diff --git a/.dev/check_urls.py b/.dev/check_urls.py
index 42b64745d..58a1354ba 100644
--- a/.dev/check_urls.py
+++ b/.dev/check_urls.py
@@ -56,8 +56,7 @@ def main():
 
     for model_name, yml_path in yml_list:
         # Default yaml loader unsafe.
-        model_infos = yml.load(
-            open(yml_path, 'r'), Loader=yml.CLoader)['Models']
+        model_infos = yml.load(open(yml_path), Loader=yml.CLoader)['Models']
         for model_info in model_infos:
             config_name = model_info['Name']
             checkpoint_url = model_info['Weights']
diff --git a/.dev/gather_models.py b/.dev/gather_models.py
index 82f812752..fe6c3901c 100644
--- a/.dev/gather_models.py
+++ b/.dev/gather_models.py
@@ -35,7 +35,7 @@ def process_checkpoint(in_file, out_file):
     # The hash code calculation and rename command differ on different system
     # platform.
     sha = calculate_file_sha256(out_file)
-    final_file = out_file.rstrip('.pth') + '-{}.pth'.format(sha[:8])
+    final_file = out_file.rstrip('.pth') + f'-{sha[:8]}.pth'
     os.rename(out_file, final_file)
 
     # Remove prefix and suffix
@@ -54,7 +54,7 @@ def get_final_iter(config):
 def get_final_results(log_json_path, iter_num):
     result_dict = dict()
     last_iter = 0
-    with open(log_json_path, 'r') as f:
+    with open(log_json_path) as f:
         for line in f.readlines():
             log_line = json.loads(line)
             if 'mode' not in log_line.keys():
@@ -125,7 +125,7 @@ def main():
         exp_dir = osp.join(work_dir, config_name)
         # check whether the exps is finished
         final_iter = get_final_iter(used_config)
-        final_model = 'iter_{}.pth'.format(final_iter)
+        final_model = f'iter_{final_iter}.pth'
         model_path = osp.join(exp_dir, final_model)
 
         # skip if the model is still training
diff --git a/.dev/generate_benchmark_train_script.py b/.dev/generate_benchmark_train_script.py
index 6e8a0ae31..4e6fa181f 100644
--- a/.dev/generate_benchmark_train_script.py
+++ b/.dev/generate_benchmark_train_script.py
@@ -74,7 +74,7 @@ def main():
     commands.append('\n')
     commands.append('\n')
 
-    with open(args.txt_path, 'r') as f:
+    with open(args.txt_path) as f:
         model_cfgs = f.readlines()
         for i, cfg in enumerate(model_cfgs):
             create_train_bash_info(commands, cfg, script_name, '$PARTITION',
diff --git a/.dev/log_collector/log_collector.py b/.dev/log_collector/log_collector.py
index d0f408087..0c2ff6188 100644
--- a/.dev/log_collector/log_collector.py
+++ b/.dev/log_collector/log_collector.py
@@ -86,7 +86,7 @@ def main():
         val_list = []
         last_iter = 0
         for log_name in log_list:
-            with open(os.path.join(preceding_path, log_name), 'r') as f:
+            with open(os.path.join(preceding_path, log_name)) as f:
                 # ignore the info line
                 f.readline()
                 all_lines = f.readlines()
diff --git a/.dev/md2yml.py b/.dev/md2yml.py
index b6c9daf09..fc9c67e47 100755
--- a/.dev/md2yml.py
+++ b/.dev/md2yml.py
@@ -15,7 +15,7 @@ import sys
 from lxml import etree
 from mmengine.fileio import dump
 
-MMSEG_ROOT = osp.dirname(osp.dirname((osp.dirname(__file__))))
+MMSEG_ROOT = osp.dirname(osp.dirname(osp.dirname(__file__)))
 
 COLLECTIONS = [
     'ANN', 'APCNet', 'BiSeNetV1', 'BiSeNetV2', 'CCNet', 'CGNet', 'DANet',
@@ -42,7 +42,7 @@ def dump_yaml_and_check_difference(obj, filename, sort_keys=False):
     str_dump = dump(obj, None, file_format='yaml', sort_keys=sort_keys)
     if osp.isfile(filename):
         file_exists = True
-        with open(filename, 'r', encoding='utf-8') as f:
+        with open(filename, encoding='utf-8') as f:
             str_orig = f.read()
     else:
         file_exists = False
@@ -97,7 +97,7 @@ def parse_md(md_file):
     # should be set with head or neck of this config file.
     is_backbone = None
 
-    with open(md_file, 'r', encoding='UTF-8') as md:
+    with open(md_file, encoding='UTF-8') as md:
         lines = md.readlines()
         i = 0
         current_dataset = ''
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index 0e3e17963..6b44b72bf 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -52,6 +52,11 @@ repos:
         language: python
         files: ^configs/.*\.md$
         require_serial: true
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v2.32.1
+    hooks:
+      - id: pyupgrade
+        args: ["--py36-plus"]
   - repo: https://github.com/open-mmlab/pre-commit-hooks
     rev: v0.2.0  # Use the rev to fix revision
     hooks:
diff --git a/docs/en/conf.py b/docs/en/conf.py
index 87b16f266..e20aab14b 100644
--- a/docs/en/conf.py
+++ b/docs/en/conf.py
@@ -28,7 +28,7 @@ version_file = '../../mmseg/version.py'
 
 
 def get_version():
-    with open(version_file, 'r') as f:
+    with open(version_file) as f:
         exec(compile(f.read(), version_file, 'exec'))
     return locals()['__version__']
 
diff --git a/docs/en/stat.py b/docs/en/stat.py
index 1398a706f..c458ee3c1 100755
--- a/docs/en/stat.py
+++ b/docs/en/stat.py
@@ -18,13 +18,15 @@ num_ckpts = 0
 for f in files:
     url = osp.dirname(f.replace('../../', url_prefix))
 
-    with open(f, 'r') as content_file:
+    with open(f) as content_file:
         content = content_file.read()
 
     title = content.split('\n')[0].replace('#', '').strip()
-    ckpts = set(x.lower().strip()
-                for x in re.findall(r'https?://download.*\.pth', content)
-                if 'mmsegmentation' in x)
+    ckpts = {
+        x.lower().strip()
+        for x in re.findall(r'https?://download.*\.pth', content)
+        if 'mmsegmentation' in x
+    }
     if len(ckpts) == 0:
         continue
 
@@ -34,7 +36,7 @@ for f in files:
     assert len(_papertype) > 0
     papertype = _papertype[0]
 
-    paper = set([(papertype, title)])
+    paper = {(papertype, title)}
 
     titles.append(title)
     num_ckpts += len(ckpts)
diff --git a/docs/zh_cn/conf.py b/docs/zh_cn/conf.py
index 353b0bc72..18420558d 100644
--- a/docs/zh_cn/conf.py
+++ b/docs/zh_cn/conf.py
@@ -28,7 +28,7 @@ version_file = '../../mmseg/version.py'
 
 
 def get_version():
-    with open(version_file, 'r') as f:
+    with open(version_file) as f:
         exec(compile(f.read(), version_file, 'exec'))
     return locals()['__version__']
 
diff --git a/docs/zh_cn/stat.py b/docs/zh_cn/stat.py
index b3a1d7306..7a86302e3 100755
--- a/docs/zh_cn/stat.py
+++ b/docs/zh_cn/stat.py
@@ -18,13 +18,15 @@ num_ckpts = 0
 for f in files:
     url = osp.dirname(f.replace('../../', url_prefix))
 
-    with open(f, 'r') as content_file:
+    with open(f) as content_file:
         content = content_file.read()
 
     title = content.split('\n')[0].replace('#', '').strip()
-    ckpts = set(x.lower().strip()
-                for x in re.findall(r'https?://download.*\.pth', content)
-                if 'mmsegmentation' in x)
+    ckpts = {
+        x.lower().strip()
+        for x in re.findall(r'https?://download.*\.pth', content)
+        if 'mmsegmentation' in x
+    }
     if len(ckpts) == 0:
         continue
 
@@ -34,7 +36,7 @@ for f in files:
     assert len(_papertype) > 0
     papertype = _papertype[0]
 
-    paper = set([(papertype, title)])
+    paper = {(papertype, title)}
 
     titles.append(title)
     num_ckpts += len(ckpts)
diff --git a/mmseg/engine/optimizers/layer_decay_optimizer_constructor.py b/mmseg/engine/optimizers/layer_decay_optimizer_constructor.py
index e614ad408..fdae3ca69 100644
--- a/mmseg/engine/optimizers/layer_decay_optimizer_constructor.py
+++ b/mmseg/engine/optimizers/layer_decay_optimizer_constructor.py
@@ -204,5 +204,4 @@ class LayerDecayOptimizerConstructor(LearningRateDecayOptimizerConstructor):
         warnings.warn('DeprecationWarning: Layer_decay_rate will '
                       'be deleted, please use decay_rate instead.')
         paramwise_cfg['decay_rate'] = paramwise_cfg.pop('layer_decay_rate')
-        super(LayerDecayOptimizerConstructor,
-              self).__init__(optim_wrapper_cfg, paramwise_cfg)
+        super().__init__(optim_wrapper_cfg, paramwise_cfg)
diff --git a/mmseg/evaluation/metrics/iou_metric.py b/mmseg/evaluation/metrics/iou_metric.py
index a065fc218..5a6958b70 100644
--- a/mmseg/evaluation/metrics/iou_metric.py
+++ b/mmseg/evaluation/metrics/iou_metric.py
@@ -212,7 +212,7 @@ class IoUMetric(BaseMetric):
             metrics = [metrics]
         allowed_metrics = ['mIoU', 'mDice', 'mFscore']
         if not set(metrics).issubset(set(allowed_metrics)):
-            raise KeyError('metrics {} is not supported'.format(metrics))
+            raise KeyError(f'metrics {metrics} is not supported')
 
         all_acc = total_area_intersect.sum() / total_area_label.sum()
         ret_metrics = OrderedDict({'aAcc': all_acc})
diff --git a/mmseg/models/backbones/beit.py b/mmseg/models/backbones/beit.py
index 15d5fc797..4553f72d8 100644
--- a/mmseg/models/backbones/beit.py
+++ b/mmseg/models/backbones/beit.py
@@ -194,7 +194,7 @@ class BEiTTransformerEncoderLayer(VisionTransformerEncoderLayer):
                  init_values=None):
         attn_cfg.update(dict(window_size=window_size, qk_scale=None))
 
-        super(BEiTTransformerEncoderLayer, self).__init__(
+        super().__init__(
             embed_dims=embed_dims,
             num_heads=num_heads,
             feedforward_channels=feedforward_channels,
@@ -214,9 +214,9 @@ class BEiTTransformerEncoderLayer(VisionTransformerEncoderLayer):
         self.drop_path = build_dropout(
             dropout_layer) if dropout_layer else nn.Identity()
         self.gamma_1 = nn.Parameter(
-            init_values * torch.ones((embed_dims)), requires_grad=True)
+            init_values * torch.ones(embed_dims), requires_grad=True)
         self.gamma_2 = nn.Parameter(
-            init_values * torch.ones((embed_dims)), requires_grad=True)
+            init_values * torch.ones(embed_dims), requires_grad=True)
 
     def build_attn(self, attn_cfg):
         self.attn = BEiTAttention(**attn_cfg)
@@ -287,7 +287,7 @@ class BEiT(BaseModule):
                  pretrained=None,
                  init_values=0.1,
                  init_cfg=None):
-        super(BEiT, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         if isinstance(img_size, int):
             img_size = to_2tuple(img_size)
         elif isinstance(img_size, tuple):
@@ -505,7 +505,7 @@ class BEiT(BaseModule):
             state_dict = self.resize_rel_pos_embed(checkpoint)
             self.load_state_dict(state_dict, False)
         elif self.init_cfg is not None:
-            super(BEiT, self).init_weights()
+            super().init_weights()
         else:
             # We only implement the 'jax_impl' initialization implemented at
             # https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/vision_transformer.py#L353  # noqa: E501
@@ -551,7 +551,7 @@ class BEiT(BaseModule):
         return tuple(outs)
 
     def train(self, mode=True):
-        super(BEiT, self).train(mode)
+        super().train(mode)
         if mode and self.norm_eval:
             for m in self.modules():
                 if isinstance(m, nn.LayerNorm):
diff --git a/mmseg/models/backbones/bisenetv1.py b/mmseg/models/backbones/bisenetv1.py
index fa9e51383..ca58bf9c5 100644
--- a/mmseg/models/backbones/bisenetv1.py
+++ b/mmseg/models/backbones/bisenetv1.py
@@ -29,7 +29,7 @@ class SpatialPath(BaseModule):
                  norm_cfg=dict(type='BN'),
                  act_cfg=dict(type='ReLU'),
                  init_cfg=None):
-        super(SpatialPath, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         assert len(num_channels) == 4, 'Length of input channels \
                                         of Spatial Path must be 4!'
 
