Lower precision in trainnet workflow

2024 5 18
1 个回答
更新时间：2024 5 19
11 次查看（30 天）

0 个投票

Hi,
Is there a way to adjust the precision when training a network using the "trainnet" workflow (2024a)? I'm interested in lowering precision to speed up training, in the same way I would use "torch.set_float32_matmul_precision" in pytorch.
Thanks,
Eric

请先登录，再回答此问题。

回答（1 个）

Matt J
Matt J 2024-5-19
编辑：Matt J 2024-5-19

0 个投票

Just pass in training data with a lower precision type (e.g., singles versus doubles).

类别

在 帮助中心 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

产品

版本

R2024a

标签

编辑：

Matt J
Matt J
2024-5-19

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by