Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

0.2.0版本tiny模型推理比0.1.6版本UniMERNet模型推理还要慢 #39

Open
arthursunbao opened this issue Nov 5, 2024 · 1 comment
Open

0.2.0版本tiny模型推理比0.1.6版本UniMERNet模型推理还要慢 #39

arthursunbao opened this issue Nov 5, 2024 · 1 comment

Comments

@arthursunbao
Copy link

如题，在L20上跑的
0.1.6 UniMERNet模型大致为800ms
0.2.0 tiny需要1200ms
@Salvatore-Love
Copy link
Collaborator

您能提供一些更加具体的信息吗。如果是对单个样本容易出现这样的偏差，比如不同模型输出长度不同，耗时情况也会不同。我们评测时是固定模型输出长度来测试模型的平均推理速度。另外关于测试的一些细节可以参考https://github.com/opendatalab/UniMERNet/issues/22

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@arthursunbao @Salvatore-Love