@@ -98,7 +98,7 @@ class AttentionRefinementModule(BaseModule):
                  norm_cfg=dict(type='BN'),
                  act_cfg=dict(type='ReLU'),
                  init_cfg=None):
-        super(AttentionRefinementModule, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         self.conv_layer = ConvModule(
             in_channels=in_channels,
             out_channels=out_channel,
@@ -152,7 +152,7 @@ class ContextPath(BaseModule):
                  norm_cfg=dict(type='BN'),
                  act_cfg=dict(type='ReLU'),
                  init_cfg=None):
-        super(ContextPath, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         assert len(context_channels) == 3, 'Length of input channels \
                                            of Context Path must be 3!'
 
@@ -228,7 +228,7 @@ class FeatureFusionModule(BaseModule):
                  norm_cfg=dict(type='BN'),
                  act_cfg=dict(type='ReLU'),
                  init_cfg=None):
-        super(FeatureFusionModule, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         self.conv1 = ConvModule(
             in_channels=in_channels,
             out_channels=out_channels,
@@ -304,7 +304,7 @@ class BiSeNetV1(BaseModule):
                  act_cfg=dict(type='ReLU'),
                  init_cfg=None):
 
-        super(BiSeNetV1, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         assert len(spatial_channels) == 4, 'Length of input channels \
                                            of Spatial Path must be 4!'
 
diff --git a/mmseg/models/backbones/bisenetv2.py b/mmseg/models/backbones/bisenetv2.py
index 256de7952..32aa49822 100644
--- a/mmseg/models/backbones/bisenetv2.py
+++ b/mmseg/models/backbones/bisenetv2.py
@@ -37,7 +37,7 @@ class DetailBranch(BaseModule):
                  norm_cfg=dict(type='BN'),
                  act_cfg=dict(type='ReLU'),
                  init_cfg=None):
-        super(DetailBranch, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         detail_branch = []
         for i in range(len(detail_channels)):
             if i == 0:
@@ -126,7 +126,7 @@ class StemBlock(BaseModule):
                  norm_cfg=dict(type='BN'),
                  act_cfg=dict(type='ReLU'),
                  init_cfg=None):
-        super(StemBlock, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
 
         self.conv_first = ConvModule(
             in_channels=in_channels,
@@ -207,7 +207,7 @@ class GELayer(BaseModule):
                  norm_cfg=dict(type='BN'),
                  act_cfg=dict(type='ReLU'),
                  init_cfg=None):
-        super(GELayer, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         mid_channel = in_channels * exp_ratio
         self.conv1 = ConvModule(
             in_channels=in_channels,
@@ -326,7 +326,7 @@ class CEBlock(BaseModule):
                  norm_cfg=dict(type='BN'),
                  act_cfg=dict(type='ReLU'),
                  init_cfg=None):
-        super(CEBlock, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         self.in_channels = in_channels
         self.out_channels = out_channels
         self.gap = nn.Sequential(
@@ -385,7 +385,7 @@ class SemanticBranch(BaseModule):
                  in_channels=3,
                  exp_ratio=6,
                  init_cfg=None):
-        super(SemanticBranch, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         self.in_channels = in_channels
         self.semantic_channels = semantic_channels
         self.semantic_stages = []
@@ -458,7 +458,7 @@ class BGALayer(BaseModule):
                  norm_cfg=dict(type='BN'),
                  act_cfg=dict(type='ReLU'),
                  init_cfg=None):
-        super(BGALayer, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         self.out_channels = out_channels
         self.align_corners = align_corners
         self.detail_dwconv = nn.Sequential(
@@ -594,7 +594,7 @@ class BiSeNetV2(BaseModule):
                 dict(
                     type='Constant', val=1, layer=['_BatchNorm', 'GroupNorm'])
             ]
-        super(BiSeNetV2, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         self.in_channels = in_channels
         self.out_indices = out_indices
         self.detail_channels = detail_channels
diff --git a/mmseg/models/backbones/cgnet.py b/mmseg/models/backbones/cgnet.py
index 13e9f9146..b74b494f5 100644
--- a/mmseg/models/backbones/cgnet.py
+++ b/mmseg/models/backbones/cgnet.py
@@ -25,7 +25,7 @@ class GlobalContextExtractor(nn.Module):
     """
 
     def __init__(self, channel, reduction=16, with_cp=False):
-        super(GlobalContextExtractor, self).__init__()
+        super().__init__()
         self.channel = channel
         self.reduction = reduction
         assert reduction >= 1 and channel >= reduction
@@ -87,7 +87,7 @@ class ContextGuidedBlock(nn.Module):
                  norm_cfg=dict(type='BN', requires_grad=True),
                  act_cfg=dict(type='PReLU'),
                  with_cp=False):
-        super(ContextGuidedBlock, self).__init__()
+        super().__init__()
         self.with_cp = with_cp
         self.downsample = downsample
 
@@ -172,7 +172,7 @@ class InputInjection(nn.Module):
     """Downsampling module for CGNet."""
 
     def __init__(self, num_downsampling):
-        super(InputInjection, self).__init__()
+        super().__init__()
         self.pool = nn.ModuleList()
         for i in range(num_downsampling):
             self.pool.append(nn.AvgPool2d(3, stride=2, padding=1))
@@ -230,7 +230,7 @@ class CGNet(BaseModule):
                  pretrained=None,
                  init_cfg=None):
 
-        super(CGNet, self).__init__(init_cfg)
+        super().__init__(init_cfg)
 
         assert not (init_cfg and pretrained), \
             'init_cfg and pretrained cannot be setting at the same time'
@@ -364,7 +364,7 @@ class CGNet(BaseModule):
     def train(self, mode=True):
         """Convert the model into training mode will keeping the normalization
         layer freezed."""
-        super(CGNet, self).train(mode)
+        super().train(mode)
         if mode and self.norm_eval:
             for m in self.modules():
                 # trick: eval have effect on BatchNorm only
diff --git a/mmseg/models/backbones/erfnet.py b/mmseg/models/backbones/erfnet.py
index 88f41dfb1..2c5ec672a 100644
--- a/mmseg/models/backbones/erfnet.py
+++ b/mmseg/models/backbones/erfnet.py
@@ -35,7 +35,7 @@ class DownsamplerBlock(BaseModule):
                  norm_cfg=dict(type='BN', eps=1e-3),
                  act_cfg=dict(type='ReLU'),
                  init_cfg=None):
-        super(DownsamplerBlock, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         self.conv_cfg = conv_cfg
         self.norm_cfg = norm_cfg
         self.act_cfg = act_cfg
@@ -95,7 +95,7 @@ class NonBottleneck1d(BaseModule):
                  norm_cfg=dict(type='BN', eps=1e-3),
                  act_cfg=dict(type='ReLU'),
                  init_cfg=None):
-        super(NonBottleneck1d, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
 
         self.conv_cfg = conv_cfg
         self.norm_cfg = norm_cfg
@@ -168,7 +168,7 @@ class UpsamplerBlock(BaseModule):
                  norm_cfg=dict(type='BN', eps=1e-3),
                  act_cfg=dict(type='ReLU'),
                  init_cfg=None):
-        super(UpsamplerBlock, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         self.conv_cfg = conv_cfg
         self.norm_cfg = norm_cfg
         self.act_cfg = act_cfg
@@ -242,7 +242,7 @@ class ERFNet(BaseModule):
                  act_cfg=dict(type='ReLU'),
                  init_cfg=None):
 
-        super(ERFNet, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         assert len(enc_downsample_channels) \
                == len(dec_upsample_channels)+1, 'Number of downsample\
                      block of encoder does not \
diff --git a/mmseg/models/backbones/fast_scnn.py b/mmseg/models/backbones/fast_scnn.py
index 9884b2e18..6ff7a3191 100644
--- a/mmseg/models/backbones/fast_scnn.py
+++ b/mmseg/models/backbones/fast_scnn.py
@@ -36,7 +36,7 @@ class LearningToDownsample(nn.Module):
                  norm_cfg=dict(type='BN'),
                  act_cfg=dict(type='ReLU'),
                  dw_act_cfg=None):
-        super(LearningToDownsample, self).__init__()
+        super().__init__()
         self.conv_cfg = conv_cfg
         self.norm_cfg = norm_cfg
         self.act_cfg = act_cfg
@@ -124,7 +124,7 @@ class GlobalFeatureExtractor(nn.Module):
                  norm_cfg=dict(type='BN'),
                  act_cfg=dict(type='ReLU'),
                  align_corners=False):
-        super(GlobalFeatureExtractor, self).__init__()
+        super().__init__()
         self.conv_cfg = conv_cfg
         self.norm_cfg = norm_cfg
         self.act_cfg = act_cfg
@@ -220,7 +220,7 @@ class FeatureFusionModule(nn.Module):
                  dwconv_act_cfg=dict(type='ReLU'),
                  conv_act_cfg=None,
                  align_corners=False):
-        super(FeatureFusionModule, self).__init__()
+        super().__init__()
         self.conv_cfg = conv_cfg
         self.norm_cfg = norm_cfg
         self.dwconv_act_cfg = dwconv_act_cfg
@@ -340,7 +340,7 @@ class FastSCNN(BaseModule):
                  dw_act_cfg=None,
                  init_cfg=None):
 
-        super(FastSCNN, self).__init__(init_cfg)
+        super().__init__(init_cfg)
 
         if init_cfg is None:
             self.init_cfg = [
diff --git a/mmseg/models/backbones/hrnet.py b/mmseg/models/backbones/hrnet.py
index ca4e15500..2da755e73 100644
--- a/mmseg/models/backbones/hrnet.py
+++ b/mmseg/models/backbones/hrnet.py
@@ -30,7 +30,7 @@ class HRModule(BaseModule):
                  norm_cfg=dict(type='BN', requires_grad=True),
                  block_init_cfg=None,
                  init_cfg=None):
-        super(HRModule, self).__init__(init_cfg)
+        super().__init__(init_cfg)
         self.block_init_cfg = block_init_cfg
         self._check_branches(num_branches, num_blocks, in_channels,
                              num_channels)
@@ -308,7 +308,7 @@ class HRNet(BaseModule):
                  multiscale_output=True,
                  pretrained=None,
                  init_cfg=None):
-        super(HRNet, self).__init__(init_cfg)
+        super().__init__(init_cfg)
 
         self.pretrained = pretrained
         self.zero_init_residual = zero_init_residual
@@ -633,7 +633,7 @@ class HRNet(BaseModule):
     def train(self, mode=True):
         """Convert the model into training mode will keeping the normalization
         layer freezed."""
-        super(HRNet, self).train(mode)
+        super().train(mode)
         self._freeze_stages()
         if mode and self.norm_eval:
             for m in self.modules():
diff --git a/mmseg/models/backbones/icnet.py b/mmseg/models/backbones/icnet.py
index faa6d15cc..8ff344856 100644
--- a/mmseg/models/backbones/icnet.py
+++ b/mmseg/models/backbones/icnet.py
@@ -64,7 +64,7 @@ class ICNet(BaseModule):
                 dict(type='Constant', val=1, layer='_BatchNorm'),
                 dict(type='Normal', mean=0.01, layer='Linear')
             ]
-        super(ICNet, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         self.align_corners = align_corners
         self.backbone = MODELS.build(backbone_cfg)
 
diff --git a/mmseg/models/backbones/mae.py b/mmseg/models/backbones/mae.py
index 1e7b932bf..a1f243f08 100644
--- a/mmseg/models/backbones/mae.py
+++ b/mmseg/models/backbones/mae.py
@@ -100,7 +100,7 @@ class MAE(BEiT):
                  pretrained=None,
                  init_values=0.1,
                  init_cfg=None):
-        super(MAE, self).__init__(
+        super().__init__(
             img_size=img_size,
             patch_size=patch_size,
             in_channels=in_channels,
@@ -186,7 +186,7 @@ class MAE(BEiT):
             state_dict = self.resize_abs_pos_embed(state_dict)
             self.load_state_dict(state_dict, False)
         elif self.init_cfg is not None:
-            super(MAE, self).init_weights()
+            super().init_weights()
         else:
             # We only implement the 'jax_impl' initialization implemented at
             # https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/vision_transformer.py#L353  # noqa: E501
diff --git a/mmseg/models/backbones/mit.py b/mmseg/models/backbones/mit.py
index faea1d0ef..66556bdfc 100644
--- a/mmseg/models/backbones/mit.py
+++ b/mmseg/models/backbones/mit.py
@@ -44,7 +44,7 @@ class MixFFN(BaseModule):
                  ffn_drop=0.,
                  dropout_layer=None,
                  init_cfg=None):
-        super(MixFFN, self).__init__(init_cfg)
+        super().__init__(init_cfg)
 
         self.embed_dims = embed_dims
         self.feedforward_channels = feedforward_channels
@@ -253,7 +253,7 @@ class TransformerEncoderLayer(BaseModule):
                  batch_first=True,
                  sr_ratio=1,
                  with_cp=False):
-        super(TransformerEncoderLayer, self).__init__()
+        super().__init__()
 
