init commit

2025-06-03 22:03:48 +08:00 · 2020-07-07 20:52:19 +08:00 · 2020-07-07 20:52:19 +08:00 · b2724da80b
commit b2724da80b
parent 0032f0b4ed
430 changed files with 20454 additions and 1 deletions
--- a/.dev/clean_models.py
+++ b/.dev/clean_models.py
@ -0,0 +1,125 @@
+import argparse
+import glob
+import json
+import os
+import os.path as osp
+
+import mmcv
+
+# build schedule look-up table to automatically find the final model
+SCHEDULES_LUT = {
+    '20ki': 20000,
+    '40ki': 40000,
+    '60ki': 60000,
+    '80ki': 80000,
+    '160ki': 160000
+}
+RESULTS_LUT = ['mIoU', 'mAcc', 'aAcc']
+
+
+def get_final_iter(config):
+    iter_num = SCHEDULES_LUT[config.split('_')[-2]]
+    return iter_num
+
+
+def get_final_results(log_json_path, iter_num):
+    result_dict = dict()
+    with open(log_json_path, 'r') as f:
+        for line in f.readlines():
+            log_line = json.loads(line)
+            if 'mode' not in log_line.keys():
+                continue
+
+            if log_line['mode'] == 'train' and log_line['iter'] == iter_num:
+                result_dict['memory'] = log_line['memory']
+
+            if log_line['iter'] == iter_num:
+                result_dict.update({
+                    key: log_line[key]
+                    for key in RESULTS_LUT if key in log_line
+                })
+                return result_dict
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(description='Gather benchmarked models')
+    parser.add_argument(
+        'root',
+        type=str,
+        help='root path of benchmarked models to be gathered')
+    parser.add_argument(
+        'config',
+        type=str,
+        help='root path of benchmarked configs to be gathered')
+
+    args = parser.parse_args()
+    return args
+
+
+def main():
+    args = parse_args()
+    models_root = args.root
+    config_name = args.config
+
+    # find all models in the root directory to be gathered
+    raw_configs = list(mmcv.scandir(config_name, '.py', recursive=True))
+
+    # filter configs that is not trained in the experiments dir
+    used_configs = []
+    for raw_config in raw_configs:
+        work_dir = osp.splitext(osp.basename(raw_config))[0]
+        if osp.exists(osp.join(models_root, work_dir)):
+            used_configs.append(work_dir)
+    print(f'Find {len(used_configs)} models to be gathered')
+
+    # find final_ckpt and log file for trained each config
+    # and parse the best performance
+    model_infos = []
+    for used_config in used_configs:
+        exp_dir = osp.join(models_root, used_config)
+        # check whether the exps is finished
+        final_iter = get_final_iter(used_config)
+        final_model = 'iter_{}.pth'.format(final_iter)
+        model_path = osp.join(exp_dir, final_model)
+
+        # skip if the model is still training
+        if not osp.exists(model_path):
+            print(f'{used_config} not finished yet')
+            continue
+
+        # get logs
+        log_json_path = glob.glob(osp.join(exp_dir, '*.log.json'))[0]
+        log_txt_path = glob.glob(osp.join(exp_dir, '*.log'))[0]
+        model_performance = get_final_results(log_json_path, final_iter)
+
+        if model_performance is None:
+            print(f'{used_config} does not have performance')
+            continue
+
+        model_time = osp.split(log_txt_path)[-1].split('.')[0]
+        model_infos.append(
+            dict(
+                config=used_config,
+                results=model_performance,
+                iters=final_iter,
+                model_time=model_time,
+                log_json_path=osp.split(log_json_path)[-1]))
+
+    # publish model for each checkpoint
+    for model in model_infos:
+
+        model_name = osp.split(model['config'])[-1].split('.')[0]
+
+        model_name += '_' + model['model_time']
+        for checkpoints in mmcv.scandir(
+                osp.join(models_root, model['config']), suffix='.pth'):
+            if checkpoints.endswith(f"iter_{model['iters']}.pth"
+                                    ) or checkpoints.endswith('latest.pth'):
+                continue
+            print('removing {}'.format(
+                osp.join(models_root, model['config'], checkpoints)))
+            os.remove(osp.join(models_root, model['config'], checkpoints))
+
+
+if __name__ == '__main__':
+    main()
--- a/.dev/gather_models.py
+++ b/.dev/gather_models.py
@ -0,0 +1,197 @@
+import argparse
+import glob
+import json
+import os
+import os.path as osp
+import shutil
+import subprocess
+
+import mmcv
+import torch
+
+# build schedule look-up table to automatically find the final model
+RESULTS_LUT = ['mIoU', 'mAcc', 'aAcc']
+
+
+def process_checkpoint(in_file, out_file):
+    checkpoint = torch.load(in_file, map_location='cpu')
+    # remove optimizer for smaller file size
+    if 'optimizer' in checkpoint:
+        del checkpoint['optimizer']
+    # if it is necessary to remove some sensitive data in checkpoint['meta'],
+    # add the code here.
+    torch.save(checkpoint, out_file)
+    sha = subprocess.check_output(['sha256sum', out_file]).decode()
+    final_file = out_file.rstrip('.pth') + '-{}.pth'.format(sha[:8])
+    subprocess.Popen(['mv', out_file, final_file])
+    return final_file
+
+
+def get_final_iter(config):
+    iter_num = config.split('_')[-2]
+    assert iter_num.endswith('k')
+    return int(iter_num[:-1]) * 1000
+
+
+def get_final_results(log_json_path, iter_num):
+    result_dict = dict()
+    with open(log_json_path, 'r') as f:
+        for line in f.readlines():
+            log_line = json.loads(line)
+            if 'mode' not in log_line.keys():
+                continue
+
+            if log_line['mode'] == 'train' and log_line['iter'] == iter_num:
+                result_dict['memory'] = log_line['memory']
+
+            if log_line['iter'] == iter_num:
+                result_dict.update({
+                    key: log_line[key]
+                    for key in RESULTS_LUT if key in log_line
+                })
+                return result_dict
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(description='Gather benchmarked models')
+    parser.add_argument(
+        'root',
+        type=str,
+        help='root path of benchmarked models to be gathered')
+    parser.add_argument(
+        'config',
+        type=str,
+        help='root path of benchmarked configs to be gathered')
+    parser.add_argument(
+        'out_dir',
+        type=str,
+        help='output path of gathered models to be stored')
+    parser.add_argument('out_file', type=str, help='the output json file name')
+    parser.add_argument(
+        '--filter', type=str, nargs='+', default=[], help='config filter')
+    parser.add_argument(
+        '--all', action='store_true', help='whether include .py and .log')
+
+    args = parser.parse_args()
+    return args
+
+
+def main():
+    args = parse_args()
+    models_root = args.root
+    models_out = args.out_dir
+    config_name = args.config
+    mmcv.mkdir_or_exist(models_out)
+
+    # find all models in the root directory to be gathered
+    raw_configs = list(mmcv.scandir(config_name, '.py', recursive=True))
+
+    # filter configs that is not trained in the experiments dir
+    used_configs = []
+    for raw_config in raw_configs:
+        work_dir = osp.splitext(osp.basename(raw_config))[0]
+        if osp.exists(osp.join(models_root, work_dir)):
+            used_configs.append((work_dir, raw_config))
+    print(f'Find {len(used_configs)} models to be gathered')
+
+    # find final_ckpt and log file for trained each config
+    # and parse the best performance
+    model_infos = []
+    for used_config, raw_config in used_configs:
+        bypass = True
+        for p in args.filter:
+            if p in used_config:
+                bypass = False
+                break
+        if bypass:
+            continue
+        exp_dir = osp.join(models_root, used_config)
+        # check whether the exps is finished
+        final_iter = get_final_iter(used_config)
+        final_model = 'iter_{}.pth'.format(final_iter)
+        model_path = osp.join(exp_dir, final_model)
+
+        # skip if the model is still training
+        if not osp.exists(model_path):
+            print(f'{used_config} train not finished yet')
+            continue
+
+        # get logs
+        log_json_paths = glob.glob(osp.join(exp_dir, '*.log.json'))
+        log_json_path = log_json_paths[0]
+        model_performance = None
+        for idx, _log_json_path in enumerate(log_json_paths):
+            model_performance = get_final_results(_log_json_path, final_iter)
+            if model_performance is not None:
+                log_json_path = _log_json_path
+                break
+
+        if model_performance is None:
+            print(f'{used_config} model_performance is None')
+            continue
+
+        model_time = osp.split(log_json_path)[-1].split('.')[0]
+        model_infos.append(
+            dict(
+                config=used_config,
+                raw_config=raw_config,
+                results=model_performance,
+                iters=final_iter,
+                model_time=model_time,
+                log_json_path=osp.split(log_json_path)[-1]))
+
+    # publish model for each checkpoint
+    publish_model_infos = []
+    for model in model_infos:
+        model_publish_dir = osp.join(models_out,
+                                     model['raw_config'].rstrip('.py'))
+        model_name = osp.split(model['config'])[-1].split('.')[0]
+
+        publish_model_path = osp.join(model_publish_dir,
+                                      model_name + '_' + model['model_time'])
+        trained_model_path = osp.join(models_root, model['config'],
+                                      'iter_{}.pth'.format(model['iters']))
+        if osp.exists(model_publish_dir):
+            for file in os.listdir(model_publish_dir):
+                if file.endswith('.pth'):
+                    print(f'model {file} found')
+                    model['model_path'] = osp.abspath(
+                        osp.join(model_publish_dir, file))
+                    break
+            if 'model_path' not in model:
+                print(f'dir {model_publish_dir} exists, no model found')
+
+        else:
+            mmcv.mkdir_or_exist(model_publish_dir)
+
+            # convert model
+            final_model_path = process_checkpoint(trained_model_path,
+                                                  publish_model_path)
+            model['model_path'] = final_model_path
+
+        new_json_path = f'{model_name}-{model["log_json_path"]}'
+        # copy log
+        shutil.copy(
+            osp.join(models_root, model['config'], model['log_json_path']),
+            osp.join(model_publish_dir, new_json_path))
+        if args.all:
+            new_txt_path = new_json_path.rstrip('.json')
+            shutil.copy(
+                osp.join(models_root, model['config'],
+                         model['log_json_path'].rstrip('.json')),
+                osp.join(model_publish_dir, new_txt_path))
+
+        if args.all:
+            # copy config to guarantee reproducibility
+            raw_config = osp.join(config_name, model['raw_config'])
+            mmcv.Config.fromfile(raw_config).dump(
+                osp.join(model_publish_dir, osp.basename(raw_config)))
+
+        publish_model_infos.append(model)
+
+    models = dict(models=publish_model_infos)
+    mmcv.dump(models, osp.join(models_out, args.out_file))
+
+
+if __name__ == '__main__':
+    main()
--- a/.dev/generate_table.py
+++ b/.dev/generate_table.py
@ -0,0 +1,152 @@
+import argparse
+import csv
+import glob
+import json
+import os.path as osp
+from collections import OrderedDict
+
+import mmcv
+
+# build schedule look-up table to automatically find the final model
+RESULTS_LUT = ['mIoU', 'mAcc', 'aAcc']
+
+
+def get_final_iter(config):
+    iter_num = config.split('_')[-2]
+    assert iter_num.endswith('ki')
+    return int(iter_num[:-2]) * 1000
+
+
+def get_final_results(log_json_path, iter_num):
+    result_dict = dict()
+    with open(log_json_path, 'r') as f:
+        for line in f.readlines():
