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

[Refactor] Refactor Deploy Code #2881

Merged
merged 5 commits into from
Jan 3, 2023

Conversation

Bobholamovic
Copy link
Member

@Bobholamovic Bobholamovic commented Dec 29, 2022

PR types

Others

PR changes

APIs

Description

  1. 重构部署部分,将公共数据结构与函数放置在 PaddleSeg 库核心代码中,以便于不同脚本复用。
  2. 解决 [Enhancement] Refine User Scripts #2849 导致的量化脚本执行出错问题。
  3. 将 UHRNet 和 RTFormer 的 TIPC config 中的 train.py 替换为 tools/train.py
  4. ConfigChecker 类添加 add_rule 接口,以便从外部追加规则。
  5. 修正 README 中语法和格式错误。

zhengya01
zhengya01 previously approved these changes Dec 29, 2022
"please set --enable_auto_tune=True to use auto_tune. \n")
exit()

if hasattr(args, 'benchmark') and args.benchmark:
Copy link
Collaborator

Choose a reason for hiding this comment

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

可以把这个auto_log删掉,没什么用,搞得逻辑还很复杂。

Copy link
Member Author

Choose a reason for hiding this comment

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

这个auto_log估计还不能删掉,因为所有的 TIPC benchmark 链条都依赖这个库的输出日志

Copy link
Collaborator

@juncaipeng juncaipeng left a comment

Choose a reason for hiding this comment

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

LGTM

@juncaipeng juncaipeng merged commit 8645221 into PaddlePaddle:develop Jan 3, 2023
@Bobholamovic Bobholamovic deleted the fix/deploy branch January 3, 2023 06:21
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.

3 participants