         # The ret[0] of build_norm_layer is norm name.
         self.norm1 = build_norm_layer(norm_cfg, embed_dims)[1]
@@ -357,7 +357,7 @@ class MixVisionTransformer(BaseModule):
                  pretrained=None,
                  init_cfg=None,
                  with_cp=False):
-        super(MixVisionTransformer, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
 
         assert not (init_cfg and pretrained), \
             'init_cfg and pretrained cannot be set at the same time'
@@ -433,7 +433,7 @@ class MixVisionTransformer(BaseModule):
                     normal_init(
                         m, mean=0, std=math.sqrt(2.0 / fan_out), bias=0)
         else:
-            super(MixVisionTransformer, self).init_weights()
+            super().init_weights()
 
     def forward(self, x):
         outs = []
diff --git a/mmseg/models/backbones/mobilenet_v2.py b/mmseg/models/backbones/mobilenet_v2.py
index 32224e08a..1c21b5df9 100644
--- a/mmseg/models/backbones/mobilenet_v2.py
+++ b/mmseg/models/backbones/mobilenet_v2.py
@@ -63,7 +63,7 @@ class MobileNetV2(BaseModule):
                  with_cp=False,
                  pretrained=None,
                  init_cfg=None):
-        super(MobileNetV2, self).__init__(init_cfg)
+        super().__init__(init_cfg)
 
         self.pretrained = pretrained
         assert not (init_cfg and pretrained), \
@@ -189,7 +189,7 @@ class MobileNetV2(BaseModule):
                 param.requires_grad = False
 
     def train(self, mode=True):
-        super(MobileNetV2, self).train(mode)
+        super().train(mode)
         self._freeze_stages()
         if mode and self.norm_eval:
             for m in self.modules():
diff --git a/mmseg/models/backbones/mobilenet_v3.py b/mmseg/models/backbones/mobilenet_v3.py
index 93717df48..1efb6e097 100644
--- a/mmseg/models/backbones/mobilenet_v3.py
+++ b/mmseg/models/backbones/mobilenet_v3.py
@@ -81,7 +81,7 @@ class MobileNetV3(BaseModule):
                  with_cp=False,
                  pretrained=None,
                  init_cfg=None):
-        super(MobileNetV3, self).__init__(init_cfg)
+        super().__init__(init_cfg)
 
         self.pretrained = pretrained
         assert not (init_cfg and pretrained), \
@@ -175,7 +175,7 @@ class MobileNetV3(BaseModule):
                 act_cfg=dict(type=act),
                 with_cp=self.with_cp)
             in_channels = out_channels
-            layer_name = 'layer{}'.format(i + 1)
+            layer_name = f'layer{i + 1}'
             self.add_module(layer_name, layer)
             layers.append(layer_name)
 
@@ -192,7 +192,7 @@ class MobileNetV3(BaseModule):
             conv_cfg=self.conv_cfg,
             norm_cfg=self.norm_cfg,
             act_cfg=dict(type='HSwish'))
-        layer_name = 'layer{}'.format(len(layer_setting) + 1)
+        layer_name = f'layer{len(layer_setting) + 1}'
         self.add_module(layer_name, layer)
         layers.append(layer_name)
 
@@ -259,7 +259,7 @@ class MobileNetV3(BaseModule):
                 param.requires_grad = False
 
     def train(self, mode=True):
-        super(MobileNetV3, self).train(mode)
+        super().train(mode)
         self._freeze_stages()
         if mode and self.norm_eval:
             for m in self.modules():
diff --git a/mmseg/models/backbones/resnest.py b/mmseg/models/backbones/resnest.py
index 519bd9738..3cc380b44 100644
--- a/mmseg/models/backbones/resnest.py
+++ b/mmseg/models/backbones/resnest.py
@@ -69,7 +69,7 @@ class SplitAttentionConv2d(nn.Module):
                  conv_cfg=None,
                  norm_cfg=dict(type='BN'),
                  dcn=None):
-        super(SplitAttentionConv2d, self).__init__()
+        super().__init__()
         inter_channels = max(in_channels * radix // reduction_factor, 32)
         self.radix = radix
         self.groups = groups
@@ -174,7 +174,7 @@ class Bottleneck(_Bottleneck):
                  avg_down_stride=True,
                  **kwargs):
         """Bottleneck block for ResNeSt."""
-        super(Bottleneck, self).__init__(inplanes, planes, **kwargs)
+        super().__init__(inplanes, planes, **kwargs)
 
         if groups == 1:
             width = self.planes
@@ -304,7 +304,7 @@ class ResNeSt(ResNetV1d):
         self.radix = radix
         self.reduction_factor = reduction_factor
         self.avg_down_stride = avg_down_stride
-        super(ResNeSt, self).__init__(**kwargs)
+        super().__init__(**kwargs)
 
     def make_res_layer(self, **kwargs):
         """Pack all blocks in a stage into a ``ResLayer``."""
diff --git a/mmseg/models/backbones/resnet.py b/mmseg/models/backbones/resnet.py
index 51ac7faab..9226c90d8 100644
--- a/mmseg/models/backbones/resnet.py
+++ b/mmseg/models/backbones/resnet.py
@@ -29,7 +29,7 @@ class BasicBlock(BaseModule):
                  dcn=None,
                  plugins=None,
                  init_cfg=None):
-        super(BasicBlock, self).__init__(init_cfg)
+        super().__init__(init_cfg)
         assert dcn is None, 'Not implemented yet.'
         assert plugins is None, 'Not implemented yet.'
 
@@ -118,7 +118,7 @@ class Bottleneck(BaseModule):
                  dcn=None,
                  plugins=None,
                  init_cfg=None):
-        super(Bottleneck, self).__init__(init_cfg)
+        super().__init__(init_cfg)
         assert style in ['pytorch', 'caffe']
         assert dcn is None or isinstance(dcn, dict)
         assert plugins is None or isinstance(plugins, list)
@@ -418,7 +418,7 @@ class ResNet(BaseModule):
                  zero_init_residual=True,
                  pretrained=None,
                  init_cfg=None):
-        super(ResNet, self).__init__(init_cfg)
+        super().__init__(init_cfg)
         if depth not in self.arch_settings:
             raise KeyError(f'invalid depth {depth} for resnet')
 
@@ -676,7 +676,7 @@ class ResNet(BaseModule):
     def train(self, mode=True):
         """Convert the model into training mode while keep normalization layer
         freezed."""
-        super(ResNet, self).train(mode)
+        super().train(mode)
         self._freeze_stages()
         if mode and self.norm_eval:
             for m in self.modules():
@@ -696,8 +696,7 @@ class ResNetV1c(ResNet):
     """
 
     def __init__(self, **kwargs):
-        super(ResNetV1c, self).__init__(
-            deep_stem=True, avg_down=False, **kwargs)
+        super().__init__(deep_stem=True, avg_down=False, **kwargs)
 
 
 @MODELS.register_module()
@@ -710,5 +709,4 @@ class ResNetV1d(ResNet):
     """
 
     def __init__(self, **kwargs):
-        super(ResNetV1d, self).__init__(
-            deep_stem=True, avg_down=True, **kwargs)
+        super().__init__(deep_stem=True, avg_down=True, **kwargs)
diff --git a/mmseg/models/backbones/resnext.py b/mmseg/models/backbones/resnext.py
index 2f7cacab7..67a244a12 100644
--- a/mmseg/models/backbones/resnext.py
+++ b/mmseg/models/backbones/resnext.py
@@ -23,7 +23,7 @@ class Bottleneck(_Bottleneck):
                  base_width=4,
                  base_channels=64,
                  **kwargs):
-        super(Bottleneck, self).__init__(inplanes, planes, **kwargs)
+        super().__init__(inplanes, planes, **kwargs)
 
         if groups == 1:
             width = self.planes
@@ -139,7 +139,7 @@ class ResNeXt(ResNet):
     def __init__(self, groups=1, base_width=4, **kwargs):
         self.groups = groups
         self.base_width = base_width
-        super(ResNeXt, self).__init__(**kwargs)
+        super().__init__(**kwargs)
 
     def make_res_layer(self, **kwargs):
         """Pack all blocks in a stage into a ``ResLayer``"""
diff --git a/mmseg/models/backbones/stdc.py b/mmseg/models/backbones/stdc.py
index 340d6ee4c..758a3c92e 100644
--- a/mmseg/models/backbones/stdc.py
+++ b/mmseg/models/backbones/stdc.py
@@ -35,7 +35,7 @@ class STDCModule(BaseModule):
                  num_convs=4,
                  fusion_type='add',
                  init_cfg=None):
-        super(STDCModule, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         assert num_convs > 1
         assert fusion_type in ['add', 'cat']
         self.stride = stride
@@ -155,7 +155,7 @@ class FeatureFusionModule(BaseModule):
                  norm_cfg=dict(type='BN'),
                  act_cfg=dict(type='ReLU'),
                  init_cfg=None):
-        super(FeatureFusionModule, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         channels = out_channels // scale_factor
         self.conv0 = ConvModule(
             in_channels, out_channels, 1, norm_cfg=norm_cfg, act_cfg=act_cfg)
@@ -240,7 +240,7 @@ class STDCNet(BaseModule):
                  with_final_conv=False,
                  pretrained=None,
                  init_cfg=None):
-        super(STDCNet, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         assert stdc_type in self.arch_settings, \
             f'invalid structure {stdc_type} for STDCNet.'
         assert bottleneck_type in ['add', 'cat'],\
@@ -370,7 +370,7 @@ class STDCContextPathNet(BaseModule):
                  align_corners=None,
                  norm_cfg=dict(type='BN'),
                  init_cfg=None):
-        super(STDCContextPathNet, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         self.backbone = MODELS.build(backbone_cfg)
         self.arms = ModuleList()
         self.convs = ModuleList()
diff --git a/mmseg/models/backbones/swin.py b/mmseg/models/backbones/swin.py
index 884548d2f..57ab99085 100644
--- a/mmseg/models/backbones/swin.py
+++ b/mmseg/models/backbones/swin.py
@@ -326,7 +326,7 @@ class SwinBlock(BaseModule):
                  with_cp=False,
                  init_cfg=None):
 
-        super(SwinBlock, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
 
         self.with_cp = with_cp
 
@@ -561,7 +561,7 @@ class SwinTransformer(BaseModule):
         else:
             raise TypeError('pretrained must be a str or None')
 