+            log_line = json.loads(line)
+            if 'mode' not in log_line.keys():
+                continue
+
+            if log_line['mode'] == 'train' and log_line[
+                    'iter'] == iter_num - 50:
+                result_dict['memory'] = log_line['memory']
+
+            if log_line['iter'] == iter_num:
+                result_dict.update({
+                    key: log_line[key] * 100
+                    for key in RESULTS_LUT if key in log_line
+                })
+                return result_dict
+
+
+def get_total_time(log_json_path, iter_num):
+
+    def convert(seconds):
+        hour = seconds // 3600
+        seconds %= 3600
+        minutes = seconds // 60
+        seconds %= 60
+
+        return f'{hour:d}:{minutes:2d}:{seconds:2d}'
+
+    time_dict = dict()
+    with open(log_json_path, 'r') as f:
+        last_iter = 0
+        total_sec = 0
+        for line in f.readlines():
+            log_line = json.loads(line)
+            if 'mode' not in log_line.keys():
+                continue
+
+            if log_line['mode'] == 'train':
+                cur_iter = log_line['iter']
+                total_sec += (cur_iter - last_iter) * log_line['time']
+                last_iter = cur_iter
+        time_dict['time'] = convert(int(total_sec))
+
+        return time_dict
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(description='Gather benchmarked models')
+    parser.add_argument(
+        'root',
+        type=str,
+        help='root path of benchmarked models to be gathered')
+    parser.add_argument(
+        'config',
+        type=str,
+        help='root path of benchmarked configs to be gathered')
+    parser.add_argument(
+        'out', type=str, help='output path of gathered models to be stored')
+
+    args = parser.parse_args()
+    return args
+
+
+def main():
+    args = parse_args()
+    models_root = args.root
+    models_out = args.out
+    config_name = args.config
+    mmcv.mkdir_or_exist(models_out)
+
+    # find all models in the root directory to be gathered
+    raw_configs = list(mmcv.scandir(config_name, '.py', recursive=True))
+
+    # filter configs that is not trained in the experiments dir
+    exp_dirs = []
+    for raw_config in raw_configs:
+        work_dir = osp.splitext(osp.basename(raw_config))[0]
+        if osp.exists(osp.join(models_root, work_dir)):
+            exp_dirs.append(work_dir)
+    print(f'Find {len(exp_dirs)} models to be gathered')
+
+    # find final_ckpt and log file for trained each config
+    # and parse the best performance
+    model_infos = []
+    for work_dir in exp_dirs:
+        exp_dir = osp.join(models_root, work_dir)
+        # check whether the exps is finished
+        final_iter = get_final_iter(work_dir)
+        final_model = 'iter_{}.pth'.format(final_iter)
+        model_path = osp.join(exp_dir, final_model)
+
+        # skip if the model is still training
+        if not osp.exists(model_path):
+            print(f'{model_path} not finished yet')
+            continue
+
+        # get logs
+        log_json_path = glob.glob(osp.join(exp_dir, '*.log.json'))[0]
+        model_performance = get_final_results(log_json_path, final_iter)
+
+        if model_performance is None:
+            continue
+
+        head = work_dir.split('_')[0]
+        backbone = work_dir.split('_')[1]
+        crop_size = work_dir.split('_')[-3]
+        dataset = work_dir.split('_')[-1]
+        model_info = OrderedDict(
+            head=head,
+            backbone=backbone,
+            crop_size=crop_size,
+            dataset=dataset,
+            iters=f'{final_iter//1000}ki')
+        model_info.update(model_performance)
+        model_time = get_total_time(log_json_path, final_iter)
+        model_info.update(model_time)
+        model_info['config'] = work_dir
+        model_infos.append(model_info)
+
+    with open(
+            osp.join(models_out, 'models_table.csv'), 'w',
+            newline='') as csvfile:
+        writer = csv.writer(
+            csvfile, delimiter='\t', quotechar='|', quoting=csv.QUOTE_MINIMAL)
+        writer.writerow(model_infos[0].keys())
+        for model_info in model_infos:
+            writer.writerow(model_info.values())
+
+
+if __name__ == '__main__':
+    main()
--- a/.dev/modelzoo_json2md.py
+++ b/.dev/modelzoo_json2md.py
@ -0,0 +1,58 @@
+import argparse
+import os
+import os.path as osp
+
+import mmcv
+from pytablewriter import Align, MarkdownTableWriter
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(description='Gather benchmarked models')
+    parser.add_argument('table_cache', type=str, help='table_cache input')
+    parser.add_argument('out', type=str, help='output path md')
+
+    args = parser.parse_args()
+    return args
+
+
+def main():
+    args = parse_args()
+    table_cache = mmcv.load(args.table_cache)
+    output_dir = args.out
+
+    writer = MarkdownTableWriter()
+    writer.headers = [
+        'Method', 'Backbone', 'Crop Size', 'Lr schd', 'Mem (GB)',
+        'Inf time (fps)', 'mIoU', 'mIoU(ms+flip)', 'download'
+    ]
+    writer.margin = 1
+    writer.align_list = [Align.CENTER] * len(writer.headers)
+    dataset_maps = {
+        'cityscapes': 'Cityscapes',
+        'ade20k': 'ADE20K',
+        'voc12aug': 'Pascal VOC 2012 + Aug'
+    }
+    for directory in table_cache:
+        for dataset in table_cache[directory]:
+            table = table_cache[directory][dataset][0]
+            writer.table_name = dataset_maps[dataset]
+            writer.value_matrix = table
+            for i in range(len(table)):
+                if table[i][-4] != '-':
+                    table[i][-4] = f'{table[i][-4]:.2f}'
+            mmcv.mkdir_or_exist(osp.join(output_dir, directory))
+            writer.dump(
+                osp.join(output_dir, directory, f'README_{dataset}.md'))
+        with open(osp.join(output_dir, directory, 'README.md'), 'w') as dst_f:
+            for dataset in dataset_maps:
+                dataset_md_file = osp.join(output_dir, directory,
+                                           f'README_{dataset}.md')
+                with open(dataset_md_file) as src_f:
+                    for line in src_f:
+                        dst_f.write(line)
+                    dst_f.write('\n')
+                os.remove(dataset_md_file)
+
+
+if __name__ == '__main__':
+    main()
--- a/.github/CODE_OF_CONDUCT.md
+++ b/.github/CODE_OF_CONDUCT.md
@ -0,0 +1,76 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, sex characteristics, gender identity and expression,
+level of experience, education, socio-economic status, nationality, personal
+appearance, race, religion, or sexual identity and orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+ advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+ address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+ professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at chenkaidev@gmail.com. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see
+https://www.contributor-covenant.org/faq
--- a/.github/CONTRIBUTING.md
+++ b/.github/CONTRIBUTING.md
@ -0,0 +1,53 @@
+# Contributing to mmsegmentation
+
+All kinds of contributions are welcome, including but not limited to the following.
+
+- Fixes (typo, bugs)
+- New features and components
+
+## Workflow
+
+1. fork and pull the latest mmsegmentation
+2. checkout a new branch (do not use master branch for PRs)
+3. commit your changes
+4. create a PR
+
+Note
+- If you plan to add some new features that involve large changes, it is encouraged to open an issue for discussion first.
+- If you are the author of some papers and would like to include your method to mmsegmentation,
+please contact Kai Chen (chenkaidev[at]gmail[dot]com). We will much appreciate your contribution.
+
+## Code style
+
+### Python
+We adopt [PEP8](https://www.python.org/dev/peps/pep-0008/) as the preferred code style.
+
+We use the following tools for linting and formatting:
+- [flake8](http://flake8.pycqa.org/en/latest/): linter
+- [yapf](https://github.com/google/yapf): formatter
+- [isort](https://github.com/timothycrosley/isort): sort imports
+
+Style configurations of yapf and isort can be found in [.style.yapf](../.style.yapf) and [.isort.cfg](../.isort.cfg).
+
+We use [pre-commit hook](https://pre-commit.com/) that checks and formats for `flake8`, `yapf`, `isort`, `trailing whitespaces`,
+ fixes `end-of-files`, sorts `requirments.txt` automatically on every commit.
+The config for a pre-commit hook is stored in [.pre-commit-config](../.pre-commit-config.yaml).
+
+After you clone the repository, you will need to install initialize pre-commit hook.
+
+```
+pip install -U pre-commit
+```
+
+From the repository folder
+```
+pre-commit install
+```
+
+After this on every commit check code linters and formatter will be enforced.
+
+
+>Before you create a PR, make sure that your code lints and is formatted by yapf.
+
+### C++ and CUDA
+We follow the [Google C++ Style Guide](https://google.github.io/styleguide/cppguide.html).
--- a/.github/ISSUE_TEMPLATE/config.yml
+++ b/.github/ISSUE_TEMPLATE/config.yml
@ -0,0 +1 @@
+blank_issues_enabled: false
--- a/.github/ISSUE_TEMPLATE/error-report.md
+++ b/.github/ISSUE_TEMPLATE/error-report.md
@ -0,0 +1,41 @@
+---
+name: Error report
+about: Create a report to help us improve
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+Thanks for your error report and we appreciate it a lot.
+
+**Checklist**
+1. I have searched related issues but cannot get the expected help.
+2. The bug has not been fixed in the latest version.
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**Reproduction**
+1. What command or script did you run?
+```
+A placeholder for the command.
+```
+2. Did you make any modifications on the code or config? Did you understand what you have modified?
+3. What dataset did you use?
+
+**Environment**
+
+1. Please run `python mmseg/utils/collect_env.py` to collect necessary environment infomation and paste it here.
+2. You may add addition that may be helpful for locating the problem, such as
+    - How you installed PyTorch [e.g., pip, conda, source]
+    - Other environment variables that may be related (such as `$PATH`, `$LD_LIBRARY_PATH`, `$PYTHONPATH`, etc.)
+
+**Error traceback**
+If applicable, paste the error trackback here.
+```
+A placeholder for trackback.
+```
+
+**Bug fix**
+If you have already identified the reason, you can provide the information here. If you are willing to create a PR to fix it, please also leave a comment here and that would be much appreciated!
--- a/.github/ISSUE_TEMPLATE/feature_request.md
+++ b/.github/ISSUE_TEMPLATE/feature_request.md
@ -0,0 +1,22 @@
+---
+name: Feature request
+about: Suggest an idea for this project
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Describe the feature**
+
+**Motivation**
+A clear and concise description of the motivation of the feature.
+Ex1. It is inconvenient when [....].
+Ex2. There is a recent paper [....], which is very helpful for [....].
+
+**Related resources**
+If there is an official code release or third-party implementations, please also provide the information here, which would be very helpful.
+
+**Additional context**
+Add any other context or screenshots about the feature request here.
+If you would like to implement the feature and create a PR, please leave a comment here and that would be much appreciated.
--- a/.github/ISSUE_TEMPLATE/general_questions.md
+++ b/.github/ISSUE_TEMPLATE/general_questions.md
@ -0,0 +1,8 @@
+---
+name: General questions
+about: Ask general questions to get help
+title: ''
+labels: ''
+assignees: ''
+
+---
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@ -0,0 +1,101 @@
+# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: build
+
+on: [push, pull_request]
+
+jobs:
+
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python 3.7
+        uses: actions/setup-python@v1
+        with:
+          python-version: 3.7
+      - name: Install linting dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install flake8 isort==4.3.21 yapf interrogate
+      - name: Lint with flake8
+        run: flake8 .
