microsoft / microsoft/Swin3D

S3DIS results

Open
#16 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Cuda
Stars
298
Forks
26
Avg merge
22h 44m
Merged PRs (30d)
1

Description

Thanks for sharing your work ! It's possible to provide Swin3D-L (without pretrained) results and the log for Swin3D-S (without pretrained).
I ran some this two exp with 4GPU & 100 epoch and I get :

  • for swin3D-S (without pretrained) mIoU=68.0 (Area 5 validation) (4 points lower your result (72.5))
  • for swin3D-L (without pretrained) mIoU = 69.4 (Area 5 valdiation)
    For both model (pretrained on Structured3D), I get your performance : 73 for Swin3d-S and 74.5 for Swin3d-L).
    So, in paper you announced 3000 epochs for S3DIS to train from scratch on S3DIS, is the number of epochs is 3000 or 100, for training without pretrained pth on Structured3D ?
    If the number if different from 100, which hyperparameter do you used (eval_freq = 2 or higher to save time, ...)
    Thank's

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with issue #16 and compare the reported S3DIS Swin3D-S and Swin3D-L results, including the 100-versus-3000 epoch question. No files or tests are named; done would be documenting the correct training duration, relevant hyperparameters, and the requested training log or results.

Written by the indexing model from the issue text.

Assessment

Domain
computer-vision, machine-learning
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.