microsoft / microsoft/DCVC

Clarifying Vimeo dataset for training

Open
#168 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
829
Forks
138
Avg merge
1d 2h
Merged PRs (30d)
1

Description

Hi,

I'm trying to replicate the training procedure and I am currently facing a couple of issues:

  1. For Stage 1 training (10 epochs, cascaded, 256×256), which dataset did you use? Was it the septuplet subset or the original Vimeo videos?

  2. Regarding the Vimeo dataset itself, which videos from the original Vimeo list were actually used, and how were they processed/prepared for training?

Thank you for your help.

Contributor guide

Open the contributing guide

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 locating the Stage 1 training configuration and the code or scripts that prepare the Vimeo dataset; no specific files or tests are named in the issue. Confirm whether training used the septuplet subset or original videos, identify the videos selected, and document the preparation steps and dataset choice.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
data, machine-learning
Issue type
Documentation
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.