+      - name: Lint with isort
+        run: isort --recursive --check-only --diff mmseg/ tests/ examples/
+      - name: Format python codes with yapf
+        run: yapf -r -d mmseg/ tests/ examples/
+      - name: Check docstring
+        run: interrogate -v --ignore-init-method --ignore-module --ignore-nested-functions --exclude mmseg/ops --ignore-regex "__repr__" --fail-under 80 mmseg
+
+  build:
+    env:
+      CUDA: 10.1.105-1
+      CUDA_SHORT: 10.1
+      UBUNTU_VERSION: ubuntu1804
+      FORCE_CUDA: 1
+      MMCV_CUDA_ARGS: -gencode=arch=compute_61,code=sm_61
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [3.6, 3.7]
+        torch: [1.3.0+cpu, 1.5.0+cpu]
+        include:
+          - torch: 1.3.0+cpu
+            torchvision: 0.4.2+cpu
+          - torch: 1.5.0+cpu
+            torchvision: 0.6.0+cpu
+          - torch: 1.5.0+cpu
+            torchvision: 0.6.0+cpu
+            python-version: 3.8
+          - torch: 1.5.0+cu101
+            torchvision: 0.6.0+cu101
+            python-version: 3.7
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install CUDA
+      if: ${{matrix.torch == '1.5.0+cu101'}}
+      run: |
+        export INSTALLER=cuda-repo-${UBUNTU_VERSION}_${CUDA}_amd64.deb
+        wget http://developer.download.nvidia.com/compute/cuda/repos/${UBUNTU_VERSION}/x86_64/${INSTALLER}
+        sudo dpkg -i ${INSTALLER}
+        wget https://developer.download.nvidia.com/compute/cuda/repos/${UBUNTU_VERSION}/x86_64/7fa2af80.pub
+        sudo apt-key add 7fa2af80.pub
+        sudo apt update -qq
+        sudo apt install -y cuda-${CUDA_SHORT/./-} cuda-cufft-dev-${CUDA_SHORT/./-}
+        sudo apt clean
+        export CUDA_HOME=/usr/local/cuda-${CUDA_SHORT}
+        export LD_LIBRARY_PATH=${CUDA_HOME}/lib64:${CUDA_HOME}/include:${LD_LIBRARY_PATH}
+        export PATH=${CUDA_HOME}/bin:${PATH}
+        sudo apt-get install -y ninja-build
+    - name: Install Pillow
+      if: ${{matrix.torchvision == '0.4.2+cpu'}}
+      run: pip install Pillow==6.2.2
+    - name: Install PyTorch
+      run: pip install torch==${{matrix.torch}} torchvision==${{matrix.torchvision}} -f https://download.pytorch.org/whl/torch_stable.html
+    - name: Install mmseg dependencies
+      run: |
+        pip install mmcv-full==latest+torch${{matrix.torch}} -f https://openmmlab.oss-accelerate.aliyuncs.com/mmcv/dist/index.html
+        pip install -r requirements.txt
+    - name: Build and install
+      run: rm -rf .eggs && pip install -e .
+    - name: Run unittests and generate coverage report
+      run: |
+        coverage run --branch --source mmseg -m pytest tests/
+        coverage xml
+        coverage report -m --omit="mmseg/utils/*","mmseg/apis/*"
+    # Only upload coverage report for python3.7 && pytorch1.5
+    - name: Upload coverage to Codecov
+      if: ${{matrix.torch == '1.5.0+cu101' && matrix.python-version == '3.7'}}
+      uses: codecov/codecov-action@v1.0.10
+      with:
+        file: ./coverage.xml
+        flags: unittests
+        env_vars: OS,PYTHON
+        name: codecov-umbrella
+        fail_ci_if_error: false
--- a/.gitignore
+++ b/.gitignore
@ -0,0 +1,118 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+
+mmseg/version.py
+data
+.vscode
+.idea
+
+# custom
+*.pkl
+*.pkl.json
+*.log.json
+work_dirs/
+
+# Pytorch
+*.pth
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@ -0,0 +1,35 @@
+repos:
+  - repo: https://gitlab.com/pycqa/flake8.git
+    rev: 3.8.3
+    hooks:
+      - id: flake8
+  - repo: https://github.com/asottile/seed-isort-config
+    rev: v2.2.0
+    hooks:
+      - id: seed-isort-config
+  - repo: https://github.com/timothycrosley/isort
+    rev: 4.3.21
+    hooks:
+      - id: isort
+  - repo: https://github.com/pre-commit/mirrors-yapf
+    rev: v0.30.0
+    hooks:
+      - id: yapf
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v3.1.0
+    hooks:
+      - id: trailing-whitespace
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: requirements-txt-fixer
+      - id: double-quote-string-fixer
+      - id: check-merge-conflict
+      - id: fix-encoding-pragma
+        args: ["--remove"]
+      - id: mixed-line-ending
+        args: ["--fix=lf"]
+  - repo: https://github.com/myint/docformatter
+    rev: v1.3.1
+    hooks:
+      - id: docformatter
+        args: ["--in-place", "--wrap-descriptions", "79"]
--- a/.style.yapf
+++ b/.style.yapf
@ -0,0 +1,4 @@
+[style]
+BASED_ON_STYLE = pep8
+BLANK_LINE_BEFORE_NESTED_CLASS_OR_DEF = true
+SPLIT_BEFORE_EXPRESSION_AFTER_OPENING_PAREN = true
--- a/2
+++ b/2
@ -200,4 +200,4 @@ Copyright 2020 The MMSegmentation Authors. All rights reserved.
   distributed under the License is distributed on an "AS IS" BASIS,
   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
   See the License for the specific language governing permissions and
-   limitations under the License.
+   limitations under the License.
--- a/README.md
+++ b/README.md
@ -0,0 +1,96 @@
+<div align="center">
+  <img src="resources/mmseg-logo.png" width="600"/>
+</div>
+
+## Introduction
+
+MMSegmentation is an open source semantic segmentation toolbox based on PyTorch.
+It is a part of the OpenMMLab project.
+
+The master branch works with **PyTorch 1.3 to 1.5**.
+
+![demo image](resources/seg_demo.gif)
+
+### Major features
+
+- **Unified Benchmark**
+
+  We provide a unified benchmark toolbox for various semantic segmentation methods.
+
+- **Modular Design**
+
+  We decompose the semantic segmentation framework into different components and one can easily construct a customized semantic segmentation framework by combining different modules.
+
+- **Support of multiple methods out of box**
+
+  The toolbox directly supports popular and contemporary semantic segmentation frameworks, *e.g.* PSPNet, DeepLabV3, PSANet, DeepLabV3+, etc.
+
+- **High efficiency**
+
+  The training speed is faster than or comparable to other codebases.
+
+## License
+
+This project is released under the [Apache 2.0 license](LICENSE).
+
+## Benchmark and model zoo
+
+Results and models are available in the [model zoo](docs/model_zoo.md).
+
+Supported backbones:
+- [x] ResNet
+- [x] ResNeXt
+- [x] HRNet
+
+Supported methods:
+- [x] [FCN](configs/fcn)
+- [x] [PSPNet](configs/pspnet)
+- [x] [DeepLabV3](configs/deeplabv3)
+- [x] [PSANet](configs/psanet)
+- [x] [DeepLabV3+](configs/deeplabv3plus)
+- [x] [UPerNet](configs/upernet)
+- [x] [NonLocal Net](configs/nonlocal_net)
+- [x] [CCNet](configs/ccnet)
+- [x] [DANet](configs/danet)
+- [x] [GCNet](configs/gcnet)
+- [x] [ANN](configs/ann)
+- [x] [OCRNet](configs/ocrnet)
+
+## Installation
+
+Please refer to [INSTALL.md](docs/install.md) for installation and dataset preparation.
+
+## Get Started
+
+Please see [getting_started.md](docs/getting_started.md) for the basic usage of MMSegmentation.
+There are also tutorials for [adding new dataset](docs/tutorials/new_dataset.md), [designing data pipeline](docs/tutorials/data_pipeline.md), and [adding new modules](docs/tutorials/new_modules.md).
+
+## Contributing
+
+We appreciate all contributions to improve MMSegmentation. Please refer to [CONTRIBUTING.md](.github/CONTRIBUTING.md) for the contributing guideline.
+
+## Acknowledgement
+
+MMSegmentation is an open source project that welcome any contribution and feedback.
+We wish that the toolbox and benchmark could serve the growing research
+community by providing a flexible as well as standardized toolkit to reimplement existing methods
+and develop their own new semantic segmentation methods.
+
+Many thanks to Ruobing Han ([@drcut](https://github.com/drcut)), Xiaoming Ma([@aishangmaxiaoming](https://github.com/aishangmaxiaoming)), Shiguang Wang ([@sunnyxiaohu](https://github.com/sunnyxiaohu)) for deployment support.
+
+## Citation
+
+If you use this toolbox or benchmark in your research, please cite this project.
+
+```
+@misc{mmseg2020,
+  author={Xu, Jiarui and Chen, Kai and Lin, Dahua},
+  title={{MMSegmenation}},
+  howpublished={\url{https://github.com/open-mmlab/mmsegmentation}},
+  year={2020}
+}
+```
+
+## Contact
+
+This repo is currently maintained by Jiarui Xu ([@xvjiarui](https://github.com/xvjiarui)), Kai Chen ([@hellock](http://github.com/hellock)).
--- a/configs/_base_/datasets/ade20k.py
+++ b/configs/_base_/datasets/ade20k.py
@ -0,0 +1,54 @@
+# dataset settings
+dataset_type = 'ADE20KDataset'
+data_root = 'data/ade/ADEChallengeData2016'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+crop_size = (512, 512)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', reduce_zero_label=True),
+    dict(type='Resize', img_scale=(2048, 512), ratio_range=(0.5, 2.0)),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_semantic_seg']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(2048, 512),
+        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    samples_per_gpu=4,
+    workers_per_gpu=4,
+    train=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir='images/training',
+        ann_dir='annotations/training',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir='images/validation',
+        ann_dir='annotations/validation',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir='images/validation',
+        ann_dir='annotations/validation',
+        pipeline=test_pipeline))
--- a/configs/_base_/datasets/cityscapes.py
+++ b/configs/_base_/datasets/cityscapes.py
@ -0,0 +1,54 @@
+# dataset settings
+dataset_type = 'CityscapesDataset'
+data_root = 'data/cityscapes/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+crop_size = (512, 1024)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(type='Resize', img_scale=(2048, 1024), ratio_range=(0.5, 2.0)),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_semantic_seg']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(2048, 1024),
+        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    samples_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir='leftImg8bit/train',
+        ann_dir='gtFine/train',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir='leftImg8bit/val',
+        ann_dir='gtFine/val',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir='leftImg8bit/val',
+        ann_dir='gtFine/val',
+        pipeline=test_pipeline))
--- a/configs/_base_/datasets/cityscapes_769x769.py
+++ b/configs/_base_/datasets/cityscapes_769x769.py
@ -0,0 +1,35 @@
+_base_ = './cityscapes.py'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+crop_size = (769, 769)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(type='Resize', img_scale=(2049, 1025), ratio_range=(0.5, 2.0)),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_semantic_seg']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(2049, 1025),
+        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    train=dict(pipeline=train_pipeline),
+    val=dict(pipeline=test_pipeline),
+    test=dict(pipeline=test_pipeline))
--- a/configs/_base_/datasets/pascal_voc12.py
+++ b/configs/_base_/datasets/pascal_voc12.py
@ -0,0 +1,57 @@
+# dataset settings
+dataset_type = 'PascalVOCDataset'
+data_root = 'data/VOCdevkit/VOC2012'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+crop_size = (512, 512)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations'),
+    dict(type='Resize', img_scale=(2048, 512), ratio_range=(0.5, 2.0)),
+    dict(type='RandomCrop', crop_size=crop_size, cat_max_ratio=0.75),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='PhotoMetricDistortion'),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_semantic_seg']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(2048, 512),
+        # img_ratios=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    samples_per_gpu=4,
+    workers_per_gpu=4,
+    train=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir='JPEGImages',
+        ann_dir='SegmentationClass',
+        split='ImageSets/Segmentation/train.txt',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir='JPEGImages',
+        ann_dir='SegmentationClass',
+        split='ImageSets/Segmentation/val.txt',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        data_root=data_root,
+        img_dir='JPEGImages',
+        ann_dir='SegmentationClass',
+        split='ImageSets/Segmentation/val.txt',
+        pipeline=test_pipeline))
--- a/configs/_base_/datasets/pascal_voc12_aug.py
+++ b/configs/_base_/datasets/pascal_voc12_aug.py
@ -0,0 +1,9 @@
+_base_ = './pascal_voc12.py'
+# dataset settings
+data = dict(
+    train=dict(
+        ann_dir=['SegmentationClass', 'SegmentationClassAug'],
+        split=[
+            'ImageSets/Segmentation/train.txt',
+            'ImageSets/Segmentation/aug.txt'
+        ]))
--- a/configs/_base_/default_runtime.py
+++ b/configs/_base_/default_runtime.py
@ -0,0 +1,14 @@
