-
Notifications
You must be signed in to change notification settings - Fork 2.6k
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
[Feature] Support K-Net #1289
[Feature] Support K-Net #1289
Conversation
Codecov Report
@@ Coverage Diff @@
## master #1289 +/- ##
==========================================
+ Coverage 90.32% 90.39% +0.06%
==========================================
Files 132 133 +1
Lines 7699 7879 +180
Branches 1290 1316 +26
==========================================
+ Hits 6954 7122 +168
- Misses 531 534 +3
- Partials 214 223 +9
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
Add ep3,4,5. |
Could anyone @ZwwWayne for code review? Thx in advance. |
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
might add readme file and metafile
configs/knet/knet_s3_upernet_swin-l_8x2_512x512_adamw_80k_ade20k.py
Outdated
Show resolved
Hide resolved
configs/knet/knet_s3_upernet_swin-l_8x2_640x640_adamw_80k_ade20k.py
Outdated
Show resolved
Hide resolved
configs/knet/knet_s3_upernet_swin-t_8x2_512x512_adamw_80k_ade20k.py
Outdated
Show resolved
Hide resolved
Tensor: The output tensor of shape | ||
(self.num_classes(KernelUpdateHead) * self.in_channels(KernelUpdateHead)/ in_channels, kernel size * kernel size, in_channels). # noqa |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Tensor: The dynamic kernel with shape ()?
is there any short description for the shape of the dynamic kernel? @MengzhangLI @ZwwWayne
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Something like: 'The dynamic kernel with shape (N, C), where N is the number of classes, C is the feature map channels'?
* knet first commit * fix import error in knet * remove kernel update head from decoder head * [Feature] Add kenerl updation for some decoder heads. * [Feature] Add kenerl updation for some decoder heads. * directly use forward_feature && modify other 3 decoder heads * remover kernel_update attr * delete unnecessary variables in forward function * delete kernel update function * delete kernel update function * delete kernel_generate_head * add unit test & comments in knet.py * add copyright to fix lint error * modify config names of knet * rename swin-l 640 * upload models&logs and refactor knet_head.py * modify docstrings and add some ut * add url, modify docstring and add loss ut * modify docstrings
* knet first commit * fix import error in knet * remove kernel update head from decoder head * [Feature] Add kenerl updation for some decoder heads. * [Feature] Add kenerl updation for some decoder heads. * directly use forward_feature && modify other 3 decoder heads * remover kernel_update attr * delete unnecessary variables in forward function * delete kernel update function * delete kernel update function * delete kernel_generate_head * add unit test & comments in knet.py * add copyright to fix lint error * modify config names of knet * rename swin-l 640 * upload models&logs and refactor knet_head.py * modify docstrings and add some ut * add url, modify docstring and add loss ut * modify docstrings
…pen-mmlab#1289) * fix non square images with UNet2DModel and DDIM/DDPM pipelines * fix unet_2d `sample_size` docstring * update pipeline tests for unet uncond Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Re-implementing K-Net.
Original paper: https://arxiv.org/abs/2106.14855.
Original repo:https://github.com/ZwwWayne/K-Net.
Results on ADE20K