Reproducing standard benchmarks using Transolver++
Nobody has claimed this yet.
Assessment
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Newbie friendliness
- 35/100
- Issue type
- Bug
- Clarity
- Needs clarification
- Activity status
- Quiet
- Tech stack
- python
- Domain
- machine-learning
Research direction
No files, tests, or entry points are named. Start by locating the training scripts and configs for the six standard benchmarks, then compare them with the paper’s hyperparameters and the stated in_project_fx and Gumbel-Softmax changes. Done means either reproducing the reported results or documenting the additional changes needed.
Written by the indexing model from the issue text.
Description
Hi, and thanks for the great work!
I’m having trouble reproducing the reported Transolver++ results on the six standard benchmarks. My understanding is that Transolver++ (a) reduces in_project_fx and (b) replaces the softmax with Gumbel-Softmax. Using the training hyperparameters from the paper, my runs do not outperform the original Transolver.
- Are there additional architectural or training changes beyond reducing in_project_fx and using Gumbel-Softmax?
- Could the reduced parameter count require capacity to be added elsewhere?
- Has anyone successfully matched the paper’s numbers, and if so, could you share the training scripts and configs?
Thanks in advance!
- Dominant language
- Python
- Stars
- 90
- Forks
- 12
- PR merge metrics
- No merged PRs in 30d
Getting set up
This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from thuml/Transolver_plus
-
Difficulty 2/5 1-3 hours Newbie friendliness 52/100
thuml/Transolver_plus#13 ·
-
About datasetOpen
Difficulty 5/5 Over a week Newbie friendliness 20/100
thuml/Transolver_plus#11 ·
-
Difficulty 5/5 Over a week Newbie friendliness 15/100
thuml/Transolver_plus#7 · 1 reaction ·
-
Difficulty 4/5 3-5 days Newbie friendliness 25/100
thuml/Transolver_plus#5 · 5 reactions ·
All issues in thuml/Transolver_plus
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 74/100
-
enhancement
Difficulty 2/5 1-3 hours Newbie friendliness 66/100
RunestoneInteractive/rs#1661 ·
Maintainers usually reply within 2 days
-
Difficulty 2/5 1-3 hours Newbie friendliness 64/100
streamlink/streamlink#7192 · 4 comments ·
Maintainers usually reply within 1 day
-
Difficulty 1/5 1-3 hours Newbie friendliness 75/100
Maintainers usually reply within 2 days
-
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
aws-samples/sample-per-model-bedrock#795 ·
Maintainers usually reply within 1 day