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook', by_epoch=False),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
+cudnn_benchmark = True
--- a/configs/_base_/models/ann_r50-d8.py
+++ b/configs/_base_/models/ann_r50-d8.py
@ -0,0 +1,46 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='ANNHead',
+        in_channels=[1024, 2048],
+        in_index=[2, 3],
+        channels=512,
+        project_channels=256,
+        query_scales=(1, ),
+        key_pool_scales=(1, 3, 6, 8),
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
+# model training and testing settings
+train_cfg = dict()
+test_cfg = dict(mode='whole')
--- a/configs/_base_/models/ccnet_r50-d8.py
+++ b/configs/_base_/models/ccnet_r50-d8.py
@ -0,0 +1,44 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='CCHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        recurrence=2,
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
+# model training and testing settings
+train_cfg = dict()
+test_cfg = dict(mode='whole')
--- a/configs/_base_/models/danet_r50-d8.py
+++ b/configs/_base_/models/danet_r50-d8.py
@ -0,0 +1,44 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='DAHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        pam_channels=64,
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
+# model training and testing settings
+train_cfg = dict()
+test_cfg = dict(mode='whole')
--- a/configs/_base_/models/deeplabv3_r50-d8.py
+++ b/configs/_base_/models/deeplabv3_r50-d8.py
@ -0,0 +1,44 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='ASPPHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        dilations=(1, 12, 24, 36),
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
+# model training and testing settings
+train_cfg = dict()
+test_cfg = dict(mode='whole')
--- a/configs/_base_/models/deeplabv3plus_r50-d8.py
+++ b/configs/_base_/models/deeplabv3plus_r50-d8.py
@ -0,0 +1,46 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='DepthwiseSeparableASPPHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        dilations=(1, 12, 24, 36),
+        c1_in_channels=256,
+        c1_channels=48,
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
+# model training and testing settings
+train_cfg = dict()
+test_cfg = dict(mode='whole')
--- a/configs/_base_/models/encnet_r50-d8.py
+++ b/configs/_base_/models/encnet_r50-d8.py
@ -0,0 +1,48 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='EncHead',
+        in_channels=[512, 1024, 2048],
+        in_index=(1, 2, 3),
+        channels=512,
+        num_codes=32,
+        use_se_loss=True,
+        add_lateral=False,
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+        loss_se_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=0.2)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
+# model training and testing settings
+train_cfg = dict()
+test_cfg = dict(mode='whole')
--- a/configs/_base_/models/fcn_hr18.py
+++ b/configs/_base_/models/fcn_hr18.py
@ -0,0 +1,52 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    pretrained='open-mmlab://msra/hrnetv2_w18',
+    backbone=dict(
+        type='HRNet',
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        extra=dict(
+            stage1=dict(
+                num_modules=1,
+                num_branches=1,
+                block='BOTTLENECK',
+                num_blocks=(4, ),
+                num_channels=(64, )),
+            stage2=dict(
+                num_modules=1,
+                num_branches=2,
+                block='BASIC',
+                num_blocks=(4, 4),
+                num_channels=(18, 36)),
+            stage3=dict(
+                num_modules=4,
+                num_branches=3,
+                block='BASIC',
+                num_blocks=(4, 4, 4),
+                num_channels=(18, 36, 72)),
+            stage4=dict(
+                num_modules=3,
+                num_branches=4,
+                block='BASIC',
+                num_blocks=(4, 4, 4, 4),
+                num_channels=(18, 36, 72, 144)))),
+    decode_head=dict(
+        type='FCNHead',
+        in_channels=[18, 36, 72, 144],
+        in_index=(0, 1, 2, 3),
+        channels=sum([18, 36, 72, 144]),
+        input_transform='resize_concat',
+        kernel_size=1,
+        num_convs=1,
+        concat_input=False,
+        drop_out_ratio=-1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)))
+# model training and testing settings
+train_cfg = dict()
+test_cfg = dict(mode='whole')
--- a/configs/_base_/models/fcn_r50-d8.py
+++ b/configs/_base_/models/fcn_r50-d8.py
@ -0,0 +1,45 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='FCNHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        num_convs=2,
+        concat_input=True,
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
+# model training and testing settings
+train_cfg = dict()
+test_cfg = dict(mode='whole')
--- a/configs/_base_/models/gcnet_r50-d8.py
+++ b/configs/_base_/models/gcnet_r50-d8.py
@ -0,0 +1,46 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='GCHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        ratio=1 / 4.,
+        pooling_type='att',
+        fusion_types=('channel_add', ),
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
+# model training and testing settings
+train_cfg = dict()
+test_cfg = dict(mode='whole')
--- a/configs/_base_/models/nonlocal_r50-d8.py
+++ b/configs/_base_/models/nonlocal_r50-d8.py
@ -0,0 +1,46 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='NLHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        drop_out_ratio=0.1,
+        reduction=2,
+        use_scale=True,
+        mode='embedded_gaussian',
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
+# model training and testing settings
+train_cfg = dict()
+test_cfg = dict(mode='whole')
--- a/configs/_base_/models/ocrnet_hr18.py
+++ b/configs/_base_/models/ocrnet_hr18.py
@ -0,0 +1,68 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+model = dict(
+    type='CascadeEncoderDecoder',
+    num_stages=2,
+    pretrained='open-mmlab://msra/hrnetv2_w18',
+    backbone=dict(
+        type='HRNet',
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        extra=dict(
+            stage1=dict(
+                num_modules=1,
+                num_branches=1,
+                block='BOTTLENECK',
+                num_blocks=(4, ),
+                num_channels=(64, )),
+            stage2=dict(
+                num_modules=1,
+                num_branches=2,
+                block='BASIC',
+                num_blocks=(4, 4),
+                num_channels=(18, 36)),
+            stage3=dict(
+                num_modules=4,
+                num_branches=3,
+                block='BASIC',
+                num_blocks=(4, 4, 4),
+                num_channels=(18, 36, 72)),
+            stage4=dict(
+                num_modules=3,
+                num_branches=4,
+                block='BASIC',
+                num_blocks=(4, 4, 4, 4),
+                num_channels=(18, 36, 72, 144)))),
+    decode_head=[
+        dict(
+            type='FCNHead',
+            in_channels=[18, 36, 72, 144],
+            channels=sum([18, 36, 72, 144]),
+            in_index=(0, 1, 2, 3),
+            input_transform='resize_concat',
+            kernel_size=1,
+            num_convs=1,
+            concat_input=False,
+            drop_out_ratio=-1,
+            num_classes=19,
+            norm_cfg=norm_cfg,
+            align_corners=False,
+            loss_decode=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
+        dict(
+            type='OCRHead',
+            in_channels=[18, 36, 72, 144],
+            in_index=(0, 1, 2, 3),
+            input_transform='resize_concat',
+            channels=512,
+            ocr_channels=256,
+            drop_out_ratio=-1,
+            num_classes=19,
+            norm_cfg=norm_cfg,
+            align_corners=False,
+            loss_decode=dict(
+                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    ])
+# model training and testing settings
+train_cfg = dict()
+test_cfg = dict(mode='whole')
--- a/configs/_base_/models/psanet_r50-d8.py
+++ b/configs/_base_/models/psanet_r50-d8.py
@ -0,0 +1,49 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='PSAHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        mask_size=(97, 97),
+        psa_type='bi-direction',
+        compact=False,
+        shrink_factor=2,
+        normalization_factor=1.0,
+        psa_softmax=True,
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
+# model training and testing settings
+train_cfg = dict()
+test_cfg = dict(mode='whole')
--- a/configs/_base_/models/pspnet_r50-d8.py
+++ b/configs/_base_/models/pspnet_r50-d8.py
@ -0,0 +1,44 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 2, 4),
+        strides=(1, 2, 1, 1),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='PSPHead',
+        in_channels=2048,
+        in_index=3,
+        channels=512,
+        pool_scales=(1, 2, 3, 6),
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
+# model training and testing settings
+train_cfg = dict()
+test_cfg = dict(mode='whole')
--- a/configs/_base_/models/upernet_r50.py
+++ b/configs/_base_/models/upernet_r50.py
@ -0,0 +1,44 @@
+# model settings
+norm_cfg = dict(type='SyncBN', requires_grad=True)
+model = dict(
+    type='EncoderDecoder',
+    pretrained='open-mmlab://resnet50_v1c',
+    backbone=dict(
+        type='ResNetV1c',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        dilations=(1, 1, 1, 1),
+        strides=(1, 2, 2, 2),
+        norm_cfg=norm_cfg,
+        norm_eval=False,
+        style='pytorch',
+        contract_dilation=True),
+    decode_head=dict(
+        type='UPerHead',
+        in_channels=[256, 512, 1024, 2048],
+        in_index=[0, 1, 2, 3],
+        pool_scales=(1, 2, 3, 6),
+        channels=512,
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
+    auxiliary_head=dict(
+        type='FCNHead',
+        in_channels=1024,
+        in_index=2,
+        channels=256,
+        num_convs=1,
+        concat_input=False,
+        drop_out_ratio=0.1,
+        num_classes=19,
+        norm_cfg=norm_cfg,
+        align_corners=False,
+        loss_decode=dict(
+            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)))
+# model training and testing settings
+train_cfg = dict()
+test_cfg = dict(mode='whole')
--- a/configs/_base_/schedules/schedule_160k.py
+++ b/configs/_base_/schedules/schedule_160k.py
@ -0,0 +1,9 @@
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
+optimizer_config = dict()
+# learning policy
+lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
+# runtime settings
+total_iters = 160000
+checkpoint_config = dict(by_epoch=False, interval=16000)
+evaluation = dict(interval=16000, metric='mIoU')
--- a/configs/_base_/schedules/schedule_20k.py
+++ b/configs/_base_/schedules/schedule_20k.py
@ -0,0 +1,9 @@
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
+optimizer_config = dict()
+# learning policy
+lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
+# runtime settings
+total_iters = 20000
+checkpoint_config = dict(by_epoch=False, interval=2000)
+evaluation = dict(interval=2000, metric='mIoU')
--- a/configs/_base_/schedules/schedule_40k.py
+++ b/configs/_base_/schedules/schedule_40k.py
@ -0,0 +1,9 @@
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
+optimizer_config = dict()
+# learning policy
+lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
+# runtime settings
+total_iters = 40000
+checkpoint_config = dict(by_epoch=False, interval=4000)
+evaluation = dict(interval=4000, metric='mIoU')
--- a/configs/_base_/schedules/schedule_80k.py
+++ b/configs/_base_/schedules/schedule_80k.py
@ -0,0 +1,9 @@
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
+optimizer_config = dict()
+# learning policy
+lr_config = dict(policy='poly', power=0.9, min_lr=1e-4, by_epoch=False)
+# runtime settings
+total_iters = 80000
+checkpoint_config = dict(by_epoch=False, interval=8000)
+evaluation = dict(interval=8000, metric='mIoU')
--- a/configs/ann/README.md
+++ b/configs/ann/README.md
@ -0,0 +1,46 @@
+# Asymmetric Non-local Neural Networks for Semantic Segmentation
+
+## Introduction
+```
+@inproceedings{annn,
+  author    = {Zhen Zhu and
+               Mengde Xu and
+               Song Bai and
+               Tengteng Huang and
+               Xiang Bai},
+  title     = {Asymmetric Non-local Neural Networks for Semantic Segmentation},
+  booktitle={International Conference on Computer Vision},
+  year      = {2019},
+  url       = {http://arxiv.org/abs/1908.07678},
+}
+```
+
+## Results and models
+
+### Cityscapes
