Skip to content
This repository has been archived by the owner on Jan 1, 2025. It is now read-only.

Video preprocessing to apply for trained model #122

Open
sakethattaluri opened this issue Feb 4, 2023 · 1 comment
Open

Video preprocessing to apply for trained model #122

sakethattaluri opened this issue Feb 4, 2023 · 1 comment

Comments

@sakethattaluri
Copy link

I have trained the timesformer model with my dataset. What preprocessing steps need to be followed on the video(transforms etc.,) if I want to use the trained model in real-time? Since same transforms which are applied on the train and test dataset need to be applied here

@xqc-qc
Copy link

xqc-qc commented Nov 9, 2023

I have trained the timesformer model with my dataset. What preprocessing steps need to be followed on the video(transforms etc.,) if I want to use the trained model in real-time? Since same transforms which are applied on the train and test dataset need to be applied here

Hello, how did you create your dataset for kinetics which includes several folders? Could you show a screenshot?I am currently having trouble creating the dataset.

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

2 participants