Pre release by xvjiarui · Pull Request #1 · open-mmlab/mmsegmentation

xvjiarui · 2020-06-14T08:32:54Z

No description provided.

* 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>

* 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> * [Fix] Add MultiImageMixDataset unittests 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>

* segmenter: add model * update * readme: update * config: update * segmenter: update readme * segmenter: update * segmenter: update * segmenter: update * configs: set checkpoint path to pretrain folder * segmenter: modify vit-s/lin, remove data config * rreadme: update * configs: transfer from _base_ to segmenter * configs: add 8x1 suffix * configs: remove redundant lines * configs: cleanup * first attempt * swipe CI error * Update mmseg/models/decode_heads/__init__.py Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn> * segmenter_linear: use fcn backbone * segmenter_mask: update * models: add segmenter vit * decoders: yapf+remove unused imports * apply precommit * segmenter/linear_head: fix * segmenter/linear_header: fix * segmenter: fix mask transformer * fix error * segmenter/mask_head: use trunc_normal init * refactor segmenter head * Fetch upstream (#1) * [Feature] Change options to cfg-option (#1129) * [Feature] Change option to cfg-option * add expire date and fix the docs * modify docstring * [Fix] Add  in metafile #1127 * [Fix] Fix correct num_classes of HRNet in LoveDA dataset #1136 * Bump to v0.20.1 (#1138) * bump version 0.20.1 * bump version 0.20.1 * [Fix] revise --option to --options #1140 Co-authored-by: Rockey <41846794+RockeyCoss@users.noreply.github.com> Co-authored-by: MengzhangLI <mcmong@pku.edu.cn> * decode_head: switch from linear to fcn * fix init list formatting * configs: remove variants, keep only vit-s on ade * align inference metric of vit-s-mask * configs: add vit t/b/l * Update mmseg/models/decode_heads/segmenter_mask_head.py Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com> * Update mmseg/models/decode_heads/segmenter_mask_head.py Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com> * Update mmseg/models/decode_heads/segmenter_mask_head.py Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com> * Update mmseg/models/decode_heads/segmenter_mask_head.py Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com> * Update mmseg/models/decode_heads/segmenter_mask_head.py Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com> * model_converters: use torch instead of einops * setup: remove einops * segmenter_mask: fix missing imports * add necessary imported init funtion * segmenter/seg-l: set resolution to 640 * segmenter/seg-l: fix test size * fix vitjax2mmseg * add README and unittest * fix unittest * add docstring * refactor config and add pretrained link * fix typo * add paper name in readme * change segmenter config names * fix typo in readme * fix typos in readme * fix segmenter typo * fix segmenter typo * delete redundant comma in config files * delete redundant comma in config files * fix convert script * update lateset master version Co-authored-by: MengzhangLI <mcmong@pku.edu.cn> Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn> Co-authored-by: Rockey <41846794+RockeyCoss@users.noreply.github.com> 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 (open-mmlab#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 (open-mmlab#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>

* 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 (open-mmlab#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 (open-mmlab#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> * [Fix] Add MultiImageMixDataset unittests 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>

* segmenter: add model * update * readme: update * config: update * segmenter: update readme * segmenter: update * segmenter: update * segmenter: update * configs: set checkpoint path to pretrain folder * segmenter: modify vit-s/lin, remove data config * rreadme: update * configs: transfer from _base_ to segmenter * configs: add 8x1 suffix * configs: remove redundant lines * configs: cleanup * first attempt * swipe CI error * Update mmseg/models/decode_heads/__init__.py Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn> * segmenter_linear: use fcn backbone * segmenter_mask: update * models: add segmenter vit * decoders: yapf+remove unused imports * apply precommit * segmenter/linear_head: fix * segmenter/linear_header: fix * segmenter: fix mask transformer * fix error * segmenter/mask_head: use trunc_normal init * refactor segmenter head * Fetch upstream (open-mmlab#1) * [Feature] Change options to cfg-option (open-mmlab#1129) * [Feature] Change option to cfg-option * add expire date and fix the docs * modify docstring * [Fix] Add  in metafile open-mmlab#1127 * [Fix] Fix correct num_classes of HRNet in LoveDA dataset open-mmlab#1136 * Bump to v0.20.1 (open-mmlab#1138) * bump version 0.20.1 * bump version 0.20.1 * [Fix] revise --option to --options open-mmlab#1140 Co-authored-by: Rockey <41846794+RockeyCoss@users.noreply.github.com> Co-authored-by: MengzhangLI <mcmong@pku.edu.cn> * decode_head: switch from linear to fcn * fix init list formatting * configs: remove variants, keep only vit-s on ade * align inference metric of vit-s-mask * configs: add vit t/b/l * Update mmseg/models/decode_heads/segmenter_mask_head.py Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com> * Update mmseg/models/decode_heads/segmenter_mask_head.py Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com> * Update mmseg/models/decode_heads/segmenter_mask_head.py Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com> * Update mmseg/models/decode_heads/segmenter_mask_head.py Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com> * Update mmseg/models/decode_heads/segmenter_mask_head.py Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com> * model_converters: use torch instead of einops * setup: remove einops * segmenter_mask: fix missing imports * add necessary imported init funtion * segmenter/seg-l: set resolution to 640 * segmenter/seg-l: fix test size * fix vitjax2mmseg * add README and unittest * fix unittest * add docstring * refactor config and add pretrained link * fix typo * add paper name in readme * change segmenter config names * fix typo in readme * fix typos in readme * fix segmenter typo * fix segmenter typo * delete redundant comma in config files * delete redundant comma in config files * fix convert script * update lateset master version Co-authored-by: MengzhangLI <mcmong@pku.edu.cn> Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn> Co-authored-by: Rockey <41846794+RockeyCoss@users.noreply.github.com> Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>

