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] Add UNet benchmark with multiple losses supervision. #1143
Conversation
Codecov Report
@@ Coverage Diff @@
## master #1143 +/- ##
==========================================
- Coverage 90.11% 90.07% -0.04%
==========================================
Files 125 125
Lines 7262 7268 +6
Branches 1206 1206
==========================================
+ Hits 6544 6547 +3
- Misses 515 518 +3
Partials 203 203
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
Should rename the title to descript this PR in more detail. |
Should not override the previous results. |
0e2885f
to
51e0cbd
Compare
Should resolve this comment. :) |
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.
The config with multiple losses can inherit from the config with only CE loss.
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.
LGTM
…mlab#1143) * upload models and new configs * fix hrf readme error * fix hrf readme error * add mDice of old models * refactor configs
mutli GPU support
* add cam runner [wip] * update webcam runner and node api * reorganize module structure * add model node * add pose model node [wip] * update message * add monitor node * rename config * refactor webcam util * add update_route_info * add input_check_interval * add fps for one-euro in mmpose node * refactor visualition nodes * fix bug * modify runner argument and fix bug * add doc * add doc * add webcam_runner docstrings * add docstrings * update interface and docstring * add RecorderNode * * add syncrhonous result binding mode * refactor node event handler * fix typing * fix typing (open-mmlab#1082) * * Add RecorderNode for saving video to files * Add exiting handler method to nodes * Add VideoEndingMessage * rename _on_exit ot on_exit * fix typing * Fix a few issues * register node event handler in __init__ * change default pose model to vipnas_mblv3 * Node._on_exit -> Node.on_exit * fix typing * fix typing * change from thread based to process based * solve cuda distributed [wip] * fix process creating method and buffer size * thread based buffer * node based on thread * node set daemon=False as default * fix logging level and add docstrings * modify register_event * * reorganize webcam tool configs * modify frame rate calculation * rename BillboardNode as NoticeBoardNode * [WebcamAPI] Add demo README (open-mmlab#1133) * add README.md * update gif * [WebcamAPI] Add facwswap node and config (open-mmlab#1094) * add facwswap node * adapt to webcam_api * adapt to webcam_api * move config * add sync mode in runner * fix bugs and update nodes * [WebcamAPI] Supersaiyan (open-mmlab#1098) * add supersaiyan effects * fix init * apply background * update config * apply saiyan effects * rebase * rebase and fix * update doc * update docs * add load image from disk or url * make the resources to url links * mv load_image_from_disk_or_url to utils/misc * move effect funcs to webcam_api * rebase * fix pytest * fix docs * add get_local_path_given_url * add get_local_path_given_url * rename to get_cached_file_path * update readme * update readme * fix bug that only one bbox is detected for each class * fix faceswap config * add newyear demo (open-mmlab#1143) Co-authored-by: zengwang <zengwang430521@gmail.com> * [Feature] Add a `SpriteNode` for Webcam API (open-mmlab#1160) * Fix missing flag in `load_image_from_disk_or_url` * Add SpriteNode * Meow dwen dwen (open-mmlab#1173) * fix mmpose nodes * add dummy video capture * add xdwendwen node * fix configs * Update README.md * [WebcamAPI] Update XDwenDwen example (open-mmlab#1177) * Update XDwenDwen example * add rigid transform * update configs and readme files * extend meow dwen dwen * update config * support cfg-options * turn-off default help instruction * fix typo Co-authored-by: Jas <jinsheng@sensetime.com> Co-authored-by: Lumin <30328525+luminxu@users.noreply.github.com> Co-authored-by: zengwang <zengwang430521@gmail.com> Co-authored-by: Ma Zerun <mzr1996@163.com>
Motivation
To improve numerical results of UNet benchmark, using multiple losses (1.0 * cross entropy loss + 3.0 * dice loss) is introduced in this pr.
To testify representation ability of UNet on natural image, benchmark of UNet on Cityscapes dataset is also added in this pr.
Note
(1) For
DRIVE
,STARE
,CHASE_DB1
andHRF
, using multiple losses (dice vs cross entropy is 3:1).(2) Add cityscapes benchmark.
CrossEntropyLoss
only and using multiple losses withCrossEntropyLoss
andDiceLoss
.mDice
results of existing usingCrossEntropyLoss
only models.