microsoft / microsoft/Swin3D

Low Result without pretrained pth

Open
#19 1 comment 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

          @Yukichiii I applied epochs = 100 // loop = 30 and eval_freq = 2. I get on Area 5 : 
  • Swin3d-S : 69.76
  • Swin3d-L : 69.79
    It is possible to provide the log ? For the tests do you use num_vote = 12 ? For training did you change any parameters on relation to code https://github.com/Yukichiii/Swin3D_Task
    The result in your paper Swin3D-S | ✗ | 72.5 (without pretrained weight), is obtained with RGB or RGB + Normals.
    Thank's

Originally posted by @hpc100 in https://github.com/microsoft/Swin3D/issues/16#issuecomment-1733586979

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 by reviewing the reported Area 5 results and the comparison with the Swin3D_Task repository, then inspect issue #16 for the surrounding context. Reproduce the stated training and evaluation settings, including epochs, loop, eval frequency, and num_vote, and document whether the reported result can be obtained without pretrained weights.

Written by the indexing model from the issue text.

Assessment

Domain
computer-vision, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.