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

Improving experiment configuration #1294

Open
wants to merge 8 commits into
base: master
Choose a base branch
from

Conversation

demmerichs
Copy link

This PR is addressing #1278.
I use this myself and be happy to address any problems or issues.
If this kind of change is not wanted, please let me know why :)

@jihanyang
Copy link
Collaborator

Hello, thanks for your effort. Could you provide some examples?

@demmerichs
Copy link
Author

Thanks for considering my contribution @jihanyang .
With the last commit 9bc206c I refactored the Waymo MPPNet configuration and added a test script in order to demonstrate that it does not change any configurations.

The output is

124c124
< TAG: mppnet
---
> TAG: mppnet_4frames
124c124
< TAG: mppnet_4frames
---
> TAG: mppnet__4frames
124c124
< TAG: mppnet_16frames
---
> TAG: mppnet__16frames
52c52
<   _BASE_CONFIG_: cfgs/dataset_configs/waymo_dataset_multiframe.yaml
---
>   _BASE_CONFIG_: cfgs/dataset_configs/modifiers/waymo/multiframe.yaml
182c182
< TAG: mppnet_e2e_memorybank_inference
---
> TAG: mppnet__e2e_memorybank_inference
52c52
<   _BASE_CONFIG_: cfgs/dataset_configs/waymo_dataset_multiframe.yaml
---
>   _BASE_CONFIG_: cfgs/dataset_configs/modifiers/waymo/multiframe.yaml
143c143
<     TRANS_INPUT: 256
---
>     TRANS_INPUT: 64
148c148
<       hidden_dim: 256
---
>       hidden_dim: 64
181c181
< TAG: mppnet_e2e_memorybank_inference_16frames
---
> TAG: mppnet__e2e_memorybank_inference__16frames

The mppnet_e2e_memorybank_inference_16frames configuration differs in TRANS_INPUT and hidden_dim, however, I created the baseline based on instructions inside the original mppnet_e2e_memorybank_inference config. I am not sure if this change was perhaps just not correctly documented, and as the configuration was not provided anyway, I would keep it as is, and add another commit to remove the test script again, and the original mppnet configuration files.

@OpenMMLab-Assistant-007

Hi
@demmerichs
We are grateful for your efforts in helping improve this open-source project during your personal time.
Welcome to join OpenMMLab Special Interest Group (SIG) private channel on Discord, where you can share your experiences, ideas, and build connections with like-minded peers. To join the SIG channel, simply message moderator— OpenMMLab on Discord or briefly share your open-source contributions in the #introductions channel and we will assist you. Look forward to seeing you there! Join us :https://discord.gg/UjgXkPWNqA
If you have a WeChat account,welcome to join our community on WeChat. You can add our assistant :openmmlabwx. Please add "mmsig + Github ID" as a remark when adding friends:)
Thank you again for your contribution❤

@demmerichs
Copy link
Author

Just did a rebase, in case this should be cleanly merged in the future!

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