* Add  save_best option in eval_hook.

* Update meta to fix best model can not test bug

* refactor with _do_evaluate

* remove redundent

* add meta

Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com>

* [Feature] Add results2img, format_results for ade dataset.

* clean rebundant code.

* Add arg: final_reshape to control if converting output feature information from NLC to NCHW;

* Fix the default value of final_reshape;

* Modify arg: final_reshape to arg: out_shape;

* Fix some unit test bug;

* mmcv eval hook

* mmcv evalhook compatible

* add warnings

* inherit from base class

* fix unitest

* adapt to mmcv 1.3.1

* fixed unittest

* set by_epoch=False

* fixed efficient test

* update docstring

Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com>

* add mFscore and refactor the metrics return value

* fix linting

* some docstring and name fix

* Adjust vision transformer backbone architectures;

* Add DropPath, trunc_normal_ for VisionTransformer implementation;

* Add class token buring intermediate period and remove it during final period;

* Fix some parameters loss bug;

* * Store intermediate token features and impose no processes on them;

* Remove class token and reshape entire token feature from NLC to NCHW;

* Fix some doc error

* Add a arg for VisionTransformer backbone to control if input class token into transformer;

* Add stochastic depth decay rule for DropPath;

* * Fix output bug when input_cls_token=False;

* Add related unit test;

* * Add arg: out_indices to control model output;

* Add unit test for DropPath;

* Apply suggestions from code review

Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>

* support reading class_weight from file in loss function

* add unit test of loss with class_weight from file

* minor fix

* move get_class_weight to utils

* remove dict calling img key for compatibility

* fix unit test

* infer batch size using len(result) to be consistent with mmcv

* [Refactor] Use MMCV MODEL_REGISTRY

* fixed args

* init

* upsample v1.0

* fix errors

* change to in_channels list

* add unittest, docstring, norm/act config and rename

Co-authored-by: xiexinch <test767803@foxmail.com>

* vit backbone

* fix lint

* add docstrings and fix pretrained pos_embed dim not match prob

* add unittest for vit

* fix lint

* add vit based fcn configs

* fix import error

* support multiple resolution input images

* upsample pos_embed at init_weights

* support resize pos_embed at evaluation

* fix training errors

* add more unitest code for vit backbone

* unitest for uncovered code

* add norm_eval unittest

* refactor _pos_embeding

* minor change

* change var name

* rafactor init_weight

* load weights after resize

* ignore 'module' in pretrain checkpoint

* add with_cp

* add with_cp

Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com>

* Add support for Pascal Context 59 classes (#459)

* Create PascalContextDataset59 class in mmseg/datasets/pascal_context.py;

* Set reduce_zero_label=True for train_pipeline and PascalContextDataset59;

* Add some configs for Pascal-Context 59 classes training and testing;

* Try to solve the problem about "fence(IoU)=nan grass(IoU)=0";

* Continue(1): Try to solve the problem about "fence(IoU)=nan grass(IoU)=0";

* ignore files and folders named tempxxx;

* Continue(2): Try to solve the problem about "fence(IoU)=nan grass(IoU)=0";

* Modify the calculation of IoU;

* Modify the CLASSES order of PascalContextDataset;

* Add "fcn", "deeplabv3", "deeplabv3+", "pspnet" config file for model training based on PascalContextDataset59;

Add some ignore items in ".gitignore";

* fix the bug "test_cfg specified in both outer field and model field " of pspnet config file;

* * Clean unnecessary codes;

* Add weighs link, config link, log link and evaluation results about PascalContextDataset59 in README.md

* Add command line argument: "-p | --port", this arg can change the transmit port when you transmit data to distributed machine.

* * Remove rebundant config files;

* Remove "-p|--port" command argument;

Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com>

* Fix fence(IoU) = 0 when training on PascalContextDataset59;

* Add a test case in test_metrics() of tests/test_metrics.py to test the bug caused by torch.histc;

* Update tests/test_metrics.py

Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>

Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>

* add dynamic export and visualize to pytorch2onnx

* update document

* fix lint

* fix dynamic error and add visualization

* fix lint

* update docstring

* update doc

* Update help info for --show

Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>

* fix lint

Co-authored-by: maningsheng <maningsheng@sensetime.com>
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>

* add more CI

* fix missing

* remove python-version

* fixed acc

* refactor test organization

* fixed se layer

* update mmcv uper bound

Signed-off-by: lizz <lizz@sensetime.com>

* Fix typo: upsampe_cfg -> upsample_cfg

Signed-off-by: lizz <lizz@sensetime.com>

* convoluton -> convolution

Signed-off-by: lizz <lizz@sensetime.com>

* more

Signed-off-by: lizz <lizz@sensetime.com>

* ok

Signed-off-by: lizz <lizz@sensetime.com>

* Include each class metrics in logs

* format

* fix the unitest

* fix the custom int class_name

* fix the custom int class_name

* fix training bugs

* fix unitest error

* fix error in num_classes==2 case

* delete comments

* pytorch metrics impl and test

* support list[str] input, delete unused test code and delete numpy version

* modify input data type

* add docstring and unitest of filename inputs

* add indents in docstring and use tempfile lib to create dir

* using with statement

* Support fcn dilate 6

* Support dilate in FCNHead

* configs for cityscapse dataset

* add configs for pytorch pretrained model

* update README

* add fps test results

* add memory test results and links

* modify log names

* Update mmseg/models/decode_heads/fcn_head.py

Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>

* dice loss

* format code, add docstring and calculate denominator without valid_mask

* minor change

* restore

* bump to v0.11

* update readme

* [Bug fix] Fixed ADE20k test

* fixed ade cfg

* [Improvement] Move train_cfg/test_cfg inside model

* fixed config dict

* fixed config dict

* add lovasz loss

* Modify as comments

* Modify paper url

* add unittest and remove Var

* impove unittest

* memory efficient test

* implement efficient test

* merge

* Add document and docstring

* fix unit test

* add memory usage report

* fix tta bug

* modify as suggested

* fix test_tta bug

* Bump to v0.10

* change version

* delete markdownlint

* Support MobileNetV3

* fix import

* add mobilenetv3 head and configs

* Modify MobileNetV3 to semantic segmentation version

* modify mobilenetv3 configs

* add std configs

* fix Conv2dAdaptivePadding bug

* add configs

* add unitest and fix bugs

* fix lraspp unitest bugs

* restore

* fix unitest

* add MobileNetV3 docstring

* add mmcv

* add mmcv

* fix syntax bug

* fix unitest bug

* fix unitest bug

* fix unitest bugs

* fix docstring

* add configs

* restore

* delete unnecessary assert

* modify unitest

* delete benchmark

* Support DMNet

* fix doc and delete norm_name