google-deepmind / google-deepmind/kinetics-i3d

train from scratch on ucf101 dataset

Open
#46 10 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
1.8k
Forks
467
PR merge metrics
No merged PRs in 30d

Description

We try to train i3d model on ucf101 from scratch, but it converges much slower with a final validation accuray around 60%. Can you offer some suggestions on train i3d model without imagenet pretrained model.

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.