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.

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

Multi box loss #6946

Closed
wants to merge 4 commits into from
Closed

Conversation

wanghaox
Copy link
Contributor

resolve #6818

set_constant(cpu_ctx, &d_loc_cpu, 0);
set_constant(cpu_ctx, &d_conf_cpu, 0);
loc_offset +=
math::TransposeFromNHWCToNCHW<platform::CPUDeviceContext, T>(
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

TransposeFromNHWCToNCHW好像是可以用GPU的。
用GPU transpose之后再copyfrom到cpu进行接下来的计算是不是更合理一些

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

这里原始实现有些晦涩,主要考虑到data layout,如果用tensor表示,而不是matrix,可能要简单一些

@paddle-bot-old paddle-bot-old bot closed this May 22, 2020
@paddle-bot-old
Copy link

Since you haven't replied for a long time, we have closed this issue/pr.
If the problem is not solved or there is a follow-up one, please reopen it at any time and we will continue to follow up.
由于您长期未回复,我们将关闭这个issue/pr。
若问题未解决或有后续问题,请随时重新打开,我们会继续跟进。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

MultiBox Loss Operator.
3 participants