Git Product home page Git Product logo

julilien / pldepth Goto Github PK

View Code? Open in Web Editor NEW
12.0 5.0 2.0 515 KB

Code for "Monocular Depth Estimation via Listwise Ranking using the Plackett-Luce Model" as published at CVPR 2021.

License: Apache License 2.0

Python 100.00%
monocular-depth-estimation monocular-depth plackett-luce learning-to-rank deep-learning machine-learning cvpr cvpr2021 preference-learning weakly-supervised-learning

pldepth's People

Contributors

julilien avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

pldepth's Issues

How should I configure the dataset?

I don't quite know how to set the path to the HR-WSI datasets and the following error message appears:

2023-03-31 06:20:48.844340: W tensorflow/core/framework/op_kernel.cc:1830] OP_REQUIRES failed at whole_file_read_ops.cc:114 : NOT_FOUND: tbd/val/valid_masks/CIHP-0000020.png; No such file or directory

Some questions about the hyper-parameters?

Thanks for the great work!
I have some questions about the hyper-parameter between the paper and the github implement.

  1. The ranking size is 5 in the paper while the github code is 3.
  2. The learning rate of PLDepth-EffNet is 1e-2,1e-3, or 1e-4? It is a little confused in the supplementary.
  3. The best sampled ranking number is 100(supplementary) or 400(sec4.4.1), while the best factor is 5 in paper and codes.

Questions regarding evaluation

Dear author,

Thank you for your great work.

I have some questions regarding the procedure for evaluating the ordinal error in your paper.

Did you first random sample 50k pairs of points, filter equidistant points, and then measure the ordinal error on the remaining points?

Or, did you random sample 50k pairs of points that are not equidistant and then measure its error?

Thanks,

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.