CopyCat Masterclass | 11. Batch Size: Optimizing Dataset Size
23Batch size, the number of crops processed per step, is key to effective training. For large, generalized datasets, opt for the largest batch size your GPU can manage for smoother, more stable loss curves and better results. However, small dataset training benefits from lower batch sizes, often achieving quicker results without sacrificing quality. Understand the limits of your dataset and hardware to choose the ideal batch size, balancing training speed and stability for your specific CopyCat project.
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
00:12 What is batch size?
00:41 Optimizing
01:12 Small vs Large batch 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