-        super(SwinTransformer, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
 
         num_layers = len(depths)
         self.out_indices = out_indices
@@ -636,7 +636,7 @@ class SwinTransformer(BaseModule):
 
     def train(self, mode=True):
         """Convert the model into training mode while keep layers freezed."""
-        super(SwinTransformer, self).train(mode)
+        super().train(mode)
         self._freeze_stages()
 
     def _freeze_stages(self):
diff --git a/mmseg/models/backbones/timm_backbone.py b/mmseg/models/backbones/timm_backbone.py
index 3ecb1c4a9..1eef302bd 100644
--- a/mmseg/models/backbones/timm_backbone.py
+++ b/mmseg/models/backbones/timm_backbone.py
@@ -37,7 +37,7 @@ class TIMMBackbone(BaseModule):
     ):
         if timm is None:
             raise RuntimeError('timm is not installed')
-        super(TIMMBackbone, self).__init__(init_cfg)
+        super().__init__(init_cfg)
         if 'norm_layer' in kwargs:
             kwargs['norm_layer'] = MMENGINE_MODELS.get(kwargs['norm_layer'])
         self.timm_model = timm.create_model(
diff --git a/mmseg/models/backbones/twins.py b/mmseg/models/backbones/twins.py
index 9ee11f0ab..b6a6eea79 100644
--- a/mmseg/models/backbones/twins.py
+++ b/mmseg/models/backbones/twins.py
@@ -62,7 +62,7 @@ class GlobalSubsampledAttention(EfficientMultiheadAttention):
                  norm_cfg=dict(type='LN'),
                  sr_ratio=1,
                  init_cfg=None):
-        super(GlobalSubsampledAttention, self).__init__(
+        super().__init__(
             embed_dims,
             num_heads,
             attn_drop=attn_drop,
@@ -112,7 +112,7 @@ class GSAEncoderLayer(BaseModule):
                  norm_cfg=dict(type='LN'),
                  sr_ratio=1.,
                  init_cfg=None):
-        super(GSAEncoderLayer, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
 
         self.norm1 = build_norm_layer(norm_cfg, embed_dims, postfix=1)[1]
         self.attn = GlobalSubsampledAttention(
@@ -172,7 +172,7 @@ class LocallyGroupedSelfAttention(BaseModule):
                  proj_drop_rate=0.,
                  window_size=1,
                  init_cfg=None):
-        super(LocallyGroupedSelfAttention, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
 
         assert embed_dims % num_heads == 0, f'dim {embed_dims} should be ' \
                                             f'divided by num_heads ' \
@@ -284,7 +284,7 @@ class LSAEncoderLayer(BaseModule):
                  window_size=1,
                  init_cfg=None):
 
-        super(LSAEncoderLayer, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
 
         self.norm1 = build_norm_layer(norm_cfg, embed_dims, postfix=1)[1]
         self.attn = LocallyGroupedSelfAttention(embed_dims, num_heads,
@@ -325,7 +325,7 @@ class ConditionalPositionEncoding(BaseModule):
     """
 
     def __init__(self, in_channels, embed_dims=768, stride=1, init_cfg=None):
-        super(ConditionalPositionEncoding, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         self.proj = nn.Conv2d(
             in_channels,
             embed_dims,
@@ -401,7 +401,7 @@ class PCPVT(BaseModule):
                  norm_after_stage=False,
                  pretrained=None,
                  init_cfg=None):
-        super(PCPVT, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         assert not (init_cfg and pretrained), \
             'init_cfg and pretrained cannot be set at the same time'
         if isinstance(pretrained, str):
@@ -471,7 +471,7 @@ class PCPVT(BaseModule):
 
     def init_weights(self):
         if self.init_cfg is not None:
-            super(PCPVT, self).init_weights()
+            super().init_weights()
         else:
             for m in self.modules():
                 if isinstance(m, nn.Linear):
@@ -563,11 +563,11 @@ class SVT(PCPVT):
                  norm_after_stage=True,
                  pretrained=None,
                  init_cfg=None):
-        super(SVT, self).__init__(in_channels, embed_dims, patch_sizes,
-                                  strides, num_heads, mlp_ratios, out_indices,
-                                  qkv_bias, drop_rate, attn_drop_rate,
-                                  drop_path_rate, norm_cfg, depths, sr_ratios,
-                                  norm_after_stage, pretrained, init_cfg)
+        super().__init__(in_channels, embed_dims, patch_sizes, strides,
+                         num_heads, mlp_ratios, out_indices, qkv_bias,
+                         drop_rate, attn_drop_rate, drop_path_rate, norm_cfg,
+                         depths, sr_ratios, norm_after_stage, pretrained,
+                         init_cfg)
         # transformer encoder
         dpr = [
             x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))
diff --git a/mmseg/models/backbones/unet.py b/mmseg/models/backbones/unet.py
index f25658ad9..545921db8 100644
--- a/mmseg/models/backbones/unet.py
+++ b/mmseg/models/backbones/unet.py
@@ -53,7 +53,7 @@ class BasicConvBlock(nn.Module):
                  act_cfg=dict(type='ReLU'),
                  dcn=None,
                  plugins=None):
-        super(BasicConvBlock, self).__init__()
+        super().__init__()
         assert dcn is None, 'Not implemented yet.'
         assert plugins is None, 'Not implemented yet.'
 
@@ -112,7 +112,7 @@ class DeconvModule(nn.Module):
                  *,
                  kernel_size=4,
                  scale_factor=2):
-        super(DeconvModule, self).__init__()
+        super().__init__()
 
         assert (kernel_size - scale_factor >= 0) and\
                (kernel_size - scale_factor) % 2 == 0,\
@@ -191,7 +191,7 @@ class InterpConv(nn.Module):
                  padding=0,
                  upsample_cfg=dict(
                      scale_factor=2, mode='bilinear', align_corners=False)):
-        super(InterpConv, self).__init__()
+        super().__init__()
 
         self.with_cp = with_cp
         conv = ConvModule(
@@ -298,7 +298,7 @@ class UNet(BaseModule):
                  plugins=None,
                  pretrained=None,
                  init_cfg=None):
-        super(UNet, self).__init__(init_cfg)
+        super().__init__(init_cfg)
 
         self.pretrained = pretrained
         assert not (init_cfg and pretrained), \
@@ -396,7 +396,7 @@ class UNet(BaseModule):
                     act_cfg=act_cfg,
                     dcn=None,
                     plugins=None))
-            self.encoder.append((nn.Sequential(*enc_conv_block)))
+            self.encoder.append(nn.Sequential(*enc_conv_block))
             in_channels = base_channels * 2**i
 
     def forward(self, x):
@@ -415,7 +415,7 @@ class UNet(BaseModule):
     def train(self, mode=True):
         """Convert the model into training mode while keep normalization layer
         freezed."""
-        super(UNet, self).train(mode)
+        super().train(mode)
         if mode and self.norm_eval:
             for m in self.modules():
                 # trick: eval have effect on BatchNorm only
diff --git a/mmseg/models/backbones/vit.py b/mmseg/models/backbones/vit.py
index e9e87dc3b..05948abe7 100644
--- a/mmseg/models/backbones/vit.py
+++ b/mmseg/models/backbones/vit.py
@@ -60,7 +60,7 @@ class TransformerEncoderLayer(BaseModule):
                  attn_cfg=dict(),
                  ffn_cfg=dict(),
                  with_cp=False):
-        super(TransformerEncoderLayer, self).__init__()
+        super().__init__()
 
         self.norm1_name, norm1 = build_norm_layer(
             norm_cfg, embed_dims, postfix=1)
@@ -197,7 +197,7 @@ class VisionTransformer(BaseModule):
                  with_cp=False,
                  pretrained=None,
                  init_cfg=None):
-        super(VisionTransformer, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
 
         if isinstance(img_size, int):
             img_size = to_2tuple(img_size)
@@ -315,7 +315,7 @@ class VisionTransformer(BaseModule):
 
             load_state_dict(self, state_dict, strict=False, logger=None)
         elif self.init_cfg is not None:
-            super(VisionTransformer, self).init_weights()
+            super().init_weights()
         else:
             # We only implement the 'jax_impl' initialization implemented at
             # https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/vision_transformer.py#L353  # noqa: E501
@@ -431,7 +431,7 @@ class VisionTransformer(BaseModule):
         return tuple(outs)
 
     def train(self, mode=True):
-        super(VisionTransformer, self).train(mode)
+        super().train(mode)
         if mode and self.norm_eval:
             for m in self.modules():
                 if isinstance(m, nn.LayerNorm):
diff --git a/mmseg/models/decode_heads/ann_head.py b/mmseg/models/decode_heads/ann_head.py
index 9cc791b26..2b40ef5aa 100644
--- a/mmseg/models/decode_heads/ann_head.py
+++ b/mmseg/models/decode_heads/ann_head.py
@@ -17,7 +17,7 @@ class PPMConcat(nn.ModuleList):
     """
 
     def __init__(self, pool_scales=(1, 3, 6, 8)):
-        super(PPMConcat, self).__init__(
+        super().__init__(
             [nn.AdaptiveAvgPool2d(pool_scale) for pool_scale in pool_scales])
 
     def forward(self, feats):
@@ -58,7 +58,7 @@ class SelfAttentionBlock(_SelfAttentionBlock):
             query_downsample = nn.MaxPool2d(kernel_size=query_scale)
         else:
             query_downsample = None
-        super(SelfAttentionBlock, self).__init__(
+        super().__init__(
             key_in_channels=low_in_channels,
             query_in_channels=high_in_channels,
             channels=channels,
@@ -100,7 +100,7 @@ class AFNB(nn.Module):
     def __init__(self, low_in_channels, high_in_channels, channels,
                  out_channels, query_scales, key_pool_scales, conv_cfg,
                  norm_cfg, act_cfg):
-        super(AFNB, self).__init__()
+        super().__init__()
         self.stages = nn.ModuleList()
         for query_scale in query_scales:
             self.stages.append(
@@ -150,7 +150,7 @@ class APNB(nn.Module):
 
     def __init__(self, in_channels, channels, out_channels, query_scales,
                  key_pool_scales, conv_cfg, norm_cfg, act_cfg):
-        super(APNB, self).__init__()
+        super().__init__()
         self.stages = nn.ModuleList()
         for query_scale in query_scales:
             self.stages.append(
@@ -201,8 +201,7 @@ class ANNHead(BaseDecodeHead):
                  query_scales=(1, ),
                  key_pool_scales=(1, 3, 6, 8),
                  **kwargs):
-        super(ANNHead, self).__init__(
-            input_transform='multiple_select', **kwargs)
+        super().__init__(input_transform='multiple_select', **kwargs)
         assert len(self.in_channels) == 2
         low_in_channels, high_in_channels = self.in_channels
         self.project_channels = project_channels
diff --git a/mmseg/models/decode_heads/apc_head.py b/mmseg/models/decode_heads/apc_head.py
index 187fdb0e9..728f39659 100644
--- a/mmseg/models/decode_heads/apc_head.py
+++ b/mmseg/models/decode_heads/apc_head.py
@@ -25,7 +25,7 @@ class ACM(nn.Module):
 
     def __init__(self, pool_scale, fusion, in_channels, channels, conv_cfg,
                  norm_cfg, act_cfg):
-        super(ACM, self).__init__()
+        super().__init__()
         self.pool_scale = pool_scale
         self.fusion = fusion
         self.in_channels = in_channels
@@ -123,7 +123,7 @@ class APCHead(BaseDecodeHead):
     """
 
     def __init__(self, pool_scales=(1, 2, 3, 6), fusion=True, **kwargs):
-        super(APCHead, self).__init__(**kwargs)
+        super().__init__(**kwargs)
         assert isinstance(pool_scales, (list, tuple))
         self.pool_scales = pool_scales
         self.fusion = fusion
diff --git a/mmseg/models/decode_heads/aspp_head.py b/mmseg/models/decode_heads/aspp_head.py
index 757e69359..6d7185d7d 100644
--- a/mmseg/models/decode_heads/aspp_head.py
+++ b/mmseg/models/decode_heads/aspp_head.py
@@ -22,7 +22,7 @@ class ASPPModule(nn.ModuleList):
 
     def __init__(self, dilations, in_channels, channels, conv_cfg, norm_cfg,
                  act_cfg):
-        super(ASPPModule, self).__init__()
+        super().__init__()
         self.dilations = dilations
         self.in_channels = in_channels
         self.channels = channels
@@ -63,7 +63,7 @@ class ASPPHead(BaseDecodeHead):
     """
 
     def __init__(self, dilations=(1, 6, 12, 18), **kwargs):
-        super(ASPPHead, self).__init__(**kwargs)
+        super().__init__(**kwargs)
         assert isinstance(dilations, (list, tuple))
         self.dilations = dilations
         self.image_pool = nn.Sequential(
diff --git a/mmseg/models/decode_heads/cascade_decode_head.py b/mmseg/models/decode_heads/cascade_decode_head.py
index 82d6c3af4..fe2bcb930 100644
--- a/mmseg/models/decode_heads/cascade_decode_head.py
+++ b/mmseg/models/decode_heads/cascade_decode_head.py
@@ -13,7 +13,7 @@ class BaseCascadeDecodeHead(BaseDecodeHead, metaclass=ABCMeta):
     :class:`CascadeEncoderDecoder."""
 
     def __init__(self, *args, **kwargs):
-        super(BaseCascadeDecodeHead, self).__init__(*args, **kwargs)
+        super().__init__(*args, **kwargs)
 