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) |                                                                                                                                                                                        download                                                                                                                                                                                        |
+|--------|----------|-----------|--------:|----------|----------------|------:|--------------:|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| ANN    | R-50-D8  | 512x1024  |   40000 |        6 |           3.71 | 77.40 |         78.57 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_40k_cityscapes/ann_r50-d8_512x1024_40k_cityscapes_20200605_095211-049fc292.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_40k_cityscapes/ann_r50-d8_512x1024_40k_cityscapes_20200605_095211.log.json)     |
+| ANN    | R-101-D8 | 512x1024  |   40000 |      9.5 |           2.55 | 76.55 |         78.85 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_40k_cityscapes/ann_r101-d8_512x1024_40k_cityscapes_20200605_095243-adf6eece.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_40k_cityscapes/ann_r101-d8_512x1024_40k_cityscapes_20200605_095243.log.json) |
+| ANN    | R-50-D8  | 769x769   |   40000 |      6.8 |           1.70 | 78.89 |         80.46 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_40k_cityscapes/ann_r50-d8_769x769_40k_cityscapes_20200530_025712-2b46b04d.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_40k_cityscapes/ann_r50-d8_769x769_40k_cityscapes_20200530_025712.log.json)         |
+| ANN    | R-101-D8 | 769x769   |   40000 |     10.7 |           1.15 | 79.32 |         80.94 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_40k_cityscapes/ann_r101-d8_769x769_40k_cityscapes_20200530_025720-059bff28.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_40k_cityscapes/ann_r101-d8_769x769_40k_cityscapes_20200530_025720.log.json)     |
+| ANN    | R-50-D8  | 512x1024  |   80000 | -        | -              | 77.34 |         78.65 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_80k_cityscapes/ann_r50-d8_512x1024_80k_cityscapes_20200607_101911-5a9ad545.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x1024_80k_cityscapes/ann_r50-d8_512x1024_80k_cityscapes_20200607_101911.log.json)     |
+| ANN    | R-101-D8 | 512x1024  |   80000 | -        | -              | 77.14 |         78.81 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_80k_cityscapes/ann_r101-d8_512x1024_80k_cityscapes_20200607_013728-aceccc6e.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x1024_80k_cityscapes/ann_r101-d8_512x1024_80k_cityscapes_20200607_013728.log.json) |
+| ANN    | R-50-D8  | 769x769   |   80000 | -        | -              | 78.88 |         80.57 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_80k_cityscapes/ann_r50-d8_769x769_80k_cityscapes_20200607_044426-cc7ff323.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r50-d8_769x769_80k_cityscapes/ann_r50-d8_769x769_80k_cityscapes_20200607_044426.log.json)         |
+| ANN    | R-101-D8 | 769x769   |   80000 | -        | -              | 78.80 |         80.34 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_80k_cityscapes/ann_r101-d8_769x769_80k_cityscapes_20200607_013713-a9d4be8d.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r101-d8_769x769_80k_cityscapes/ann_r101-d8_769x769_80k_cityscapes_20200607_013713.log.json)     |
+
+### ADE20K
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) |                                                                                                                                                                                download                                                                                                                                                                                |
+|--------|----------|-----------|--------:|----------|----------------|------:|--------------:|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| ANN    | R-50-D8  | 512x512   |   80000 |      9.1 |          21.01 | 41.01 |         42.30 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_80k_ade20k/ann_r50-d8_512x512_80k_ade20k_20200615_014818-26f75e11.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_80k_ade20k/ann_r50-d8_512x512_80k_ade20k_20200615_014818.log.json)         |
+| ANN    | R-101-D8 | 512x512   |   80000 |     12.5 |          14.12 | 42.94 |         44.18 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_80k_ade20k/ann_r101-d8_512x512_80k_ade20k_20200615_014818-c0153543.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_80k_ade20k/ann_r101-d8_512x512_80k_ade20k_20200615_014818.log.json)     |
+| ANN    | R-50-D8  | 512x512   |  160000 | -        | -              | 41.74 |         42.62 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_160k_ade20k/ann_r50-d8_512x512_160k_ade20k_20200615_231733-892247bc.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_160k_ade20k/ann_r50-d8_512x512_160k_ade20k_20200615_231733.log.json)     |
+| ANN    | R-101-D8 | 512x512   |  160000 | -        | -              | 42.94 |         44.06 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_160k_ade20k/ann_r101-d8_512x512_160k_ade20k_20200615_231733-955eb1ec.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_160k_ade20k/ann_r101-d8_512x512_160k_ade20k_20200615_231733.log.json) |
+
+### Pascal VOC 2012 + Aug
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) |                                                                                                                                                                                  download                                                                                                                                                                                  |
+|--------|----------|-----------|--------:|----------|----------------|------:|--------------:|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| ANN    | R-50-D8  | 512x512   |   20000 |        6 |          20.92 | 74.86 |         76.13 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_20k_voc12aug/ann_r50-d8_512x512_20k_voc12aug_20200617_222246-dfcb1c62.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_20k_voc12aug/ann_r50-d8_512x512_20k_voc12aug_20200617_222246.log.json)     |
+| ANN    | R-101-D8 | 512x512   |   20000 |      9.5 |          13.94 | 77.47 |         78.70 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_20k_voc12aug/ann_r101-d8_512x512_20k_voc12aug_20200617_222246-2fad0042.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_20k_voc12aug/ann_r101-d8_512x512_20k_voc12aug_20200617_222246.log.json) |
+| ANN    | R-50-D8  | 512x512   |   40000 | -        | -              | 76.56 |         77.51 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_40k_voc12aug/ann_r50-d8_512x512_40k_voc12aug_20200613_231314-b5dac322.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r50-d8_512x512_40k_voc12aug/ann_r50-d8_512x512_40k_voc12aug_20200613_231314.log.json)     |
+| ANN    | R-101-D8 | 512x512   |   40000 | -        | -              | 76.70 |         78.06 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_40k_voc12aug/ann_r101-d8_512x512_40k_voc12aug_20200613_231314-bd205bbe.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ann/ann_r101-d8_512x512_40k_voc12aug/ann_r101-d8_512x512_40k_voc12aug_20200613_231314.log.json) |
--- a/configs/ann/ann_r101-d8_512x1024_40k_cityscapes.py
+++ b/configs/ann/ann_r101-d8_512x1024_40k_cityscapes.py
@ -0,0 +1,2 @@
+_base_ = './ann_r50-d8_512x1024_40k_cityscapes.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/ann/ann_r101-d8_512x1024_80k_cityscapes.py
+++ b/configs/ann/ann_r101-d8_512x1024_80k_cityscapes.py
@ -0,0 +1,2 @@
+_base_ = './ann_r50-d8_512x1024_80k_cityscapes.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/ann/ann_r101-d8_512x512_160k_ade20k.py
+++ b/configs/ann/ann_r101-d8_512x512_160k_ade20k.py
@ -0,0 +1,2 @@
+_base_ = './ann_r50-d8_512x512_160k_ade20k.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/ann/ann_r101-d8_512x512_20k_voc12aug.py
+++ b/configs/ann/ann_r101-d8_512x512_20k_voc12aug.py
@ -0,0 +1,2 @@
+_base_ = './ann_r50-d8_512x512_20k_voc12aug.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/ann/ann_r101-d8_512x512_40k_voc12aug.py
+++ b/configs/ann/ann_r101-d8_512x512_40k_voc12aug.py
@ -0,0 +1,2 @@
+_base_ = './ann_r50-d8_512x512_40k_voc12aug.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/ann/ann_r101-d8_512x512_80k_ade20k.py
+++ b/configs/ann/ann_r101-d8_512x512_80k_ade20k.py
@ -0,0 +1,2 @@
+_base_ = './ann_r50-d8_512x512_80k_ade20k.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/ann/ann_r101-d8_769x769_40k_cityscapes.py
+++ b/configs/ann/ann_r101-d8_769x769_40k_cityscapes.py
@ -0,0 +1,2 @@
+_base_ = './ann_r50-d8_769x769_40k_cityscapes.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/ann/ann_r101-d8_769x769_80k_cityscapes.py
+++ b/configs/ann/ann_r101-d8_769x769_80k_cityscapes.py
@ -0,0 +1,2 @@
+_base_ = './ann_r50-d8_769x769_80k_cityscapes.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/ann/ann_r50-d8_512x1024_40k_cityscapes.py
+++ b/configs/ann/ann_r50-d8_512x1024_40k_cityscapes.py
@ -0,0 +1,4 @@
+_base_ = [
+    '../_base_/models/ann_r50-d8.py', '../_base_/datasets/cityscapes.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_40k.py'
+]
--- a/configs/ann/ann_r50-d8_512x1024_80k_cityscapes.py
+++ b/configs/ann/ann_r50-d8_512x1024_80k_cityscapes.py
@ -0,0 +1,4 @@
+_base_ = [
+    '../_base_/models/ann_r50-d8.py', '../_base_/datasets/cityscapes.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py'
+]
--- a/configs/ann/ann_r50-d8_512x512_160k_ade20k.py
+++ b/configs/ann/ann_r50-d8_512x512_160k_ade20k.py
@ -0,0 +1,6 @@
+_base_ = [
+    '../_base_/models/ann_r50-d8.py', '../_base_/datasets/ade20k.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py'
+]
+model = dict(
+    decode_head=dict(num_classes=150), auxiliary_head=dict(num_classes=150))
--- a/configs/ann/ann_r50-d8_512x512_20k_voc12aug.py
+++ b/configs/ann/ann_r50-d8_512x512_20k_voc12aug.py
@ -0,0 +1,6 @@
+_base_ = [
+    '../_base_/models/ann_r50-d8.py', '../_base_/datasets/pascal_voc12_aug.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_20k.py'
+]
+model = dict(
+    decode_head=dict(num_classes=21), auxiliary_head=dict(num_classes=21))
--- a/configs/ann/ann_r50-d8_512x512_40k_voc12aug.py
+++ b/configs/ann/ann_r50-d8_512x512_40k_voc12aug.py
@ -0,0 +1,6 @@
+_base_ = [
+    '../_base_/models/ann_r50-d8.py', '../_base_/datasets/pascal_voc12_aug.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_40k.py'
+]
+model = dict(
+    decode_head=dict(num_classes=21), auxiliary_head=dict(num_classes=21))
--- a/configs/ann/ann_r50-d8_512x512_80k_ade20k.py
+++ b/configs/ann/ann_r50-d8_512x512_80k_ade20k.py
@ -0,0 +1,6 @@
+_base_ = [
+    '../_base_/models/ann_r50-d8.py', '../_base_/datasets/ade20k.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py'
+]
+model = dict(
+    decode_head=dict(num_classes=150), auxiliary_head=dict(num_classes=150))
--- a/configs/ann/ann_r50-d8_769x769_40k_cityscapes.py
+++ b/configs/ann/ann_r50-d8_769x769_40k_cityscapes.py
@ -0,0 +1,9 @@
+_base_ = [
+    '../_base_/models/ann_r50-d8.py',
+    '../_base_/datasets/cityscapes_769x769.py', '../_base_/default_runtime.py',
+    '../_base_/schedules/schedule_40k.py'
+]
+model = dict(
+    decode_head=dict(align_corners=True),
+    auxiliary_head=dict(align_corners=True))
+test_cfg = dict(mode='slide', crop_size=(769, 769), stride=(513, 513))
--- a/configs/ann/ann_r50-d8_769x769_80k_cityscapes.py
+++ b/configs/ann/ann_r50-d8_769x769_80k_cityscapes.py
@ -0,0 +1,9 @@
+_base_ = [
+    '../_base_/models/ann_r50-d8.py',
+    '../_base_/datasets/cityscapes_769x769.py', '../_base_/default_runtime.py',
+    '../_base_/schedules/schedule_80k.py'
+]
+model = dict(
+    decode_head=dict(align_corners=True),
+    auxiliary_head=dict(align_corners=True))
+test_cfg = dict(mode='slide', crop_size=(769, 769), stride=(513, 513))
--- a/configs/ccnet/README.md
+++ b/configs/ccnet/README.md
@ -0,0 +1,41 @@
+# CCNet: Criss-Cross Attention for Semantic Segmentation
+
+## Introduction
+```
+@article{huang2018ccnet,
+    title={CCNet: Criss-Cross Attention for Semantic Segmentation},
+    author={Huang, Zilong and Wang, Xinggang and Huang, Lichao and Huang, Chang and Wei, Yunchao and Liu, Wenyu},
+    booktitle={ICCV},
+    year={2019}
+}
+```
+
+## Results and models
+
+### Cityscapes
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) |                                                                                                                                                                                              download                                                                                                                                                                                              |
