit Patel
    @shobhitpatel101
    @vicente-gonzalez-ruiz Does the input image has some fixed size (width, height) or a random one.
    Vicente González Ruiz
    @vicente-gonzalez-ruiz
    Each image has a different dimension. Your code should read the image header to get this information.
    But, even knowing this, you can consider now that the input image has 256x256 pixels and that the output one has 512x512 (as lena).
    Thank you for the link!
    Shobhit Patel
    @shobhitpatel101
    @vicente-gonzalez-ruiz thank you
    Vicente González Ruiz
    @vicente-gonzalez-ruiz
    You're welcome!
    Shobhit Patel
    @shobhitpatel101
    I am following this paper for training, https://arxiv.org/pdf/1606.03498.pdf
    Vicente González Ruiz
    @vicente-gonzalez-ruiz
    I have read the half of the paper and I think that is very good. Go ahead.
    Shobhit Patel
    @shobhitpatel101
    Ok thanks
    @vicente-gonzalez-ruiz i am following this paper for model training.
    Vicente González Ruiz
    @vicente-gonzalez-ruiz
    :-)
    Shobhit Patel
    @shobhitpatel101
    Very nice, we are selected as honorable. Getting motivated :-)
    Vicente González Ruiz
    @vicente-gonzalez-ruiz
    Yes!
    @shobhitpatel101. I have seen that you are not pushing new things to your repo, and that I have a repo already created for this project. Do you mind if you clone my repo (https://github.com/vicente-gonzalez-ruiz/Super-resolution_Imaging), and include all the stuff you have at (https://github.com/shobhitpatel101/image-enhancement), included the developments you have since 2nd May?
    The idea is to work using pull-request against my repo. In this way, I can follow better your work.
    Shobhit Patel
    @shobhitpatel101
    @vicente-gonzalez-ruiz I am developing it in my local system, it is easy for training and updating, I will update the repo, till what I have done, asap.
    Vicente González Ruiz
    @vicente-gonzalez-ruiz
    Ok, no problem. But I don't see any problem if you commits your changes to your repo at github and, each week you performs a pull-request. It's a bad idea to have the work stored ONLY in a system ... believe me.
    Shobhit Patel
    @shobhitpatel101
    I will update :-)
    Vicente González Ruiz
    @vicente-gonzalez-ruiz
    Thanks!
    Shobhit Patel
    @shobhitpatel101
    @vicente-gonzalez-ruiz sir, i have created a pull request for training module of model.
    Vicente González Ruiz
    @vicente-gonzalez-ruiz
    Thank you, @shobhitpatel101
    Shobhit Patel
    @shobhitpatel101

    Dear Students,

    I hope you are having a good time working on the projects in the frame of SOCIS,
    a listed here: https://socis.esa.int/projects/

    Could you please provide a link to your public code repository to be posted
    on the website (if available)?

    Thanks
    Artur
    This message is intended only for the recipient(s) named above. It may contain proprietary information and/or
    protected content. Any unauthorised disclosure, use, retention or dissemination is prohibited. If you have received
    this e-mail in error, please notify the sender immediately. ESA applies appropriate organisational measures to protect
    personal data, in case of data privacy queries, please contact the ESA Data Protection Officer (dpo@esa.int).

    @vicente-gonzalez-ruiz can i give this repo.. https://github.com/vicente-gonzalez-ruiz/Super-resolution_Imaging or my fork version?
    Vicente González Ruiz
    @vicente-gonzalez-ruiz
    Yes @shobhitpatel101, provide both (your fork and my repo). No problem.
    Shobhit Patel
    @shobhitpatel101
    Ok thank you
    BTW, how the work goes?
    Shobhit Patel
    @shobhitpatel101
    @vicente-gonzalez-ruiz training part is approximately done.
    Thank you for the resources.
    Vicente González Ruiz
    @vicente-gonzalez-ruiz
    OK, please, could you provide some details about how are you performing the training?
    Shobhit Patel
    @shobhitpatel101

    @vicente-gonzalez-ruiz sir, I have used a set of images data to generate its downsampled images X(0.5) and trained my model to generate that X2(original) image from downsampled images.

    basically, this contains 3 steps

    1) converting original images to X(0.5) (256x256)downsampled images.

    2) generating the X(2) (512x512) images from the model

    3) comparing it with original images and updating model to reduce loss.

    Vicente González Ruiz
    @vicente-gonzalez-ruiz
    OK, sounds good. When do you think that we can do some test?
    Shobhit Patel
    @shobhitpatel101
    Thanks, end of this month!
    Vicente González Ruiz
    @vicente-gonzalez-ruiz
    Hi @shobhitpatel101, which is the difference between the images "original_2X" and "processed_2X"?
    Shobhit Patel
    @shobhitpatel101
    Both images are 2x , but in processed_2x some features of images are more dominant like edges, colour contrast,etc.
    Vicente González Ruiz
    @vicente-gonzalez-ruiz
    OK, thanks. However, remember that the idea is to use an image of half-resolution (0.5x) to get the full-resolution one (1x). In this way, we can compare with the original (1x).
    Shobhit Patel
    @shobhitpatel101
    Ok ,we can input a downsampled image as input 1x -> 0.5x then using model we can again generat 0.5x to 1x which is (2x) of input image.
    I will make a function which will convert input image from 1x to 0.5x
    Vicente González Ruiz
    @vicente-gonzalez-ruiz
    Please, use pywavelets
    Shobhit Patel
    @shobhitpatel101
    Ok
    Vicente González Ruiz
    @vicente-gonzalez-ruiz
    Maybe this can help you
    Shobhit Patel
    @shobhitpatel101
    thank you