add config file for occlusion face

[FIX] fixing bug in `test_cfg` for U-Net _base_ script

Add glide modeling files

xvjiarui added 30 commits April 1, 2020 17:01

merge mmdet resnet

a3fc8f6

change default to navie syncbn, reformart pretrain

4c5df48

remove work_dir from slurm_train

5313e35

fixed norm import, fixed csaill r101 config

a7afe48

add eval_hook w\o dist

825f12f

make crop and pad together

e9d3d60

add augment ablation

1be3fd6

use ratio range, set norm_mult=0

c651526

add lr_mult, fix aux_head config

7692f14

add ratio option in test_aug

4947a21

add CCNet

6ac9df8

refactor slurm_train

2ac9e17

Merge branch 'master' into ccnet

9354e85

fixed cc head

58ae663

reorder rotate, change psp to syncbn, clean configs

a270d70

Merge branch 'master' into ccnet

c0211aa

fixed lr

e5d3bc1

add psa head

e89bb5d

add optimizer builder

71a54c4

Merge branch 'master' into psanet

9618ee1

fixed psa config

f5230cb

add nonlocal and gcnet

4fd8738

rename ccnet

e916d1f

fixed backward bug

f78db2c

add norm_cfg in NLNet, add FCN

5ce030f

add uper head

558a398

add hrnet

3f793c0

add option in train.py, update requirements

bf0b17a

update docs

b96ce40

make dataset transforms align with mmdet

1a195c7

add data

29f4257

xvjiarui force-pushed the pre-release branch from 493788e to 29f4257 Compare July 5, 2020 16:49

xvjiarui added 6 commits July 6, 2020 16:06

add more doc string

ebb7ca8

fixed ci, delete unused module

7bad7d7

update readme

f231096

update install guide

11907d8

reduce size

d6a6bcd

update ack

d52a863

hellock merged commit a6a5ed7 into open-mmlab:master Jul 7, 2020

UESTC-Liuxin mentioned this pull request Aug 2, 2020

CUDA error: an illegal memory access was encountered #42

Closed

bkbjsd mentioned this pull request Nov 21, 2020

CUDA error: an illegal memory access was encountered #270

Closed

babakbch mentioned this pull request Sep 7, 2021

RuntimeError: CUDA out of memory. #832

Closed

chiba1sonny mentioned this pull request Nov 8, 2021

RuntimeError: CUDA out of memory. Tried to allocate 850.00 MiB (GPU 0; 10.91 GiB total capacity; 8.69 GiB already allocated; 863.44 MiB free; 8.98 GiB reserved in total by PyTorch) #1021

Closed

chenhaiwen mentioned this pull request Nov 25, 2021

ImportError: And RuntimeError: Broken pipe #1077

Closed

uniyushu mentioned this pull request Mar 1, 2022

RuntimeError: CUDA error: an illegal memory access was encountered #1338

Closed

Lsz-20 mentioned this pull request Mar 15, 2022

train errors #1379

Closed

dongbo811 mentioned this pull request Mar 28, 2022

The training is normal, but the verification always fails #1427

Closed

deepakkupanda mentioned this pull request May 26, 2022

ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: -6) #1618

Open

zhiweil20 mentioned this pull request Jun 29, 2022

ValueError: size shape must match input shape. Input is 2D, size is 3 #1719

Closed

MeowZheng pushed a commit that referenced this pull request Nov 11, 2022

Merge pull request #1 from jinwonkim93/face_occlusion

f4022fb

add config file for occlusion face

MeowZheng pushed a commit that referenced this pull request Nov 28, 2022

Merge pull request #1 from smttsp/ISSUE-2337/bug/unet_param

bd87c92

[FIX] fixing bug in `test_cfg` for U-Net _base_ script

GuoPingPan mentioned this pull request Feb 16, 2023

Binary Segmentation Error when using out_channls = 1 with segmentation model stdc #2607

Closed

3 tasks

xiaoaxiaoxiaocao mentioned this pull request Mar 5, 2023

Help me, binary segmentation acc error! #2628

Closed

aravind-h-v pushed a commit to aravind-h-v/mmsegmentation that referenced this pull request Mar 27, 2023

Merge pull request open-mmlab#1 from huggingface/add-glide

2db090d

Add glide modeling files

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Pre release#1

Pre release#1
hellock merged 260 commits intoopen-mmlab:masterfrom
xvjiarui:pre-release

xvjiarui commented Jun 14, 2020

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

xvjiarui commented Jun 14, 2020

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants