facebookresearch / facebookresearch/SlowFast

question about using my own dataset

Open
#366 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
7.4k
Forks
1.3k
PR merge metrics
No merged PRs in 30d

Description

Hello,
I tried to run the project on my own video dataset.
I couldn't figure out how to organize the path to the data and the csv file, and also I would like to understand what should be the configuration that will be best fit.
right now I get an error because the value of 'num_samples' in TrainMeter class is zero.
It will be really helpful if u could help,
Thank u!!

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.