+|--------|----------|-----------|--------:|----------|----------------|------:|--------------:|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| CCNet  | R-50-D8  | 512x1024  |   40000 |        6 |           3.32 | 77.76 |         78.87 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_40k_cityscapes/ccnet_r50-d8_512x1024_40k_cityscapes_20200616_142517-4123f401.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_40k_cityscapes/ccnet_r50-d8_512x1024_40k_cityscapes_20200616_142517.log.json)     |
+| CCNet  | R-101-D8 | 512x1024  |   40000 |      9.5 |           2.31 | 76.35 |         78.19 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_40k_cityscapes/ccnet_r101-d8_512x1024_40k_cityscapes_20200616_142540-a3b84ba6.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_40k_cityscapes/ccnet_r101-d8_512x1024_40k_cityscapes_20200616_142540.log.json) |
+| CCNet  | R-50-D8  | 769x769   |   40000 |      6.8 |           1.43 | 78.46 |         79.93 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_40k_cityscapes/ccnet_r50-d8_769x769_40k_cityscapes_20200616_145125-76d11884.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_40k_cityscapes/ccnet_r50-d8_769x769_40k_cityscapes_20200616_145125.log.json)         |
+| CCNet  | R-101-D8 | 769x769   |   40000 |     10.7 |           1.01 | 76.94 |         78.62 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_40k_cityscapes/ccnet_r101-d8_769x769_40k_cityscapes_20200617_101428-4f57c8d0.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_40k_cityscapes/ccnet_r101-d8_769x769_40k_cityscapes_20200617_101428.log.json)     |
+| CCNet  | R-50-D8  | 512x1024  |   80000 | -        | -              | 79.03 |         80.16 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_80k_cityscapes/ccnet_r50-d8_512x1024_80k_cityscapes_20200617_010421-869a3423.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x1024_80k_cityscapes/ccnet_r50-d8_512x1024_80k_cityscapes_20200617_010421.log.json)     |
+| CCNet  | R-101-D8 | 512x1024  |   80000 | -        | -              | 78.87 |         79.90 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_80k_cityscapes/ccnet_r101-d8_512x1024_80k_cityscapes_20200617_203935-ffae8917.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x1024_80k_cityscapes/ccnet_r101-d8_512x1024_80k_cityscapes_20200617_203935.log.json) |
+| CCNet  | R-50-D8  | 769x769   |   80000 | -        | -              | 79.29 |         81.08 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_80k_cityscapes/ccnet_r50-d8_769x769_80k_cityscapes_20200617_010421-73eed8ca.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_769x769_80k_cityscapes/ccnet_r50-d8_769x769_80k_cityscapes_20200617_010421.log.json)         |
+| CCNet  | R-101-D8 | 769x769   |   80000 | -        | -              | 79.45 |         80.66 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_80k_cityscapes/ccnet_r101-d8_769x769_80k_cityscapes_20200618_011502-ad3cd481.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_769x769_80k_cityscapes/ccnet_r101-d8_769x769_80k_cityscapes_20200618_011502.log.json)     |
+
+### ADE20K
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) |                                                                                                                                                                                      download                                                                                                                                                                                      |
+|--------|----------|-----------|--------:|----------|----------------|------:|--------------:|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| CCNet  | R-50-D8  | 512x512   |   80000 |      8.8 |          20.89 | 41.78 |         42.98 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_80k_ade20k/ccnet_r50-d8_512x512_80k_ade20k_20200615_014848-aa37f61e.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_80k_ade20k/ccnet_r50-d8_512x512_80k_ade20k_20200615_014848.log.json)         |
+| CCNet  | R-101-D8 | 512x512   |   80000 |     12.2 |          14.11 | 43.97 |         45.13 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_80k_ade20k/ccnet_r101-d8_512x512_80k_ade20k_20200615_014848-1f4929a3.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_80k_ade20k/ccnet_r101-d8_512x512_80k_ade20k_20200615_014848.log.json)     |
+| CCNet  | R-50-D8  | 512x512   |  160000 | -        | -              | 42.08 |         43.13 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_160k_ade20k/ccnet_r50-d8_512x512_160k_ade20k_20200616_084435-7c97193b.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_160k_ade20k/ccnet_r50-d8_512x512_160k_ade20k_20200616_084435.log.json)     |
+| CCNet  | R-101-D8 | 512x512   |  160000 | -        | -              | 43.71 |         45.04 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_160k_ade20k/ccnet_r101-d8_512x512_160k_ade20k_20200616_000644-e849e007.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_160k_ade20k/ccnet_r101-d8_512x512_160k_ade20k_20200616_000644.log.json) |
+
+### Pascal VOC 2012 + Aug
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) |                                                                                                                                                                                        download                                                                                                                                                                                        |
+|--------|----------|-----------|--------:|----------|----------------|------:|--------------:|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| CCNet  | R-50-D8  | 512x512   |   20000 |        6 |          20.45 | 76.17 |         77.51 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_20k_voc12aug/ccnet_r50-d8_512x512_20k_voc12aug_20200617_193212-fad81784.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_20k_voc12aug/ccnet_r50-d8_512x512_20k_voc12aug_20200617_193212.log.json)     |
+| CCNet  | R-101-D8 | 512x512   |   20000 |      9.5 |          13.64 | 77.27 |         79.02 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_20k_voc12aug/ccnet_r101-d8_512x512_20k_voc12aug_20200617_193212-0007b61d.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_20k_voc12aug/ccnet_r101-d8_512x512_20k_voc12aug_20200617_193212.log.json) |
+| CCNet  | R-50-D8  | 512x512   |   40000 | -        | -              | 75.96 |         77.04 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_40k_voc12aug/ccnet_r50-d8_512x512_40k_voc12aug_20200613_232127-c2a15f02.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r50-d8_512x512_40k_voc12aug/ccnet_r50-d8_512x512_40k_voc12aug_20200613_232127.log.json)     |
+| CCNet  | R-101-D8 | 512x512   |   40000 | -        | -              | 77.87 |         78.90 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_40k_voc12aug/ccnet_r101-d8_512x512_40k_voc12aug_20200613_232127-c30da577.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/ccnet/ccnet_r101-d8_512x512_40k_voc12aug/ccnet_r101-d8_512x512_40k_voc12aug_20200613_232127.log.json) |
--- a/configs/ccnet/ccnet_r101-d8_512x1024_40k_cityscapes.py
+++ b/configs/ccnet/ccnet_r101-d8_512x1024_40k_cityscapes.py
@ -0,0 +1,2 @@
+_base_ = './ccnet_r50-d8_512x1024_40k_cityscapes.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/ccnet/ccnet_r101-d8_512x1024_80k_cityscapes.py
+++ b/configs/ccnet/ccnet_r101-d8_512x1024_80k_cityscapes.py
@ -0,0 +1,2 @@
+_base_ = './ccnet_r50-d8_512x1024_80k_cityscapes.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/ccnet/ccnet_r101-d8_512x512_160k_ade20k.py
+++ b/configs/ccnet/ccnet_r101-d8_512x512_160k_ade20k.py
@ -0,0 +1,2 @@
+_base_ = './ccnet_r50-d8_512x512_160k_ade20k.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/ccnet/ccnet_r101-d8_512x512_20k_voc12aug.py
+++ b/configs/ccnet/ccnet_r101-d8_512x512_20k_voc12aug.py
@ -0,0 +1,2 @@
+_base_ = './ccnet_r50-d8_512x512_20k_voc12aug.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/ccnet/ccnet_r101-d8_512x512_40k_voc12aug.py
+++ b/configs/ccnet/ccnet_r101-d8_512x512_40k_voc12aug.py
@ -0,0 +1,2 @@
+_base_ = './ccnet_r50-d8_512x512_40k_voc12aug.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/ccnet/ccnet_r101-d8_512x512_80k_ade20k.py
+++ b/configs/ccnet/ccnet_r101-d8_512x512_80k_ade20k.py
@ -0,0 +1,2 @@
+_base_ = './ccnet_r50-d8_512x512_80k_ade20k.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/ccnet/ccnet_r101-d8_769x769_40k_cityscapes.py
+++ b/configs/ccnet/ccnet_r101-d8_769x769_40k_cityscapes.py
@ -0,0 +1,2 @@
+_base_ = './ccnet_r50-d8_769x769_40k_cityscapes.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/ccnet/ccnet_r101-d8_769x769_80k_cityscapes.py
+++ b/configs/ccnet/ccnet_r101-d8_769x769_80k_cityscapes.py
@ -0,0 +1,2 @@
+_base_ = './ccnet_r50-d8_769x769_80k_cityscapes.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/ccnet/ccnet_r50-d8_512x1024_40k_cityscapes.py
+++ b/configs/ccnet/ccnet_r50-d8_512x1024_40k_cityscapes.py
@ -0,0 +1,4 @@
+_base_ = [
+    '../_base_/models/ccnet_r50-d8.py', '../_base_/datasets/cityscapes.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_40k.py'
+]
--- a/configs/ccnet/ccnet_r50-d8_512x1024_80k_cityscapes.py
+++ b/configs/ccnet/ccnet_r50-d8_512x1024_80k_cityscapes.py
@ -0,0 +1,4 @@
+_base_ = [
+    '../_base_/models/ccnet_r50-d8.py', '../_base_/datasets/cityscapes.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py'
+]
--- a/configs/ccnet/ccnet_r50-d8_512x512_160k_ade20k.py
+++ b/configs/ccnet/ccnet_r50-d8_512x512_160k_ade20k.py
@ -0,0 +1,6 @@
+_base_ = [
+    '../_base_/models/ccnet_r50-d8.py', '../_base_/datasets/ade20k.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py'
+]
+model = dict(
+    decode_head=dict(num_classes=150), auxiliary_head=dict(num_classes=150))
--- a/configs/ccnet/ccnet_r50-d8_512x512_20k_voc12aug.py
+++ b/configs/ccnet/ccnet_r50-d8_512x512_20k_voc12aug.py
@ -0,0 +1,7 @@
+_base_ = [
+    '../_base_/models/ccnet_r50-d8.py',
+    '../_base_/datasets/pascal_voc12_aug.py', '../_base_/default_runtime.py',
+    '../_base_/schedules/schedule_20k.py'
+]
+model = dict(
+    decode_head=dict(num_classes=21), auxiliary_head=dict(num_classes=21))
--- a/configs/ccnet/ccnet_r50-d8_512x512_40k_voc12aug.py
+++ b/configs/ccnet/ccnet_r50-d8_512x512_40k_voc12aug.py
@ -0,0 +1,7 @@
+_base_ = [
+    '../_base_/models/ccnet_r50-d8.py',
+    '../_base_/datasets/pascal_voc12_aug.py', '../_base_/default_runtime.py',
+    '../_base_/schedules/schedule_40k.py'
+]
+model = dict(
+    decode_head=dict(num_classes=21), auxiliary_head=dict(num_classes=21))
--- a/configs/ccnet/ccnet_r50-d8_512x512_80k_ade20k.py
+++ b/configs/ccnet/ccnet_r50-d8_512x512_80k_ade20k.py
@ -0,0 +1,6 @@
+_base_ = [
+    '../_base_/models/ccnet_r50-d8.py', '../_base_/datasets/ade20k.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py'
+]
+model = dict(
+    decode_head=dict(num_classes=150), auxiliary_head=dict(num_classes=150))
--- a/configs/ccnet/ccnet_r50-d8_769x769_40k_cityscapes.py
+++ b/configs/ccnet/ccnet_r50-d8_769x769_40k_cityscapes.py
@ -0,0 +1,9 @@
+_base_ = [
+    '../_base_/models/ccnet_r50-d8.py',
+    '../_base_/datasets/cityscapes_769x769.py', '../_base_/default_runtime.py',
+    '../_base_/schedules/schedule_40k.py'
+]
+model = dict(
+    decode_head=dict(align_corners=True),
+    auxiliary_head=dict(align_corners=True))
+test_cfg = dict(mode='slide', crop_size=(769, 769), stride=(513, 513))
--- a/configs/ccnet/ccnet_r50-d8_769x769_80k_cityscapes.py
+++ b/configs/ccnet/ccnet_r50-d8_769x769_80k_cityscapes.py
@ -0,0 +1,9 @@
+_base_ = [
+    '../_base_/models/ccnet_r50-d8.py',
+    '../_base_/datasets/cityscapes_769x769.py', '../_base_/default_runtime.py',
+    '../_base_/schedules/schedule_80k.py'
+]
+model = dict(
+    decode_head=dict(align_corners=True),
+    auxiliary_head=dict(align_corners=True))
+test_cfg = dict(mode='slide', crop_size=(769, 769), stride=(513, 513))
--- a/configs/danet/README.md
+++ b/configs/danet/README.md
@ -0,0 +1,41 @@
+# Dual Attention Network for Scene Segmentation
+
+## Introduction
+```
+@article{fu2018dual,
+  title={Dual Attention Network for Scene Segmentation},
+  author={Jun Fu, Jing Liu, Haijie Tian, Yong Li, Yongjun Bao, Zhiwei Fang,and Hanqing Lu},
+  booktitle={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
+  year={2019}
+}
+```
+
+## Results and models
+
+### Cityscapes
