CopyCat Masterclass | 5. How Big Should Your Training Dataset Be?
32Discover the optimal dataset size for training CopyCat. Learn the effectiveness of using 1-30 images for specific shot training, capturing diverse motion and lighting variations. Use larger datasets, ranging from thousands to millions of images, for generalized tasks. We reveal how our human-matting model excelled with around 10,000 images and why a dataset of 10-20 thousand images is typically sufficient for broader applications. Master the balance between dataset size and training specificity with CopyCat.
Check out the full course on our Learn page: https://learn.foundry.com/course/7922...
Alternatively, get the CopyCat Masterclass sessions direct to your inbox. Sign up here https://hubs.la/Q02JlBCf0
00:00 Introduction
00:31 Small Dataset Training
01:21 Large Dataset Training
01:32 Optimal Dataset size
About Us:
We are the creators of industry-standard visual effects, computer graphics and 3D design software for the Digital Design, Media and Entertainment industries. Since 1996, Foundry has strived to bring artists and studios the best tools for their workflows so they can battle industry constraints whilst staying creative.
Subscribe to our channel and get the latest news, tutorials, webinars and updates from the Foundry team.
Follow Us:
/ thefoundryteam
/ foundryteam
/ thefoundryteam
/ foundryteam