8000 [WIP] [Feature] Refactor assigner and sampler by BIGWangYuDong · Pull Request #9518 · open-mmlab/mmdetection · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

[WIP] [Feature] Refactor assigner and sampler #9518

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

Draft
wants to merge 1 commit into
base: dev-3.x
Choose a base branch
from

Conversation

BIGWangYuDong
Copy link
Collaborator

Refactor AssignerResult and SamplingResult.

  • keep AssignerResult and SamplingResult have the same logic, which means can deprecate pseudo sampler
  • the input of SamplingResult changed to InstanceData, which can have better scalability, (can deprecate MaskSamplingResult)
  • Use AvoidCUDAOOM instead of assign_on_cpu in assigner

@ZwwWayne ZwwWayne added this to the 3.0.0rc6 milestone Dec 26, 2022

self.pos_assigned_gt_inds = pred_instances.gt_inds[pos_inds] - 1

def update_sampling_result(self,
Copy link
Member

Choose a reason for hiding this comment

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

This logic should be placed in the sampler, instead of in a method of the AssignResult.

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.

4 participants
0