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) |                                                                                                                                                                                              download                                                                                                                                                                                              |
+|--------|----------|-----------|--------:|----------|----------------|------:|---------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| DANet  | R-50-D8  | 512x1024  |   40000 |      7.4 |           2.66 | 78.74 | -             | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_40k_cityscapes/danet_r50-d8_512x1024_40k_cityscapes_20200605_191324-c0dbfa5f.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_40k_cityscapes/danet_r50-d8_512x1024_40k_cityscapes_20200605_191324.log.json)     |
+| DANet  | R-101-D8 | 512x1024  |   40000 |     10.9 |           1.99 | 80.52 | -             | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_40k_cityscapes/danet_r101-d8_512x1024_40k_cityscapes_20200605_200831-c57a7157.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_40k_cityscapes/danet_r101-d8_512x1024_40k_cityscapes_20200605_200831.log.json) |
+| DANet  | R-50-D8  | 769x769   |   40000 |      8.8 |           1.56 | 78.88 |         80.62 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_40k_cityscapes/danet_r50-d8_769x769_40k_cityscapes_20200530_025703-76681c60.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_40k_cityscapes/danet_r50-d8_769x769_40k_cityscapes_20200530_025703.log.json)         |
+| DANet  | R-101-D8 | 769x769   |   40000 |     12.8 |           1.07 | 79.88 |         81.47 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_40k_cityscapes/danet_r101-d8_769x769_40k_cityscapes_20200530_025717-dcb7fd4e.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_40k_cityscapes/danet_r101-d8_769x769_40k_cityscapes_20200530_025717.log.json)     |
+| DANet  | R-50-D8  | 512x1024  |   80000 | -        | -              | 79.34 | -             | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_80k_cityscapes/danet_r50-d8_512x1024_80k_cityscapes_20200607_133029-2bfa2293.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x1024_80k_cityscapes/danet_r50-d8_512x1024_80k_cityscapes_20200607_133029.log.json)     |
+| DANet  | R-101-D8 | 512x1024  |   80000 | -        | -              | 80.41 | -             | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_80k_cityscapes/danet_r101-d8_512x1024_80k_cityscapes_20200607_132918-955e6350.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x1024_80k_cityscapes/danet_r101-d8_512x1024_80k_cityscapes_20200607_132918.log.json) |
+| DANet  | R-50-D8  | 769x769   |   80000 | -        | -              | 79.27 |         80.96 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_80k_cityscapes/danet_r50-d8_769x769_80k_cityscapes_20200607_132954-495689b4.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r50-d8_769x769_80k_cityscapes/danet_r50-d8_769x769_80k_cityscapes_20200607_132954.log.json)         |
+| DANet  | R-101-D8 | 769x769   |   80000 | -        | -              | 80.47 |         82.02 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_80k_cityscapes/danet_r101-d8_769x769_80k_cityscapes_20200607_132918-f3a929e7.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r101-d8_769x769_80k_cityscapes/danet_r101-d8_769x769_80k_cityscapes_20200607_132918.log.json)     |
+
+### ADE20K
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) |                                                                                                                                                                                      download                                                                                                                                                                                      |
+|--------|----------|-----------|--------:|----------|----------------|------:|--------------:|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| DANet  | R-50-D8  | 512x512   |   80000 |     11.5 |          21.20 | 41.66 |         42.90 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_80k_ade20k/danet_r50-d8_512x512_80k_ade20k_20200615_015125-edb18e08.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_80k_ade20k/danet_r50-d8_512x512_80k_ade20k_20200615_015125.log.json)         |
+| DANet  | R-101-D8 | 512x512   |   80000 |       15 |          14.18 | 43.64 |         45.19 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_80k_ade20k/danet_r101-d8_512x512_80k_ade20k_20200615_015126-d0357c73.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_80k_ade20k/danet_r101-d8_512x512_80k_ade20k_20200615_015126.log.json)     |
+| DANet  | R-50-D8  | 512x512   |  160000 | -        | -              | 42.45 |         43.25 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_160k_ade20k/danet_r50-d8_512x512_160k_ade20k_20200616_082340-9cb35dcd.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_160k_ade20k/danet_r50-d8_512x512_160k_ade20k_20200616_082340.log.json)     |
+| DANet  | R-101-D8 | 512x512   |  160000 | -        | -              | 44.17 |         45.02 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_160k_ade20k/danet_r101-d8_512x512_160k_ade20k_20200616_082348-23bf12f9.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_160k_ade20k/danet_r101-d8_512x512_160k_ade20k_20200616_082348.log.json) |
+
+### Pascal VOC 2012 + Aug
+| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) |                                                                                                                                                                                        download                                                                                                                                                                                        |
+|--------|----------|-----------|--------:|----------|----------------|------:|--------------:|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| DANet  | R-50-D8  | 512x512   |   20000 |      6.5 |          20.94 | 74.45 |         75.69 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_20k_voc12aug/danet_r50-d8_512x512_20k_voc12aug_20200618_070026-9e9e3ab3.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_20k_voc12aug/danet_r50-d8_512x512_20k_voc12aug_20200618_070026.log.json)     |
+| DANet  | R-101-D8 | 512x512   |   20000 |      9.9 |          13.76 | 76.02 |         77.23 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_20k_voc12aug/danet_r101-d8_512x512_20k_voc12aug_20200618_070026-d48d23b2.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_20k_voc12aug/danet_r101-d8_512x512_20k_voc12aug_20200618_070026.log.json) |
+| DANet  | R-50-D8  | 512x512   |   40000 | -        | -              | 76.37 |         77.29 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_40k_voc12aug/danet_r50-d8_512x512_40k_voc12aug_20200613_235526-426e3a64.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r50-d8_512x512_40k_voc12aug/danet_r50-d8_512x512_40k_voc12aug_20200613_235526.log.json)     |
+| DANet  | R-101-D8 | 512x512   |   40000 | -        | -              | 76.51 |         77.32 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_40k_voc12aug/danet_r101-d8_512x512_40k_voc12aug_20200613_223031-788e232a.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/danet/danet_r101-d8_512x512_40k_voc12aug/danet_r101-d8_512x512_40k_voc12aug_20200613_223031.log.json) |
--- a/configs/danet/danet_r101-d8_512x1024_40k_cityscapes.py
+++ b/configs/danet/danet_r101-d8_512x1024_40k_cityscapes.py
@ -0,0 +1,2 @@
+_base_ = './danet_r50-d8_512x1024_40k_cityscapes.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/danet/danet_r101-d8_512x1024_80k_cityscapes.py
+++ b/configs/danet/danet_r101-d8_512x1024_80k_cityscapes.py
@ -0,0 +1,2 @@
+_base_ = './danet_r50-d8_512x1024_80k_cityscapes.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/danet/danet_r101-d8_512x512_160k_ade20k.py
+++ b/configs/danet/danet_r101-d8_512x512_160k_ade20k.py
@ -0,0 +1,2 @@
+_base_ = './danet_r50-d8_512x512_160k_ade20k.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/danet/danet_r101-d8_512x512_20k_voc12aug.py
+++ b/configs/danet/danet_r101-d8_512x512_20k_voc12aug.py
@ -0,0 +1,2 @@
+_base_ = './danet_r50-d8_512x512_20k_voc12aug.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/danet/danet_r101-d8_512x512_40k_voc12aug.py
+++ b/configs/danet/danet_r101-d8_512x512_40k_voc12aug.py
@ -0,0 +1,2 @@
+_base_ = './danet_r50-d8_512x512_40k_voc12aug.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/danet/danet_r101-d8_512x512_80k_ade20k.py
+++ b/configs/danet/danet_r101-d8_512x512_80k_ade20k.py
@ -0,0 +1,2 @@
+_base_ = './danet_r50-d8_512x512_80k_ade20k.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/danet/danet_r101-d8_769x769_40k_cityscapes.py
+++ b/configs/danet/danet_r101-d8_769x769_40k_cityscapes.py
@ -0,0 +1,2 @@
+_base_ = './danet_r50-d8_769x769_40k_cityscapes.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/danet/danet_r101-d8_769x769_80k_cityscapes.py
+++ b/configs/danet/danet_r101-d8_769x769_80k_cityscapes.py
@ -0,0 +1,2 @@
+_base_ = './danet_r50-d8_769x769_80k_cityscapes.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/danet/danet_r50-d8_512x1024_40k_cityscapes.py
+++ b/configs/danet/danet_r50-d8_512x1024_40k_cityscapes.py
@ -0,0 +1,4 @@
+_base_ = [
+    '../_base_/models/danet_r50-d8.py', '../_base_/datasets/cityscapes.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_40k.py'
+]
--- a/configs/danet/danet_r50-d8_512x1024_80k_cityscapes.py
+++ b/configs/danet/danet_r50-d8_512x1024_80k_cityscapes.py
@ -0,0 +1,4 @@
+_base_ = [
+    '../_base_/models/danet_r50-d8.py', '../_base_/datasets/cityscapes.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py'
+]
--- a/configs/danet/danet_r50-d8_512x512_160k_ade20k.py
+++ b/configs/danet/danet_r50-d8_512x512_160k_ade20k.py
@ -0,0 +1,6 @@
+_base_ = [
+    '../_base_/models/danet_r50-d8.py', '../_base_/datasets/ade20k.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_160k.py'
+]
+model = dict(
+    decode_head=dict(num_classes=150), auxiliary_head=dict(num_classes=150))
--- a/configs/danet/danet_r50-d8_512x512_20k_voc12aug.py
+++ b/configs/danet/danet_r50-d8_512x512_20k_voc12aug.py
@ -0,0 +1,7 @@
+_base_ = [
+    '../_base_/models/danet_r50-d8.py',
+    '../_base_/datasets/pascal_voc12_aug.py', '../_base_/default_runtime.py',
+    '../_base_/schedules/schedule_20k.py'
+]
+model = dict(
+    decode_head=dict(num_classes=21), auxiliary_head=dict(num_classes=21))
--- a/configs/danet/danet_r50-d8_512x512_40k_voc12aug.py
+++ b/configs/danet/danet_r50-d8_512x512_40k_voc12aug.py
@ -0,0 +1,7 @@
+_base_ = [
+    '../_base_/models/danet_r50-d8.py',
+    '../_base_/datasets/pascal_voc12_aug.py', '../_base_/default_runtime.py',
+    '../_base_/schedules/schedule_40k.py'
+]
+model = dict(
+    decode_head=dict(num_classes=21), auxiliary_head=dict(num_classes=21))
--- a/configs/danet/danet_r50-d8_512x512_80k_ade20k.py
+++ b/configs/danet/danet_r50-d8_512x512_80k_ade20k.py
@ -0,0 +1,6 @@
+_base_ = [
+    '../_base_/models/danet_r50-d8.py', '../_base_/datasets/ade20k.py',
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py'
+]
+model = dict(
+    decode_head=dict(num_classes=150), auxiliary_head=dict(num_classes=150))
--- a/configs/danet/danet_r50-d8_769x769_40k_cityscapes.py
+++ b/configs/danet/danet_r50-d8_769x769_40k_cityscapes.py
@ -0,0 +1,9 @@
+_base_ = [
+    '../_base_/models/danet_r50-d8.py',
+    '../_base_/datasets/cityscapes_769x769.py', '../_base_/default_runtime.py',
+    '../_base_/schedules/schedule_40k.py'
+]
+model = dict(
+    decode_head=dict(align_corners=True),
+    auxiliary_head=dict(align_corners=True))
+test_cfg = dict(mode='slide', crop_size=(769, 769), stride=(513, 513))
--- a/configs/danet/danet_r50-d8_769x769_80k_cityscapes.py
+++ b/configs/danet/danet_r50-d8_769x769_80k_cityscapes.py
@ -0,0 +1,9 @@
+_base_ = [
+    '../_base_/models/danet_r50-d8.py',
+    '../_base_/datasets/cityscapes_769x769.py', '../_base_/default_runtime.py',
+    '../_base_/schedules/schedule_80k.py'
+]
+model = dict(
+    decode_head=dict(align_corners=True),
+    auxiliary_head=dict(align_corners=True))
+test_cfg = dict(mode='slide', crop_size=(769, 769), stride=(513, 513))
--- a/configs/deeplabv3/README.md
+++ b/configs/deeplabv3/README.md
@ -0,0 +1,43 @@
+# Rethinking atrous convolution for semantic image segmentation
+
+## Introduction
+```
+@article{chen2017rethinking,
+  title={Rethinking atrous convolution for semantic image segmentation},
+  author={Chen, Liang-Chieh and Papandreou, George and Schroff, Florian and Adam, Hartwig},
+  journal={arXiv preprint arXiv:1706.05587},
+  year={2017}
+}
+```
+
+## Results and models
+
+Note: `D-8` here corresponding to the output stride 8 setting for DeepLab series.