     @abstractmethod
     def forward(self, inputs, prev_output):
diff --git a/mmseg/models/decode_heads/cc_head.py b/mmseg/models/decode_heads/cc_head.py
index 03ad3db76..e9075a264 100644
--- a/mmseg/models/decode_heads/cc_head.py
+++ b/mmseg/models/decode_heads/cc_head.py
@@ -26,7 +26,7 @@ class CCHead(FCNHead):
         if CrissCrossAttention is None:
             raise RuntimeError('Please install mmcv-full for '
                                'CrissCrossAttention ops')
-        super(CCHead, self).__init__(num_convs=2, **kwargs)
+        super().__init__(num_convs=2, **kwargs)
         self.recurrence = recurrence
         self.cca = CrissCrossAttention(self.channels)
 
diff --git a/mmseg/models/decode_heads/da_head.py b/mmseg/models/decode_heads/da_head.py
index 6a58e256a..d87214365 100644
--- a/mmseg/models/decode_heads/da_head.py
+++ b/mmseg/models/decode_heads/da_head.py
@@ -21,7 +21,7 @@ class PAM(_SelfAttentionBlock):
     """
 
     def __init__(self, in_channels, channels):
-        super(PAM, self).__init__(
+        super().__init__(
             key_in_channels=in_channels,
             query_in_channels=in_channels,
             channels=channels,
@@ -43,7 +43,7 @@ class PAM(_SelfAttentionBlock):
 
     def forward(self, x):
         """Forward function."""
-        out = super(PAM, self).forward(x, x)
+        out = super().forward(x, x)
 
         out = self.gamma(out) + x
         return out
@@ -53,7 +53,7 @@ class CAM(nn.Module):
     """Channel Attention Module (CAM)"""
 
     def __init__(self):
-        super(CAM, self).__init__()
+        super().__init__()
         self.gamma = Scale(0)
 
     def forward(self, x):
@@ -86,7 +86,7 @@ class DAHead(BaseDecodeHead):
     """
 
     def __init__(self, pam_channels, **kwargs):
-        super(DAHead, self).__init__(**kwargs)
+        super().__init__(**kwargs)
         self.pam_channels = pam_channels
         self.pam_in_conv = ConvModule(
             self.in_channels,
@@ -173,15 +173,12 @@ class DAHead(BaseDecodeHead):
         loss = dict()
         loss.update(
             add_prefix(
-                super(DAHead, self).loss_by_feat(pam_cam_seg_logit,
-                                                 batch_data_samples),
+                super().loss_by_feat(pam_cam_seg_logit, batch_data_samples),
                 'pam_cam'))
         loss.update(
-            add_prefix(
-                super(DAHead, self).loss_by_feat(pam_seg_logit,
-                                                 batch_data_samples), 'pam'))
+            add_prefix(super().loss_by_feat(pam_seg_logit, batch_data_samples),
+                       'pam'))
         loss.update(
-            add_prefix(
-                super(DAHead, self).loss_by_feat(cam_seg_logit,
-                                                 batch_data_samples), 'cam'))
+            add_prefix(super().loss_by_feat(cam_seg_logit, batch_data_samples),
+                       'cam'))
         return loss
diff --git a/mmseg/models/decode_heads/decode_head.py b/mmseg/models/decode_heads/decode_head.py
index 6fdfbba1d..9d81ec237 100644
--- a/mmseg/models/decode_heads/decode_head.py
+++ b/mmseg/models/decode_heads/decode_head.py
@@ -97,7 +97,7 @@ class BaseDecodeHead(BaseModule, metaclass=ABCMeta):
                  align_corners=False,
                  init_cfg=dict(
                      type='Normal', std=0.01, override=dict(name='conv_seg'))):
-        super(BaseDecodeHead, self).__init__(init_cfg)
+        super().__init__(init_cfg)
         self._init_inputs(in_channels, in_index, input_transform)
         self.channels = channels
         self.num_classes = num_classes
diff --git a/mmseg/models/decode_heads/dm_head.py b/mmseg/models/decode_heads/dm_head.py
index 30405e3eb..7694abd8a 100644
--- a/mmseg/models/decode_heads/dm_head.py
+++ b/mmseg/models/decode_heads/dm_head.py
@@ -24,7 +24,7 @@ class DCM(nn.Module):
 
     def __init__(self, filter_size, fusion, in_channels, channels, conv_cfg,
                  norm_cfg, act_cfg):
-        super(DCM, self).__init__()
+        super().__init__()
         self.filter_size = filter_size
         self.fusion = fusion
         self.in_channels = in_channels
@@ -105,7 +105,7 @@ class DMHead(BaseDecodeHead):
     """
 
     def __init__(self, filter_sizes=(1, 3, 5, 7), fusion=False, **kwargs):
-        super(DMHead, self).__init__(**kwargs)
+        super().__init__(**kwargs)
         assert isinstance(filter_sizes, (list, tuple))
         self.filter_sizes = filter_sizes
         self.fusion = fusion
diff --git a/mmseg/models/decode_heads/dnl_head.py b/mmseg/models/decode_heads/dnl_head.py
index 400a17556..248c11814 100644
--- a/mmseg/models/decode_heads/dnl_head.py
+++ b/mmseg/models/decode_heads/dnl_head.py
@@ -111,7 +111,7 @@ class DNLHead(FCNHead):
                  mode='embedded_gaussian',
                  temperature=0.05,
                  **kwargs):
-        super(DNLHead, self).__init__(num_convs=2, **kwargs)
+        super().__init__(num_convs=2, **kwargs)
         self.reduction = reduction
         self.use_scale = use_scale
         self.mode = mode
diff --git a/mmseg/models/decode_heads/dpt_head.py b/mmseg/models/decode_heads/dpt_head.py
index 989b53aa4..d2cfd89da 100644
--- a/mmseg/models/decode_heads/dpt_head.py
+++ b/mmseg/models/decode_heads/dpt_head.py
@@ -30,7 +30,7 @@ class ReassembleBlocks(BaseModule):
                  readout_type='ignore',
                  patch_size=16,
                  init_cfg=None):
-        super(ReassembleBlocks, self).__init__(init_cfg)
+        super().__init__(init_cfg)
 
         assert readout_type in ['ignore', 'add', 'project']
         self.readout_type = readout_type
@@ -116,7 +116,7 @@ class PreActResidualConvUnit(BaseModule):
                  stride=1,
                  dilation=1,
                  init_cfg=None):
-        super(PreActResidualConvUnit, self).__init__(init_cfg)
+        super().__init__(init_cfg)
 
         self.conv1 = ConvModule(
             in_channels,
@@ -168,7 +168,7 @@ class FeatureFusionBlock(BaseModule):
                  expand=False,
                  align_corners=True,
                  init_cfg=None):
-        super(FeatureFusionBlock, self).__init__(init_cfg)
+        super().__init__(init_cfg)
 
         self.in_channels = in_channels
         self.expand = expand
@@ -242,7 +242,7 @@ class DPTHead(BaseDecodeHead):
                  act_cfg=dict(type='ReLU'),
                  norm_cfg=dict(type='BN'),
                  **kwargs):
-        super(DPTHead, self).__init__(**kwargs)
+        super().__init__(**kwargs)
 
         self.in_channels = self.in_channels
         self.expand_channels = expand_channels
diff --git a/mmseg/models/decode_heads/ema_head.py b/mmseg/models/decode_heads/ema_head.py
index d7923f424..ab8dbb0c2 100644
--- a/mmseg/models/decode_heads/ema_head.py
+++ b/mmseg/models/decode_heads/ema_head.py
@@ -30,7 +30,7 @@ class EMAModule(nn.Module):
     """
 
     def __init__(self, channels, num_bases, num_stages, momentum):
-        super(EMAModule, self).__init__()
+        super().__init__()
         assert num_stages >= 1, 'num_stages must be at least 1!'
         self.num_bases = num_bases
         self.num_stages = num_stages
@@ -99,7 +99,7 @@ class EMAHead(BaseDecodeHead):
                  concat_input=True,
                  momentum=0.1,
                  **kwargs):
-        super(EMAHead, self).__init__(**kwargs)
+        super().__init__(**kwargs)
         self.ema_channels = ema_channels
         self.num_bases = num_bases
         self.num_stages = num_stages
diff --git a/mmseg/models/decode_heads/enc_head.py b/mmseg/models/decode_heads/enc_head.py
index cfceb9428..ef48fb699 100644
--- a/mmseg/models/decode_heads/enc_head.py
+++ b/mmseg/models/decode_heads/enc_head.py
@@ -26,7 +26,7 @@ class EncModule(nn.Module):
     """
 
     def __init__(self, in_channels, num_codes, conv_cfg, norm_cfg, act_cfg):
-        super(EncModule, self).__init__()
+        super().__init__()
         self.encoding_project = ConvModule(
             in_channels,
             in_channels,
@@ -90,8 +90,7 @@ class EncHead(BaseDecodeHead):
                      use_sigmoid=True,
                      loss_weight=0.2),
                  **kwargs):
-        super(EncHead, self).__init__(
-            input_transform='multiple_select', **kwargs)
+        super().__init__(input_transform='multiple_select', **kwargs)
         self.use_se_loss = use_se_loss
         self.add_lateral = add_lateral
         self.num_codes = num_codes
@@ -188,8 +187,7 @@ class EncHead(BaseDecodeHead):
         """Compute segmentation and semantic encoding loss."""
         seg_logit, se_seg_logit = seg_logit
         loss = dict()
-        loss.update(
-            super(EncHead, self).loss_by_feat(seg_logit, batch_data_samples))
+        loss.update(super().loss_by_feat(seg_logit, batch_data_samples))
 
         seg_label = self._stack_batch_gt(batch_data_samples)
         se_loss = self.loss_se_decode(
diff --git a/mmseg/models/decode_heads/fcn_head.py b/mmseg/models/decode_heads/fcn_head.py
index 4e3b974a8..341801888 100644
--- a/mmseg/models/decode_heads/fcn_head.py
+++ b/mmseg/models/decode_heads/fcn_head.py
@@ -31,7 +31,7 @@ class FCNHead(BaseDecodeHead):
         self.num_convs = num_convs
         self.concat_input = concat_input
         self.kernel_size = kernel_size
-        super(FCNHead, self).__init__(**kwargs)
+        super().__init__(**kwargs)
         if num_convs == 0:
             assert self.in_channels == self.channels
 
diff --git a/mmseg/models/decode_heads/fpn_head.py b/mmseg/models/decode_heads/fpn_head.py
index a9af1feec..25f481fe8 100644
--- a/mmseg/models/decode_heads/fpn_head.py
+++ b/mmseg/models/decode_heads/fpn_head.py
@@ -22,8 +22,7 @@ class FPNHead(BaseDecodeHead):
     """
 
     def __init__(self, feature_strides, **kwargs):
-        super(FPNHead, self).__init__(
-            input_transform='multiple_select', **kwargs)
+        super().__init__(input_transform='multiple_select', **kwargs)
         assert len(feature_strides) == len(self.in_channels)
         assert min(feature_strides) == feature_strides[0]
         self.feature_strides = feature_strides
diff --git a/mmseg/models/decode_heads/gc_head.py b/mmseg/models/decode_heads/gc_head.py
index e89b92d8b..14f0ef021 100644
--- a/mmseg/models/decode_heads/gc_head.py
+++ b/mmseg/models/decode_heads/gc_head.py
@@ -26,7 +26,7 @@ class GCHead(FCNHead):
                  pooling_type='att',
                  fusion_types=('channel_add', ),
                  **kwargs):
-        super(GCHead, self).__init__(num_convs=2, **kwargs)
+        super().__init__(num_convs=2, **kwargs)
         self.ratio = ratio
         self.pooling_type = pooling_type
         self.fusion_types = fusion_types
diff --git a/mmseg/models/decode_heads/isa_head.py b/mmseg/models/decode_heads/isa_head.py
index 3769bdff4..355f215f3 100644
--- a/mmseg/models/decode_heads/isa_head.py
+++ b/mmseg/models/decode_heads/isa_head.py
@@ -22,7 +22,7 @@ class SelfAttentionBlock(_SelfAttentionBlock):
     """
 
     def __init__(self, in_channels, channels, conv_cfg, norm_cfg, act_cfg):
-        super(SelfAttentionBlock, self).__init__(
+        super().__init__(
             key_in_channels=in_channels,
             query_in_channels=in_channels,
             channels=channels,
@@ -51,7 +51,7 @@ class SelfAttentionBlock(_SelfAttentionBlock):
 
     def forward(self, x):
         """Forward function."""
-        context = super(SelfAttentionBlock, self).forward(x, x)
+        context = super().forward(x, x)
         return self.output_project(context)
 
