Add parameters to make custom backbone for detr #14933
Conversation
| @@ -155,6 +155,10 @@ def __init__( | |||
| bbox_loss_coefficient=5, | |||
| giou_loss_coefficient=2, | |||
| eos_coefficient=0.1, | |||
| in_chans=3, | |||
There was a problem hiding this comment.
| in_chans=3, | |
| num_channels=3, |
I would rename this to num_channels to be consistent with other models in the library (like ViT).
| @@ -155,6 +155,10 @@ def __init__( | |||
| bbox_loss_coefficient=5, | |||
| giou_loss_coefficient=2, | |||
| eos_coefficient=0.1, | |||
| in_chans=3, | |||
| pretrained=True, | |||
There was a problem hiding this comment.
| pretrained=True, | |
| use_pretrained_backbone=True, |
This can be renamed to use_pretrained_backbone, for clarity.
| @@ -155,6 +155,10 @@ def __init__( | |||
| bbox_loss_coefficient=5, | |||
| giou_loss_coefficient=2, | |||
| eos_coefficient=0.1, | |||
| in_chans=3, | |||
| pretrained=True, | |||
| freeze_layers=True, | |||
There was a problem hiding this comment.
I would leave away this one, as there's already a method one can call on DetrModel, called freeze_backbone as seen here.
Maybe we can improve its documentation for visibility.
There was a problem hiding this comment.
I think this parameter is more specific, it disables freezing 2-4 layer of resnet-50 (this was just hard coded into encoder initialisation), but I can change it if you think freeze_backbone is better anyway
| in_chans=3, | ||
| pretrained=True, | ||
| freeze_layers=True, | ||
| fix_batch_norm=True, |
There was a problem hiding this comment.
What's the reason you want to replace the frozen batch norm layers?
There was a problem hiding this comment.
Training from scratch, I want to try training from fully randomly initialised model. Also I don't have pretrained backbone for my problem anyway, so I think this parameter won't harm
Zhylkaaa
force-pushed
the
add_chans_detr
branch
from
17a2e7b to
23986a3
Compare
|
This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread. Please note that issues that do not follow the contributing guidelines are likely to be ignored. |
What does this PR do?
Added few parameters to be able to create custom backbone models for different use cases (partially explained in mentioned issue)
Closes #14875
Before submitting
Pull Request section?
to it if that's the case.
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.
Maybe @LysandreJik can help with review?