+
+### Cityscapes
+|  Method   | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) |                                                                                                                                                                                                          download                                                                                                                                                                                                          |
+|-----------|----------|-----------|--------:|----------|----------------|------:|--------------:|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| DeepLabV3 | R-50-D8  | 512x1024  |   40000 |      6.1 |           2.57 | 79.09 |         80.45 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_40k_cityscapes/deeplabv3_r50-d8_512x1024_40k_cityscapes_20200605_022449-acadc2f8.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_40k_cityscapes/deeplabv3_r50-d8_512x1024_40k_cityscapes_20200605_022449.log.json)     |
+| DeepLabV3 | R-101-D8 | 512x1024  |   40000 |      9.6 |           1.92 | 77.12 |         79.61 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_40k_cityscapes/deeplabv3_r101-d8_512x1024_40k_cityscapes_20200605_012241-7fd3f799.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_40k_cityscapes/deeplabv3_r101-d8_512x1024_40k_cityscapes_20200605_012241.log.json) |
+| DeepLabV3 | R-50-D8  | 769x769   |   40000 |      6.9 |           1.11 | 78.58 |         79.89 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_40k_cityscapes/deeplabv3_r50-d8_769x769_40k_cityscapes_20200606_113723-7eda553c.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_40k_cityscapes/deeplabv3_r50-d8_769x769_40k_cityscapes_20200606_113723.log.json)         |
+| DeepLabV3 | R-101-D8 | 769x769   |   40000 |     10.9 |           0.83 | 79.27 |         80.11 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_40k_cityscapes/deeplabv3_r101-d8_769x769_40k_cityscapes_20200606_113809-c64f889f.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_40k_cityscapes/deeplabv3_r101-d8_769x769_40k_cityscapes_20200606_113809.log.json)     |
+| DeepLabV3 | R-50-D8  | 512x1024  |   80000 | -        | -              | 79.32 |         80.57 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_80k_cityscapes/deeplabv3_r50-d8_512x1024_80k_cityscapes_20200606_113404-b92cfdd4.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x1024_80k_cityscapes/deeplabv3_r50-d8_512x1024_80k_cityscapes_20200606_113404.log.json)     |
+| DeepLabV3 | R-101-D8 | 512x1024  |   80000 | -        | -              | 80.20 |         81.21 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_80k_cityscapes/deeplabv3_r101-d8_512x1024_80k_cityscapes_20200606_113503-9e428899.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x1024_80k_cityscapes/deeplabv3_r101-d8_512x1024_80k_cityscapes_20200606_113503.log.json) |
+| DeepLabV3 | R-50-D8  | 769x769   |   80000 | -        | -              | 79.89 |         81.06 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_80k_cityscapes/deeplabv3_r50-d8_769x769_80k_cityscapes_20200606_221338-788d6228.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_769x769_80k_cityscapes/deeplabv3_r50-d8_769x769_80k_cityscapes_20200606_221338.log.json)         |
+| DeepLabV3 | R-101-D8 | 769x769   |   80000 | -        | -              | 79.67 |         80.81 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_80k_cityscapes/deeplabv3_r101-d8_769x769_80k_cityscapes_20200607_013353-60e95418.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_769x769_80k_cityscapes/deeplabv3_r101-d8_769x769_80k_cityscapes_20200607_013353.log.json)     |
+
+### ADE20K
+|  Method   | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) |                                                                                                                                                                                                  download                                                                                                                                                                                                  |
+|-----------|----------|-----------|--------:|----------|----------------|------:|--------------:|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| DeepLabV3 | R-50-D8  | 512x512   |   80000 |      8.9 |          14.76 | 42.42 |         43.28 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_80k_ade20k/deeplabv3_r50-d8_512x512_80k_ade20k_20200614_185028-0bb3f844.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_80k_ade20k/deeplabv3_r50-d8_512x512_80k_ade20k_20200614_185028.log.json)         |
+| DeepLabV3 | R-101-D8 | 512x512   |   80000 |     12.4 |          10.14 | 44.08 |         45.19 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_80k_ade20k/deeplabv3_r101-d8_512x512_80k_ade20k_20200615_021256-d89c7fa4.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_80k_ade20k/deeplabv3_r101-d8_512x512_80k_ade20k_20200615_021256.log.json)     |
+| DeepLabV3 | R-50-D8  | 512x512   |  160000 | -        | -              | 42.66 |         44.09 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_160k_ade20k/deeplabv3_r50-d8_512x512_160k_ade20k_20200615_123227-5d0ee427.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_160k_ade20k/deeplabv3_r50-d8_512x512_160k_ade20k_20200615_123227.log.json)     |
+| DeepLabV3 | R-101-D8 | 512x512   |  160000 | -        | -              | 45.00 |         46.66 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_160k_ade20k/deeplabv3_r101-d8_512x512_160k_ade20k_20200615_105816-b1f72b3b.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_160k_ade20k/deeplabv3_r101-d8_512x512_160k_ade20k_20200615_105816.log.json) |
+
+### Pascal VOC 2012 + Aug
+|  Method   | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU  | mIoU(ms+flip) |                                                                                                                                                                                                    download                                                                                                                                                                                                    |
+|-----------|----------|-----------|--------:|----------|----------------|------:|--------------:|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| DeepLabV3 | R-50-D8  | 512x512   |   20000 |      6.1 |          13.88 | 76.17 |         77.42 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_20k_voc12aug/deeplabv3_r50-d8_512x512_20k_voc12aug_20200617_010906-596905ef.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_20k_voc12aug/deeplabv3_r50-d8_512x512_20k_voc12aug_20200617_010906.log.json)     |
+| DeepLabV3 | R-101-D8 | 512x512   |   20000 |      9.6 |           9.81 | 78.70 |         79.95 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_20k_voc12aug/deeplabv3_r101-d8_512x512_20k_voc12aug_20200617_010932-8d13832f.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_20k_voc12aug/deeplabv3_r101-d8_512x512_20k_voc12aug_20200617_010932.log.json) |
+| DeepLabV3 | R-50-D8  | 512x512   |   40000 | -        | -              | 77.68 |         78.78 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_40k_voc12aug/deeplabv3_r50-d8_512x512_40k_voc12aug_20200613_161546-2ae96e7e.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r50-d8_512x512_40k_voc12aug/deeplabv3_r50-d8_512x512_40k_voc12aug_20200613_161546.log.json)     |
+| DeepLabV3 | R-101-D8 | 512x512   |   40000 | -        | -              | 77.92 |         79.18 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_40k_voc12aug/deeplabv3_r101-d8_512x512_40k_voc12aug_20200613_161432-0017d784.pth) &#124; [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/deeplabv3/deeplabv3_r101-d8_512x512_40k_voc12aug/deeplabv3_r101-d8_512x512_40k_voc12aug_20200613_161432.log.json) |
--- a/configs/deeplabv3/deeplabv3_r101-d8_512x1024_40k_cityscapes.py
+++ b/configs/deeplabv3/deeplabv3_r101-d8_512x1024_40k_cityscapes.py
@ -0,0 +1,2 @@
+_base_ = './deeplabv3_r50-d8_512x1024_40k_cityscapes.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/deeplabv3/deeplabv3_r101-d8_512x1024_80k_cityscapes.py
+++ b/configs/deeplabv3/deeplabv3_r101-d8_512x1024_80k_cityscapes.py
@ -0,0 +1,2 @@
+_base_ = './deeplabv3_r50-d8_512x1024_80k_cityscapes.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/deeplabv3/deeplabv3_r101-d8_512x512_160k_ade20k.py
+++ b/configs/deeplabv3/deeplabv3_r101-d8_512x512_160k_ade20k.py
@ -0,0 +1,2 @@
+_base_ = './deeplabv3_r50-d8_512x512_160k_ade20k.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/deeplabv3/deeplabv3_r101-d8_512x512_20k_voc12aug.py
+++ b/configs/deeplabv3/deeplabv3_r101-d8_512x512_20k_voc12aug.py
@ -0,0 +1,2 @@
+_base_ = './deeplabv3_r50-d8_512x512_20k_voc12aug.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/deeplabv3/deeplabv3_r101-d8_512x512_40k_voc12aug.py
+++ b/configs/deeplabv3/deeplabv3_r101-d8_512x512_40k_voc12aug.py
@ -0,0 +1,2 @@
+_base_ = './deeplabv3_r50-d8_512x512_40k_voc12aug.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/deeplabv3/deeplabv3_r101-d8_512x512_80k_ade20k.py
+++ b/configs/deeplabv3/deeplabv3_r101-d8_512x512_80k_ade20k.py
@ -0,0 +1,2 @@
+_base_ = './deeplabv3_r50-d8_512x512_80k_ade20k.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/deeplabv3/deeplabv3_r101-d8_769x769_40k_cityscapes.py
+++ b/configs/deeplabv3/deeplabv3_r101-d8_769x769_40k_cityscapes.py
@ -0,0 +1,2 @@
+_base_ = './deeplabv3_r50-d8_769x769_40k_cityscapes.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/configs/deeplabv3/deeplabv3_r101-d8_769x769_80k_cityscapes.py
+++ b/configs/deeplabv3/deeplabv3_r101-d8_769x769_80k_cityscapes.py
@ -0,0 +1,2 @@
+_base_ = './deeplabv3_r50-d8_769x769_80k_cityscapes.py'
+model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))
--- a/Show More
+++ b/Show More