Skip to content
Snippets Groups Projects
Select Git revision
  • v2
  • Coscine/FederationAdaption default
  • gitkeep
  • dev protected
  • Sprint/2022-01
  • fixmerge
  • master
  • develop protected
  • dependabot/nuget/Samples/SampleMvcApplication/bootstrap-3.4.1
  • dependabot/nuget/Samples/SampleOwinApplication/bootstrap-3.4.1
  • v1
  • netcore-cookiemanager
  • limitingcookiemanager
  • owin-cookiemanager
  • owin-cookiemanger-changeinterface
  • excess-cookies
  • missing_nodes_exceptions
  • empty_ref_exception
  • fix_shared_options
  • csphashsupport
  • v2.7.0
  • v1.0.2
  • v2.6.0
  • v2.5.0
  • v1.0.1
  • v2.4.0
  • v2.3.0
  • v2.2.0
  • v2.1.0
  • v2.0.0
  • v1.0.0
  • v0.24.0
  • v0.23.0
  • v2.0.0-preview01
  • v0.22.0
  • v0.21.2
  • v0.21.1
  • v0.21.0
  • v0.20.0
  • v0.19.0
40 results

WebSSO

  • Open with
  • Download source code
  • Download directory
  • Your workspaces

      A workspace is a virtual sandbox environment for your code in GitLab.

      No agents available to create workspaces. Please consult Workspaces documentation for troubleshooting.

  • Code owners
    Assign users and groups as approvers for specific file changes. Learn more.

    srn-cfd-web

    This repository runs a web application for predicting the super resolution output using the trained model. It makes use of the Flask python library as an interface between HTML and python. For now, the prediction generates a server on your local machine and makes the computation. The remote computing platforms like AWS, Azure, Google Cloud Computing (GCP) or Heroku are all paid/require credit card information. Nevertheless, this repo shows a working model for the webpage.

    Running the website locally

    1. CLone the repository
    2. Install the packages from the requirements.txt file
    3. Run the app.py file from inside your virtual environment
    4. After running this file, you will see a https link in the terminal, e.g., http://127.0.0.1:5000
    5. Open this link in the browser
    6. In the browser, click on choose file. For testing, I have provided 2 sample files inside the folder 00_test_points
    7. Click on predict. After the calculation is done, a line will show up on the webpage where you can download the prediction file.
    8. As backup, the predictions are also saved in the predictions folder

    Things to Note

    • The input files are currently in npy format only. THe shape of each test input is (n, 512, 512, 2), where n is the number of test examples
    • Loading the website the first time might take some time, because it needs to load the tensorflow and other libraries

    Instructions