support coco stuff-10k/164k #625
Conversation
DerrickWang005
commented
Jun 22, 2021
•
DerrickWang005
commented
- Conversion scripts of Coco Stuff-10k/164k.
- Guideline of the dataset preparation.
- Dataset file of Coco Stuff-10k/164k.
- Four configurations of PSPNet on Coco Stuff-10k/164k.
Codecov Report
@@ Coverage Diff @@
## master #625 +/- ##
==========================================
- Coverage 89.05% 89.05% -0.01%
==========================================
Files 111 112 +1
Lines 6051 6060 +9
Branches 969 970 +1
==========================================
+ Hits 5389 5397 +8
- Misses 467 468 +1
Partials 195 195
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
|
Hi @DerrickWang005 |
|
You are welcome. :) |
| if args.out_dir is None: | ||
| out_mask_dir = osp.join(coco_path, 'masks') | ||
| else: | ||
| out_mask_dir = args.out_dir |
There was a problem hiding this comment.
Refactor it according to coco stuff 10k
|
Hi @DerrickWang005 |
fix the description of the dataset
fix the doc tree of coco stuff 10k
fix img_dir
|
COCO-Stuff 164k results: |
|
COCO-Stuff 10k results: |
|
Task linked: CU-1f0zypv coco-stuff dataset |
|
Add coco stuff in README.md |
|
Update supported datasets in README.md. |
|
Can this be merged in the near future? |
This month. |
mmseg/datasets/coco_stuff.py
Outdated
| [192, 64, 128], | ||
| [64, 192, 96], | ||
| [64, 160, 64], | ||
| [64, 64, 0], |
There was a problem hiding this comment.
| [64, 64, 0], | |
| [64, 64, 0] |
* support coco stuff-10k/164k * update docs * fix docs * update docs * fix import lints * Update docs/dataset_prepare.md * Update docs/dataset_prepare.md * Update tools/convert_datasets/coco_stuff164k.py * Update tools/convert_datasets/coco_stuff10k.py * Update tools/convert_datasets/coco_stuff10k.py * Update tools/convert_datasets/coco_stuff10k.py * Update tools/convert_datasets/coco_stuff10k.py * Update coco_stuff.py fix the description of the dataset * Update dataset_prepare.md fix the doc tree of coco stuff 10k * Update coco_stuff10k.py fix img_dir * Update coco_stuff.py fix descriptions * Update coco_stuff164k.py fix out_dir * Update coco_stuff10k.py fix save file name * Update coco_stuff.py fix seg_map_suffix * Update dataset_prepare.md fix -p * Update dataset_prepare.md fix doc tree * modify coco stuff convertor * Remove redundant code * fix 164k convert bug * remove redundant comment * add deeplabv3 configs and more iterations * replace shutil.move with shtil.copyfile * Update deeplabv3_r50-d8_512x512_4x4_80k_coco_stuff10k.py fix wrong config * Update deeplabv3_r101-d8_512x512_4x4_80k_coco_stuff164k.py fix wrong config * fix wrong configs * fix wrong configs * fix wrong path for coco stuff 10k * fix convert bugs * fix seg_filename bug * when nproc=0, use track progress * rename configs: coco_stuff --> coco-stuff * add coco-stuff 10k and 164k to README.md * update configs * add deeplabv3 benchmark * add pspnet benchmark * remove redundant comma Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
|
Hi @DerrickWang005 ！First of all, we want to express our gratitude for your significant PR in this project. Your contribution is highly appreciated, and we are grateful for your efforts in helping improve this open-source project during your personal time. We believe that many developers will benefit from your PR. We would also like to invite you to join our 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 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：） |
* [Improvement] Support non-sparse(one-hot like) label for CrossEntropyLoss * fix * update changelog * detect loss from the shape of label * update docs * fix unittest, use almost equal instead of equal * rename `non-sparse label` to `soft label` * fix lint * fix test * rename sparse to hard, add assert for kwargs * update docs * update docs
