Skip to content
This repository has been archived by the owner on Oct 31, 2023. It is now read-only.

PASCAL VOC dataset settings #5

Closed
prinshul opened this issue Mar 24, 2021 · 2 comments
Closed

PASCAL VOC dataset settings #5

prinshul opened this issue Mar 24, 2021 · 2 comments

Comments

@prinshul
Copy link

Can you please mention the settings for PASCAL VOC dataset like Image size, batch size (labeled/unlabeled), total iterations, epochs?

@ycliu93
Copy link
Contributor

ycliu93 commented Mar 27, 2021

Here are the details of VOC experiments. You could directly use the following parameters in your config files.

INPUT:
  MIN_SIZE_TRAIN: (480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800)
  MIN_SIZE_TEST: 800
SOLVER:
  MAX_ITER: 180000 
  IMG_PER_BATCH_LABEL: 32
  IMG_PER_BATCH_UNLABEL: 32
  BASE_LR: 0.001

For other parameters, you could check the last page of the appendix.https://arxiv.org/pdf/2102.09480.pdf

@namihagi
Copy link

I have other question about voc setting.
BURN_UP_STEP is 45k iterations in your VOC setting?

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants