OpenGVLab / OpenGVLab/Ask-Anything

Question regarding training time

Open
#247 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
3.4k
Forks
268
PR merge metrics
No merged PRs in 30d

Description

Hello,

As a reference, how long did it take for you to train Stage 1 and 2, respectively (with the training data you described in the paper and set in the configuration file)?

Regarding training resource, from other posts I see that you are using 32 A100 for training.

Context - I found training Stage 1 and 2 with images is pretty fast but training with videos take much much longer time. So it would be helpful to know how long you took to understand if I missed something. (So if it's also possible to share how long it took you to train with images and videos respectively, then it would be even better)

Thank you!

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 the training configuration and the paper referenced in the issue; the payload does not identify their filenames or a specific entry point. Determine whether documented Stage 1 and Stage 2 image and video training durations already exist, then make the expected resource and timing information available if the project has a documentation location.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.