-
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] Add MultiImageMixDataset #1105
Conversation
* remove dynamic_scale & add palette * modify retrieve_data_cfg method * modify retrieve_data_cfg func
Codecov Report
@@ Coverage Diff @@
## master #1105 +/- ##
==========================================
+ Coverage 89.57% 90.03% +0.45%
==========================================
Files 120 125 +5
Lines 6717 7314 +597
Branches 1122 1219 +97
==========================================
+ Hits 6017 6585 +568
- Misses 496 524 +28
- Partials 204 205 +1
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
Hi, @lkm2835 thanks for your pr. We would review it ASAP. Best, |
Okay I see . We will do some tests with and without Mosaic. Please note that our custom dataset has a few noises in annotation. |
Please improve the unittests coverage. |
Can browse more images and label annotations to check the correctness of mosaic augmentation. |
Hi @RockeyCoss |
We made changes you requested. And I browsed about 100 images and annotations and they seemed all fine :) |
Thanks for your hard work. |
Thanks for your contribution. I will combine it with Mosaic data augmentation and do some experiments. |
When it merged with Mosaic, it will be easy to improve the unittests coverage. |
Sorry for taking so late. I brought some results below.
We have done different img scales test for Mosaic augmentation as well, but 512x512 showed best performance. (Mosaic prob =1.0)
According to test results, Mosaic augmentation seems to show better performance on a few label images. |
What's the best result on your custom dataset (SOTA)? |
The best result is 0.5814 ,which is 512x512 img scale for Mosaic(prob=1) augmentation. Here is config script for more detail.
(segformer_mit-b0_512x512) |
I mean the best result you got before. |
Oh I see. Unfortunately, now we only have the best result which had been applied many tricks(due to competition),so it is hard to tell the best result of the model itself. We will do test right away with same condition as before . |
That may not be a good data augmentation strategy for segmentation. |
So we are just using SOTA model(without any tricks) we used and doing some augmentation tests only. |
Make sense. |
Here's some results we have done.
Actually, we did several more tests such as without crop, changing center ratio, img scale etc . |
Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
* Fix typo in usage example * original MultiImageMixDataset code in mmdet * Add MultiImageMixDataset unittests in test_dataset_wrapper * fix lint error * fix value name ann_file to ann_dir * modify retrieve_data_cfg (#1) * remove dynamic_scale & add palette * modify retrieve_data_cfg method * modify retrieve_data_cfg func * fix error * improve the unittests coverage * fix unittests error * Dataset (#2) * add cfg-options * Add unittest in test_build_dataset * add blank line * add blank line * add a blank line Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com> Co-authored-by: Younghoon-Lee <72462227+Younghoon-Lee@users.noreply.github.com> Co-authored-by: MeowZheng <meowzheng@outlook.com> Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
Modification
mmseg/datasets/builder.py
: Add (if cfg['type'] == 'MultiImageMixDataset'])mmseg/datasets/dataset_wrappers.py
: Add class MultiImageMixDatasettests/test_data/test_dataset.py
: Add unittestsUse cases (Optional)
use case in mmdet
Original code: MultiImageMixDataset in mmdet
Related: Issue#1045, Pull Request#1093