 
@@ -68,7 +68,7 @@ class ISAHead(BaseDecodeHead):
     """
 
     def __init__(self, isa_channels, down_factor=(8, 8), **kwargs):
-        super(ISAHead, self).__init__(**kwargs)
+        super().__init__(**kwargs)
         self.down_factor = down_factor
 
         self.in_conv = ConvModule(
diff --git a/mmseg/models/decode_heads/knet_head.py b/mmseg/models/decode_heads/knet_head.py
index 1b19b4a0f..181ae0216 100644
--- a/mmseg/models/decode_heads/knet_head.py
+++ b/mmseg/models/decode_heads/knet_head.py
@@ -48,7 +48,7 @@ class KernelUpdator(nn.Module):
             norm_cfg=dict(type='LN'),
             act_cfg=dict(type='ReLU', inplace=True),
     ):
-        super(KernelUpdator, self).__init__()
+        super().__init__()
         self.in_channels = in_channels
         self.feat_channels = feat_channels
         self.out_channels_raw = out_channels
@@ -213,7 +213,7 @@ class KernelUpdateHead(nn.Module):
                      out_channels=256,
                      act_cfg=dict(type='ReLU', inplace=True),
                      norm_cfg=dict(type='LN'))):
-        super(KernelUpdateHead, self).__init__()
+        super().__init__()
         self.num_classes = num_classes
         self.in_channels = in_channels
         self.out_channels = out_channels
diff --git a/mmseg/models/decode_heads/lraspp_head.py b/mmseg/models/decode_heads/lraspp_head.py
index f8c693bc4..ba2465f27 100644
--- a/mmseg/models/decode_heads/lraspp_head.py
+++ b/mmseg/models/decode_heads/lraspp_head.py
@@ -22,7 +22,7 @@ class LRASPPHead(BaseDecodeHead):
     """
 
     def __init__(self, branch_channels=(32, 64), **kwargs):
-        super(LRASPPHead, self).__init__(**kwargs)
+        super().__init__(**kwargs)
         if self.input_transform != 'multiple_select':
             raise ValueError('in Lite R-ASPP (LRASPP) head, input_transform '
                              f'must be \'multiple_select\'. But received '
diff --git a/mmseg/models/decode_heads/nl_head.py b/mmseg/models/decode_heads/nl_head.py
index 7903f1ace..0ffcc2a2f 100644
--- a/mmseg/models/decode_heads/nl_head.py
+++ b/mmseg/models/decode_heads/nl_head.py
@@ -26,7 +26,7 @@ class NLHead(FCNHead):
                  use_scale=True,
                  mode='embedded_gaussian',
                  **kwargs):
-        super(NLHead, self).__init__(num_convs=2, **kwargs)
+        super().__init__(num_convs=2, **kwargs)
         self.reduction = reduction
         self.use_scale = use_scale
         self.mode = mode
diff --git a/mmseg/models/decode_heads/ocr_head.py b/mmseg/models/decode_heads/ocr_head.py
index 57d91613d..9afe37beb 100644
--- a/mmseg/models/decode_heads/ocr_head.py
+++ b/mmseg/models/decode_heads/ocr_head.py
@@ -18,7 +18,7 @@ class SpatialGatherModule(nn.Module):
     """
 
     def __init__(self, scale):
-        super(SpatialGatherModule, self).__init__()
+        super().__init__()
         self.scale = scale
 
     def forward(self, feats, probs):
@@ -46,7 +46,7 @@ class ObjectAttentionBlock(_SelfAttentionBlock):
             query_downsample = nn.MaxPool2d(kernel_size=scale)
         else:
             query_downsample = None
-        super(ObjectAttentionBlock, self).__init__(
+        super().__init__(
             key_in_channels=in_channels,
             query_in_channels=in_channels,
             channels=channels,
@@ -73,8 +73,7 @@ class ObjectAttentionBlock(_SelfAttentionBlock):
 
     def forward(self, query_feats, key_feats):
         """Forward function."""
-        context = super(ObjectAttentionBlock,
-                        self).forward(query_feats, key_feats)
+        context = super().forward(query_feats, key_feats)
         output = self.bottleneck(torch.cat([context, query_feats], dim=1))
         if self.query_downsample is not None:
             output = resize(query_feats)
@@ -96,7 +95,7 @@ class OCRHead(BaseCascadeDecodeHead):
     """
 
     def __init__(self, ocr_channels, scale=1, **kwargs):
-        super(OCRHead, self).__init__(**kwargs)
+        super().__init__(**kwargs)
         self.ocr_channels = ocr_channels
         self.scale = scale
         self.object_context_block = ObjectAttentionBlock(
diff --git a/mmseg/models/decode_heads/point_head.py b/mmseg/models/decode_heads/point_head.py
index a57d531bd..e8e433d66 100644
--- a/mmseg/models/decode_heads/point_head.py
+++ b/mmseg/models/decode_heads/point_head.py
@@ -74,7 +74,7 @@ class PointHead(BaseCascadeDecodeHead):
                  norm_cfg=None,
                  act_cfg=dict(type='ReLU', inplace=False),
                  **kwargs):
-        super(PointHead, self).__init__(
+        super().__init__(
             input_transform='multiple_select',
             conv_cfg=conv_cfg,
             norm_cfg=norm_cfg,
diff --git a/mmseg/models/decode_heads/psa_head.py b/mmseg/models/decode_heads/psa_head.py
index cf3749f9c..13ee5c58a 100644
--- a/mmseg/models/decode_heads/psa_head.py
+++ b/mmseg/models/decode_heads/psa_head.py
@@ -43,7 +43,7 @@ class PSAHead(BaseDecodeHead):
                  **kwargs):
         if PSAMask is None:
             raise RuntimeError('Please install mmcv-full for PSAMask ops')
-        super(PSAHead, self).__init__(**kwargs)
+        super().__init__(**kwargs)
         assert psa_type in ['collect', 'distribute', 'bi-direction']
         self.psa_type = psa_type
         self.compact = compact
diff --git a/mmseg/models/decode_heads/psp_head.py b/mmseg/models/decode_heads/psp_head.py
index c22337fde..a40ec41de 100644
--- a/mmseg/models/decode_heads/psp_head.py
+++ b/mmseg/models/decode_heads/psp_head.py
@@ -24,7 +24,7 @@ class PPM(nn.ModuleList):
 
     def __init__(self, pool_scales, in_channels, channels, conv_cfg, norm_cfg,
                  act_cfg, align_corners, **kwargs):
-        super(PPM, self).__init__()
+        super().__init__()
         self.pool_scales = pool_scales
         self.align_corners = align_corners
         self.in_channels = in_channels
@@ -72,7 +72,7 @@ class PSPHead(BaseDecodeHead):
     """
 
     def __init__(self, pool_scales=(1, 2, 3, 6), **kwargs):
-        super(PSPHead, self).__init__(**kwargs)
+        super().__init__(**kwargs)
         assert isinstance(pool_scales, (list, tuple))
         self.pool_scales = pool_scales
         self.psp_modules = PPM(
diff --git a/mmseg/models/decode_heads/segmenter_mask_head.py b/mmseg/models/decode_heads/segmenter_mask_head.py
index bcb72ba36..85d27735b 100644
--- a/mmseg/models/decode_heads/segmenter_mask_head.py
+++ b/mmseg/models/decode_heads/segmenter_mask_head.py
@@ -61,8 +61,7 @@ class SegmenterMaskTransformerHead(BaseDecodeHead):
             init_std=0.02,
             **kwargs,
     ):
-        super(SegmenterMaskTransformerHead, self).__init__(
-            in_channels=in_channels, **kwargs)
+        super().__init__(in_channels=in_channels, **kwargs)
 
         dpr = [x.item() for x in torch.linspace(0, drop_path_rate, num_layers)]
         self.layers = ModuleList()
diff --git a/mmseg/models/decode_heads/sep_aspp_head.py b/mmseg/models/decode_heads/sep_aspp_head.py
index a1ffae708..9dba68c9e 100644
--- a/mmseg/models/decode_heads/sep_aspp_head.py
+++ b/mmseg/models/decode_heads/sep_aspp_head.py
@@ -13,7 +13,7 @@ class DepthwiseSeparableASPPModule(ASPPModule):
     conv."""
 
     def __init__(self, **kwargs):
-        super(DepthwiseSeparableASPPModule, self).__init__(**kwargs)
+        super().__init__(**kwargs)
         for i, dilation in enumerate(self.dilations):
             if dilation > 1:
                 self[i] = DepthwiseSeparableConvModule(
@@ -41,7 +41,7 @@ class DepthwiseSeparableASPPHead(ASPPHead):
     """
 
     def __init__(self, c1_in_channels, c1_channels, **kwargs):
-        super(DepthwiseSeparableASPPHead, self).__init__(**kwargs)
+        super().__init__(**kwargs)
         assert c1_in_channels >= 0
         self.aspp_modules = DepthwiseSeparableASPPModule(
             dilations=self.dilations,
diff --git a/mmseg/models/decode_heads/sep_fcn_head.py b/mmseg/models/decode_heads/sep_fcn_head.py
index 5c8b79bd0..3b15983bc 100644
--- a/mmseg/models/decode_heads/sep_fcn_head.py
+++ b/mmseg/models/decode_heads/sep_fcn_head.py
@@ -32,7 +32,7 @@ class DepthwiseSeparableFCNHead(FCNHead):
     """
 
     def __init__(self, dw_act_cfg=None, **kwargs):
-        super(DepthwiseSeparableFCNHead, self).__init__(**kwargs)
+        super().__init__(**kwargs)
         self.convs[0] = DepthwiseSeparableConvModule(
             self.in_channels,
             self.channels,
diff --git a/mmseg/models/decode_heads/setr_mla_head.py b/mmseg/models/decode_heads/setr_mla_head.py
index 887e11bc2..1975991a6 100644
--- a/mmseg/models/decode_heads/setr_mla_head.py
+++ b/mmseg/models/decode_heads/setr_mla_head.py
@@ -21,8 +21,7 @@ class SETRMLAHead(BaseDecodeHead):
     """
 
     def __init__(self, mla_channels=128, up_scale=4, **kwargs):
-        super(SETRMLAHead, self).__init__(
-            input_transform='multiple_select', **kwargs)
+        super().__init__(input_transform='multiple_select', **kwargs)
         self.mla_channels = mla_channels
 
         num_inputs = len(self.in_channels)
diff --git a/mmseg/models/decode_heads/setr_up_head.py b/mmseg/models/decode_heads/setr_up_head.py
index 151e9ebce..9c796d816 100644
--- a/mmseg/models/decode_heads/setr_up_head.py
+++ b/mmseg/models/decode_heads/setr_up_head.py
@@ -41,7 +41,7 @@ class SETRUPHead(BaseDecodeHead):
 
         assert kernel_size in [1, 3], 'kernel_size must be 1 or 3.'
 
-        super(SETRUPHead, self).__init__(init_cfg=init_cfg, **kwargs)
+        super().__init__(init_cfg=init_cfg, **kwargs)
 
         assert isinstance(self.in_channels, int)
 
diff --git a/mmseg/models/decode_heads/stdc_head.py b/mmseg/models/decode_heads/stdc_head.py
index 0314a0ebd..1c1c21e30 100644
--- a/mmseg/models/decode_heads/stdc_head.py
+++ b/mmseg/models/decode_heads/stdc_head.py
@@ -21,7 +21,7 @@ class STDCHead(FCNHead):
     """
 
     def __init__(self, boundary_threshold=0.1, **kwargs):
-        super(STDCHead, self).__init__(**kwargs)
+        super().__init__(**kwargs)
         self.boundary_threshold = boundary_threshold
         # Using register buffer to make laplacian kernel on the same
         # device of `seg_label`.
@@ -93,6 +93,5 @@ class STDCHead(FCNHead):
             seg_data_sample.gt_sem_seg = PixelData(data=label)
             batch_sample_list.append(seg_data_sample)
 
-        loss = super(STDCHead, self).loss_by_feat(seg_logits,
-                                                  batch_sample_list)
+        loss = super().loss_by_feat(seg_logits, batch_sample_list)
         return loss
diff --git a/mmseg/models/decode_heads/uper_head.py b/mmseg/models/decode_heads/uper_head.py
index 651236b20..b1ccc3173 100644
--- a/mmseg/models/decode_heads/uper_head.py
+++ b/mmseg/models/decode_heads/uper_head.py
@@ -22,8 +22,7 @@ class UPerHead(BaseDecodeHead):
     """
 
     def __init__(self, pool_scales=(1, 2, 3, 6), **kwargs):
-        super(UPerHead, self).__init__(
-            input_transform='multiple_select', **kwargs)
+        super().__init__(input_transform='multiple_select', **kwargs)
         # PSP Module
         self.psp_modules = PPM(
             pool_scales,
diff --git a/mmseg/models/losses/cross_entropy_loss.py b/mmseg/models/losses/cross_entropy_loss.py
index e607248fb..770b99748 100644
--- a/mmseg/models/losses/cross_entropy_loss.py
+++ b/mmseg/models/losses/cross_entropy_loss.py
@@ -223,7 +223,7 @@ class CrossEntropyLoss(nn.Module):
                  loss_weight=1.0,
                  loss_name='loss_ce',
                  avg_non_ignore=False):
-        super(CrossEntropyLoss, self).__init__()
+        super().__init__()
         assert (use_sigmoid is False) or (use_mask is False)
         self.use_sigmoid = use_sigmoid
         self.use_mask = use_mask
diff --git a/mmseg/models/losses/dice_loss.py b/mmseg/models/losses/dice_loss.py
index 4a98aaee9..2ee89a81f 100644
--- a/mmseg/models/losses/dice_loss.py
+++ b/mmseg/models/losses/dice_loss.py
@@ -80,7 +80,7 @@ class DiceLoss(nn.Module):
                  ignore_index=255,
                  loss_name='loss_dice',
                  **kwards):
-        super(DiceLoss, self).__init__()
+        super().__init__()
         self.smooth = smooth
         self.exponent = exponent
         self.reduction = reduction
diff --git a/mmseg/models/losses/focal_loss.py b/mmseg/models/losses/focal_loss.py
index cd7eff4f6..299adc054 100644
--- a/mmseg/models/losses/focal_loss.py
+++ b/mmseg/models/losses/focal_loss.py
@@ -172,7 +172,7 @@ class FocalLoss(nn.Module):
                 loss item to be included into the backward graph, `loss_` must
                 be the prefix of the name. Defaults to 'loss_focal'.
         """
-        super(FocalLoss, self).__init__()
+        super().__init__()
         assert use_sigmoid is True, \
             'AssertionError: Only sigmoid focal loss supported now.'
         assert reduction in ('none', 'mean', 'sum'), \
diff --git a/mmseg/models/losses/lovasz_loss.py b/mmseg/models/losses/lovasz_loss.py
index e63a0ab8f..b47f9d8a1 100644
--- a/mmseg/models/losses/lovasz_loss.py
+++ b/mmseg/models/losses/lovasz_loss.py
@@ -257,7 +257,7 @@ class LovaszLoss(nn.Module):
                  class_weight=None,
                  loss_weight=1.0,
                  loss_name='loss_lovasz'):
-        super(LovaszLoss, self).__init__()
+        super().__init__()
         assert loss_type in ('binary', 'multi_class'), "loss_type should be \
                                                     'binary' or 'multi_class'."
 
diff --git a/mmseg/models/losses/tversky_loss.py b/mmseg/models/losses/tversky_loss.py
index 4ad14f783..bfca1af66 100644
--- a/mmseg/models/losses/tversky_loss.py
+++ b/mmseg/models/losses/tversky_loss.py
@@ -88,7 +88,7 @@ class TverskyLoss(nn.Module):
                  alpha=0.3,
                  beta=0.7,
                  loss_name='loss_tversky'):
-        super(TverskyLoss, self).__init__()
+        super().__init__()
         self.smooth = smooth
         self.class_weight = get_class_weight(class_weight)
         self.loss_weight = loss_weight
diff --git a/mmseg/models/necks/featurepyramid.py b/mmseg/models/necks/featurepyramid.py
index 40453653d..dc1250d39 100644
--- a/mmseg/models/necks/featurepyramid.py
+++ b/mmseg/models/necks/featurepyramid.py
@@ -23,7 +23,7 @@ class Feature2Pyramid(nn.Module):
                  embed_dim,
                  rescales=[4, 2, 1, 0.5],
                  norm_cfg=dict(type='SyncBN', requires_grad=True)):
-        super(Feature2Pyramid, self).__init__()
+        super().__init__()
         self.rescales = rescales
         self.upsample_4x = None
         for k in self.rescales:
diff --git a/mmseg/models/necks/fpn.py b/mmseg/models/necks/fpn.py
index 98fb650f5..ddab74c00 100644
--- a/mmseg/models/necks/fpn.py
+++ b/mmseg/models/necks/fpn.py
@@ -80,7 +80,7 @@ class FPN(BaseModule):
                  upsample_cfg=dict(mode='nearest'),
                  init_cfg=dict(
                      type='Xavier', layer='Conv2d', distribution='uniform')):
-        super(FPN, self).__init__(init_cfg)
+        super().__init__(init_cfg)
         assert isinstance(in_channels, list)
         self.in_channels = in_channels
         self.out_channels = out_channels
diff --git a/mmseg/models/necks/ic_neck.py b/mmseg/models/necks/ic_neck.py
index c554d227b..9763541e0 100644
--- a/mmseg/models/necks/ic_neck.py
+++ b/mmseg/models/necks/ic_neck.py
@@ -42,7 +42,7 @@ class CascadeFeatureFusion(BaseModule):
                  act_cfg=dict(type='ReLU'),
                  align_corners=False,
                  init_cfg=None):
-        super(CascadeFeatureFusion, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         self.align_corners = align_corners
         self.conv_low = ConvModule(
             low_channels,
@@ -108,7 +108,7 @@ class ICNeck(BaseModule):
                  act_cfg=dict(type='ReLU'),
                  align_corners=False,
                  init_cfg=None):
-        super(ICNeck, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         assert len(in_channels) == 3, 'Length of input channels \
                                         must be 3!'
 
diff --git a/mmseg/models/necks/jpu.py b/mmseg/models/necks/jpu.py
index 6aad895c3..3ea0fe218 100644
--- a/mmseg/models/necks/jpu.py
+++ b/mmseg/models/necks/jpu.py
@@ -51,7 +51,7 @@ class JPU(BaseModule):
                  norm_cfg=dict(type='BN'),
                  act_cfg=dict(type='ReLU'),
                  init_cfg=None):
-        super(JPU, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
         assert isinstance(in_channels, tuple)
         assert isinstance(dilations, tuple)
         self.in_channels = in_channels
diff --git a/mmseg/models/necks/mla_neck.py b/mmseg/models/necks/mla_neck.py
index 64a409239..db250aefb 100644
--- a/mmseg/models/necks/mla_neck.py
+++ b/mmseg/models/necks/mla_neck.py
@@ -12,7 +12,7 @@ class MLAModule(nn.Module):
                  out_channels=256,
                  norm_cfg=None,
                  act_cfg=None):
-        super(MLAModule, self).__init__()
+        super().__init__()
         self.channel_proj = nn.ModuleList()
         for i in range(len(in_channels)):
             self.channel_proj.append(
@@ -83,7 +83,7 @@ class MLANeck(nn.Module):
                  norm_layer=dict(type='LN', eps=1e-6, requires_grad=True),
                  norm_cfg=None,
                  act_cfg=None):
-        super(MLANeck, self).__init__()
+        super().__init__()
         assert isinstance(in_channels, list)
         self.in_channels = in_channels
         self.out_channels = out_channels
diff --git a/mmseg/models/necks/multilevel_neck.py b/mmseg/models/necks/multilevel_neck.py
index 3f76c5e6a..c997125f2 100644
--- a/mmseg/models/necks/multilevel_neck.py
+++ b/mmseg/models/necks/multilevel_neck.py
@@ -29,7 +29,7 @@ class MultiLevelNeck(nn.Module):
                  scales=[0.5, 1, 2, 4],
                  norm_cfg=None,
                  act_cfg=None):
-        super(MultiLevelNeck, self).__init__()
+        super().__init__()
         assert isinstance(in_channels, list)
         self.in_channels = in_channels
         self.out_channels = out_channels
diff --git a/mmseg/models/segmentors/base.py b/mmseg/models/segmentors/base.py
index d303bdec4..8ae713f8f 100644
--- a/mmseg/models/segmentors/base.py
+++ b/mmseg/models/segmentors/base.py
@@ -27,7 +27,7 @@ class BaseSegmentor(BaseModel, metaclass=ABCMeta):
     def __init__(self,
                  data_preprocessor: OptConfigType = None,
                  init_cfg: OptMultiConfig = None):
-        super(BaseSegmentor, self).__init__(
+        super().__init__(
             data_preprocessor=data_preprocessor, init_cfg=init_cfg)
 
     @property
diff --git a/mmseg/models/segmentors/cascade_encoder_decoder.py b/mmseg/models/segmentors/cascade_encoder_decoder.py
index 33bcbddd8..f76e66f93 100644
--- a/mmseg/models/segmentors/cascade_encoder_decoder.py
+++ b/mmseg/models/segmentors/cascade_encoder_decoder.py
@@ -48,7 +48,7 @@ class CascadeEncoderDecoder(EncoderDecoder):
                  pretrained: Optional[str] = None,
                  init_cfg: OptMultiConfig = None):
         self.num_stages = num_stages
-        super(CascadeEncoderDecoder, self).__init__(
+        super().__init__(
             backbone=backbone,
             decode_head=decode_head,
             neck=neck,
diff --git a/mmseg/models/segmentors/encoder_decoder.py b/mmseg/models/segmentors/encoder_decoder.py
index 0f678957d..cf99ecf63 100644
--- a/mmseg/models/segmentors/encoder_decoder.py
+++ b/mmseg/models/segmentors/encoder_decoder.py
@@ -78,7 +78,7 @@ class EncoderDecoder(BaseSegmentor):
                  data_preprocessor: OptConfigType = None,
                  pretrained: Optional[str] = None,
                  init_cfg: OptMultiConfig = None):
-        super(EncoderDecoder, self).__init__(
+        super().__init__(
             data_preprocessor=data_preprocessor, init_cfg=init_cfg)
         if pretrained is not None:
             assert backbone.get('pretrained') is None, \
diff --git a/mmseg/models/utils/embed.py b/mmseg/models/utils/embed.py
index adabcf29c..aef0a40b0 100644
--- a/mmseg/models/utils/embed.py
+++ b/mmseg/models/utils/embed.py
@@ -42,7 +42,7 @@ class AdaptivePadding(nn.Module):
 
     def __init__(self, kernel_size=1, stride=1, dilation=1, padding='corner'):
 
-        super(AdaptivePadding, self).__init__()
+        super().__init__()
 
         assert padding in ('same', 'corner')
 
@@ -120,7 +120,7 @@ class PatchEmbed(BaseModule):
                  norm_cfg=None,
                  input_size=None,
                  init_cfg=None):
-        super(PatchEmbed, self).__init__(init_cfg=init_cfg)
+        super().__init__(init_cfg=init_cfg)
 
         self.embed_dims = embed_dims
         if stride is None:
diff --git a/mmseg/models/utils/encoding.py b/mmseg/models/utils/encoding.py
index f397cc54e..ee4f0574f 100644
--- a/mmseg/models/utils/encoding.py
+++ b/mmseg/models/utils/encoding.py
@@ -16,7 +16,7 @@ class Encoding(nn.Module):
     """
 
