Skip to content
This repository has been archived by the owner on Oct 31, 2023. It is now read-only.

problem of inference precision #31

Closed
aso538 opened this issue Dec 6, 2022 · 1 comment
Closed

problem of inference precision #31

aso538 opened this issue Dec 6, 2022 · 1 comment

Comments

@aso538
Copy link

aso538 commented Dec 6, 2022

Thank you very much for your open source. But when I reproduce the inference precision, when I use the model provided by the official, the inference precision is inconsistent with that given in readme. What is the reason.

i use the LeViT-256 Acc@1 81.584 Acc@5 95.464 loss 0.745

@btgraham
Copy link
Contributor

btgraham commented Dec 6, 2022

The accuracy of any machine learning model will vary slightly between CPU and GPU, and between different versions of PyTorch, CUDNN, etc, due to numerical rounding errors. Unless the change in performance is large, this is to be expected.

@btgraham btgraham closed this as completed Dec 6, 2022
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants