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

使用这个Forward框架进行推断的时候会有精度损失吗？ #10

Closed
dgl547437235 opened this issue Apr 28, 2021 · 6 comments
Closed

使用这个Forward框架进行推断的时候会有精度损失吗？ #10

dgl547437235 opened this issue Apr 28, 2021 · 6 comments
Labels
question Further information is requested Stale

Comments

@dgl547437235
Copy link

No description provided.

@yuanzexi
Copy link
Collaborator

@dgl547437235 FLOAT 推理模式下基本无损失；而 HALF 和 INT8 的推理模式下，因数据类型原因定会存在一定的精度损失。由于最终是以 TensorRT 的推理引擎进行推理，所以详细精度损失情况，可参考 TensorRT。

@Fan9
Copy link

Fan9 commented Apr 29, 2021

NLP的Bert分类模型测试，float 32 精度没有损失。Half和INT8暂时还没测

@yuanzexi yuanzexi added the question Further information is requested label May 18, 2021
@Fan9
Copy link

Fan9 commented May 24, 2021

Bert的float 16也测过了，1000条样本的F1没有损失，可能也和具体任务有关

@yuanzexi
Copy link
Collaborator

@Fan9 感谢反馈！~

@github-actions
Copy link

This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 5 days.

@github-actions github-actions bot added the Stale label Jun 24, 2021
@github-actions
Copy link

This issue was closed because it has been stalled for 5 days with no activity.

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

No branches or pull requests
3 participants
@yuanzexi @dgl547437235 @Fan9