Commit Graph

6 Commits (4841933454077880198213d58760e345608878db)

Author SHA1 Message Date
MengzhangLI f3ae2342eb
[Enchance] Support random seed for distributed sampler (#1411)
* support random seed for distributed sampler

* move mmseg/utils/dist_util.py to mmseg/core/utils/dist_util.py

* move mmseg/utils/dist_util.py to mmseg/core/utils/dist_util.py

* change dist sampler

* change dist sampler

* fix docstring in sync_random_seed
2022-03-28 23:50:39 +08:00
MengzhangLI 7ddd2fe2ec
[Feature] Support ConvNext (#1216)
* upload original backbone and configs

* ConvNext Refactor

* ConvNext Refactor

* convnext customization refactor with mmseg style

* convnext customization refactor with mmseg style

* add ade20k_640x640.py

* upload files for training

* delete dist_optimizer_hook and remove layer_decay_optimizer_constructor

* check max(out_indices) < num_stages

* add unittest

* fix lint error

* use MMClassification backbone

* fix bugs in base_1k

* add mmcls in requirements/mminstall.txt

* add mmcls in requirements/mminstall.txt

* fix drop_path_rate and layer_scale_init_value

* use logger.info instead of print

* add mmcls in runtime.txt

* fix f string && delete

* add doctring in LearningRateDecayOptimizerConstructor and fix mmcls version in requirements

* fix typo in LearningRateDecayOptimizerConstructor

* use ConvNext models in unit test for LearningRateDecayOptimizerConstructor

* add unit test

* fix typo

* fix typo

* add layer_wise and fix redundant backbone.downsample_norm in it

* fix unit test

* give a ground truth lr_scale and weight_decay

* upload models and readme

* delete 'backbone.stem_norm' and 'backbone.downsample_norm' in get_num_layer()

* fix unit test and use mmcls url

* update md2yml.py and metafile

* fix typo
2022-03-04 15:52:01 +08:00
Junjun2016 441be4e435
[Dcos] Add header for files (#796)
* Add header for files

* Delete header in config files
2021-08-16 23:16:55 -07:00
Jerry Jiarui XU f95079ba8a
[Enhance] Migrate to MMCV DepthwiseSeparableConv (#158)
* Add D16-MG124 models

* Use MMCV DepthSepConv

* add OHEM

* add warmup

* fixed test

* fixed test

* change to bs 16

* revert config

* add models

* seperate
2020-09-25 19:56:10 +08:00
Jerry Jiarui XU 1765c12985
Support FP16 (#21)
* Support FP16

* add miss folder

* add tests

* remove useless config

* update memory

* reduce config

* migrate fp16 to mmcv

* add model link
2020-07-20 15:17:18 +08:00
Jiarui XU b2724da80b init commit 2020-07-10 02:39:01 +08:00