facebookresearch / facebookresearch/SlowFast
question about using my own dataset
Open
- 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
Assessment
This issue has not been assessed yet.