     def __init__(self, channels, num_codes):
-        super(Encoding, self).__init__()
+        super().__init__()
         # init codewords and smoothing factor
         self.channels, self.num_codes = channels, num_codes
         std = 1. / ((num_codes * channels)**0.5)
diff --git a/mmseg/models/utils/inverted_residual.py b/mmseg/models/utils/inverted_residual.py
index c9cda7682..56190b3bf 100644
--- a/mmseg/models/utils/inverted_residual.py
+++ b/mmseg/models/utils/inverted_residual.py
@@ -40,7 +40,7 @@ class InvertedResidual(nn.Module):
                  act_cfg=dict(type='ReLU6'),
                  with_cp=False,
                  **kwargs):
-        super(InvertedResidual, self).__init__()
+        super().__init__()
         self.stride = stride
         assert stride in [1, 2], f'stride must in [1, 2]. ' \
             f'But received {stride}.'
@@ -138,7 +138,7 @@ class InvertedResidualV3(nn.Module):
                  norm_cfg=dict(type='BN'),
                  act_cfg=dict(type='ReLU'),
                  with_cp=False):
-        super(InvertedResidualV3, self).__init__()
+        super().__init__()
         self.with_res_shortcut = (stride == 1 and in_channels == out_channels)
         assert stride in [1, 2]
         self.with_cp = with_cp
diff --git a/mmseg/models/utils/res_layer.py b/mmseg/models/utils/res_layer.py
index 2847d189b..3dd7a6f75 100644
--- a/mmseg/models/utils/res_layer.py
+++ b/mmseg/models/utils/res_layer.py
@@ -93,4 +93,4 @@ class ResLayer(Sequential):
                     conv_cfg=conv_cfg,
                     norm_cfg=norm_cfg,
                     **kwargs))
-        super(ResLayer, self).__init__(*layers)
+        super().__init__(*layers)
diff --git a/mmseg/models/utils/se_layer.py b/mmseg/models/utils/se_layer.py
index 34085753e..0ff632cfe 100644
--- a/mmseg/models/utils/se_layer.py
+++ b/mmseg/models/utils/se_layer.py
@@ -30,7 +30,7 @@ class SELayer(nn.Module):
                  conv_cfg=None,
                  act_cfg=(dict(type='ReLU'),
                           dict(type='HSigmoid', bias=3.0, divisor=6.0))):
-        super(SELayer, self).__init__()
+        super().__init__()
         if isinstance(act_cfg, dict):
             act_cfg = (act_cfg, act_cfg)
         assert len(act_cfg) == 2
diff --git a/mmseg/models/utils/self_attention_block.py b/mmseg/models/utils/self_attention_block.py
index 245de62b1..5bb6e8284 100644
--- a/mmseg/models/utils/self_attention_block.py
+++ b/mmseg/models/utils/self_attention_block.py
@@ -36,7 +36,7 @@ class SelfAttentionBlock(nn.Module):
                  key_downsample, key_query_num_convs, value_out_num_convs,
                  key_query_norm, value_out_norm, matmul_norm, with_out,
                  conv_cfg, norm_cfg, act_cfg):
-        super(SelfAttentionBlock, self).__init__()
+        super().__init__()
         if share_key_query:
             assert key_in_channels == query_in_channels
         self.key_in_channels = key_in_channels
diff --git a/mmseg/models/utils/up_conv_block.py b/mmseg/models/utils/up_conv_block.py
index d8396d9c2..4fa3b598d 100644
--- a/mmseg/models/utils/up_conv_block.py
+++ b/mmseg/models/utils/up_conv_block.py
@@ -57,7 +57,7 @@ class UpConvBlock(nn.Module):
                  upsample_cfg=dict(type='InterpConv'),
                  dcn=None,
                  plugins=None):
-        super(UpConvBlock, self).__init__()
+        super().__init__()
         assert dcn is None, 'Not implemented yet.'
         assert plugins is None, 'Not implemented yet.'
 
diff --git a/mmseg/models/utils/wrappers.py b/mmseg/models/utils/wrappers.py
index ce67e4beb..abbd0c029 100644
--- a/mmseg/models/utils/wrappers.py
+++ b/mmseg/models/utils/wrappers.py
@@ -34,7 +34,7 @@ class Upsample(nn.Module):
                  scale_factor=None,
                  mode='nearest',
                  align_corners=None):
-        super(Upsample, self).__init__()
+        super().__init__()
         self.size = size
         if isinstance(scale_factor, tuple):
             self.scale_factor = tuple(float(factor) for factor in scale_factor)
diff --git a/mmseg/structures/sampler/ohem_pixel_sampler.py b/mmseg/structures/sampler/ohem_pixel_sampler.py
index e5016ffb6..a974273ca 100644
--- a/mmseg/structures/sampler/ohem_pixel_sampler.py
+++ b/mmseg/structures/sampler/ohem_pixel_sampler.py
@@ -23,7 +23,7 @@ class OHEMPixelSampler(BasePixelSampler):
     """
 
     def __init__(self, context, thresh=None, min_kept=100000):
-        super(OHEMPixelSampler, self).__init__()
+        super().__init__()
         self.context = context
         assert min_kept > 1
         self.thresh = thresh
diff --git a/mmseg/utils/collect_env.py b/mmseg/utils/collect_env.py
index 22b56992d..d5d6ea290 100644
--- a/mmseg/utils/collect_env.py
+++ b/mmseg/utils/collect_env.py
@@ -15,4 +15,4 @@ def collect_env():
 
 if __name__ == '__main__':
     for name, val in collect_env().items():
-        print('{}: {}'.format(name, val))
+        print(f'{name}: {val}')
diff --git a/mmseg/utils/misc.py b/mmseg/utils/misc.py
index 89469ba41..4413234fb 100644
--- a/mmseg/utils/misc.py
+++ b/mmseg/utils/misc.py
@@ -52,12 +52,12 @@ def stack_batch(inputs: List[torch.Tensor],
     """
     assert isinstance(inputs, list), \
         f'Expected input type to be list, but got {type(inputs)}'
-    assert len(set([tensor.ndim for tensor in inputs])) == 1, \
+    assert len({tensor.ndim for tensor in inputs}) == 1, \
         f'Expected the dimensions of all inputs must be the same, ' \
         f'but got {[tensor.ndim for tensor in inputs]}'
     assert inputs[0].ndim == 3, f'Expected tensor dimension to be 3, ' \
         f'but got {inputs[0].ndim}'
-    assert len(set([tensor.shape[0] for tensor in inputs])) == 1, \
+    assert len({tensor.shape[0] for tensor in inputs}) == 1, \
         f'Expected the channels of all inputs must be the same, ' \
         f'but got {[tensor.shape[0] for tensor in inputs]}'
 
diff --git a/setup.py b/setup.py
index ad09e6ce7..79ecaa54b 100755
--- a/setup.py
+++ b/setup.py
@@ -18,7 +18,7 @@ version_file = 'mmseg/version.py'
 
 
 def get_version():
-    with open(version_file, 'r') as f:
+    with open(version_file) as f:
         exec(compile(f.read(), version_file, 'exec'))
     return locals()['__version__']
 
@@ -74,12 +74,11 @@ def parse_requirements(fname='requirements.txt', with_version=True):
             yield info
 
     def parse_require_file(fpath):
-        with open(fpath, 'r') as f:
+        with open(fpath) as f:
             for line in f.readlines():
                 line = line.strip()
                 if line and not line.startswith('#'):
-                    for info in parse_line(line):
-                        yield info
+                    yield from parse_line(line)
 
     def gen_packages_items():
         if exists(require_fpath):
diff --git a/tests/test_config.py b/tests/test_config.py
index d644a34ba..6e044967d 100644
--- a/tests/test_config.py
+++ b/tests/test_config.py
@@ -31,7 +31,7 @@ def test_config_build_segmentor():
     """Test that all segmentation models defined in the configs can be
     initialized."""
     config_dpath = _get_config_directory()
-    print('Found config_dpath = {!r}'.format(config_dpath))
+    print(f'Found config_dpath = {config_dpath!r}')
 
     config_fpaths = []
     # one config each sub folder
@@ -42,20 +42,20 @@ def test_config_build_segmentor():
     config_fpaths = [p for p in config_fpaths if p.find('_base_') == -1]
     config_names = [relpath(p, config_dpath) for p in config_fpaths]
 
-    print('Using {} config files'.format(len(config_names)))
+    print(f'Using {len(config_names)} config files')
 
     for config_fname in config_names:
         config_fpath = join(config_dpath, config_fname)
         config_mod = Config.fromfile(config_fpath)
 
         config_mod.model
-        print('Building segmentor, config_fpath = {!r}'.format(config_fpath))
+        print(f'Building segmentor, config_fpath = {config_fpath!r}')
 
         # Remove pretrained keys to allow for testing in an offline environment
         if 'pretrained' in config_mod.model:
             config_mod.model['pretrained'] = None
 
-        print('building {}'.format(config_fname))
+        print(f'building {config_fname}')
         segmentor = build_segmentor(config_mod.model)
         assert segmentor is not None
 
@@ -72,19 +72,18 @@ def test_config_data_pipeline():
 
     register_all_modules()
     config_dpath = _get_config_directory()
-    print('Found config_dpath = {!r}'.format(config_dpath))
+    print(f'Found config_dpath = {config_dpath!r}')
 
     import glob
     config_fpaths = list(glob.glob(join(config_dpath, '**', '*.py')))
     config_fpaths = [p for p in config_fpaths if p.find('_base_') == -1]
     config_names = [relpath(p, config_dpath) for p in config_fpaths]
 
-    print('Using {} config files'.format(len(config_names)))
+    print(f'Using {len(config_names)} config files')
 
     for config_fname in config_names:
         config_fpath = join(config_dpath, config_fname)
-        print(
-            'Building data pipeline, config_fpath = {!r}'.format(config_fpath))
+        print(f'Building data pipeline, config_fpath = {config_fpath!r}')
         config_mod = Config.fromfile(config_fpath)
 
         # remove loading pipeline
@@ -112,7 +111,7 @@ def test_config_data_pipeline():
             gt_seg_map=seg)
         results['seg_fields'] = ['gt_seg_map']
 
-        print('Test training data pipeline: \n{!r}'.format(train_pipeline))
+        print(f'Test training data pipeline: \n{train_pipeline!r}')
         output_results = train_pipeline(results)
         assert output_results is not None
 
@@ -123,7 +122,7 @@ def test_config_data_pipeline():
             img_shape=img.shape,
             ori_shape=img.shape,
         )
-        print('Test testing data pipeline: \n{!r}'.format(test_pipeline))
+        print(f'Test testing data pipeline: \n{test_pipeline!r}')
         output_results = test_pipeline(results)
         assert output_results is not None
 
diff --git a/tests/test_datasets/test_dataset_builder.py b/tests/test_datasets/test_dataset_builder.py
index 5e70726aa..099c5b1df 100644
--- a/tests/test_datasets/test_dataset_builder.py
+++ b/tests/test_datasets/test_dataset_builder.py
@@ -11,7 +11,7 @@ register_all_modules()
 
 
 @DATASETS.register_module()
-class ToyDataset(object):
+class ToyDataset:
 
     def __init__(self, cnt=0):
         self.cnt = cnt
diff --git a/tests/test_datasets/test_loading.py b/tests/test_datasets/test_loading.py
index bccba9379..a774d5a5b 100644
--- a/tests/test_datasets/test_loading.py
+++ b/tests/test_datasets/test_loading.py
@@ -10,7 +10,7 @@ from mmcv.transforms import LoadImageFromFile
 from mmseg.datasets.transforms import LoadAnnotations, LoadImageFromNDArray
 
 
-class TestLoading(object):
+class TestLoading:
 
     @classmethod
     def setup_class(cls):
diff --git a/tests/test_models/test_backbones/test_resnet.py b/tests/test_models/test_backbones/test_resnet.py
index d0e287422..f2f24ba56 100644
--- a/tests/test_models/test_backbones/test_resnet.py
+++ b/tests/test_models/test_backbones/test_resnet.py
@@ -331,7 +331,7 @@ def test_resnet_backbone():
         for param in layer.parameters():
             assert param.requires_grad is False
     for i in range(1, frozen_stages + 1):
-        layer = getattr(model, 'layer{}'.format(i))
+        layer = getattr(model, f'layer{i}')
         for mod in layer.modules():
             if isinstance(mod, _BatchNorm):
                 assert mod.training is False
@@ -347,7 +347,7 @@ def test_resnet_backbone():
     for param in model.stem.parameters():
         assert param.requires_grad is False
     for i in range(1, frozen_stages + 1):
-        layer = getattr(model, 'layer{}'.format(i))
+        layer = getattr(model, f'layer{i}')
         for mod in layer.modules():
             if isinstance(mod, _BatchNorm):
                 assert mod.training is False
diff --git a/tools/analysis_tools/analyze_logs.py b/tools/analysis_tools/analyze_logs.py
index 0539a3c59..7464d2316 100644
--- a/tools/analysis_tools/analyze_logs.py
+++ b/tools/analysis_tools/analyze_logs.py
@@ -101,7 +101,7 @@ def load_json_logs(json_logs):
     log_dicts = [dict() for _ in json_logs]
     prev_step = 0
     for json_log, log_dict in zip(json_logs, log_dicts):
-        with open(json_log, 'r') as log_file:
+        with open(json_log) as log_file:
             for line in log_file:
                 log = json.loads(line.strip())
                 # the final step in json file is 0.
diff --git a/tools/dataset_converters/chase_db1.py b/tools/dataset_converters/chase_db1.py
index 82e687ce1..f4fefbd77 100644
--- a/tools/dataset_converters/chase_db1.py
+++ b/tools/dataset_converters/chase_db1.py
@@ -47,7 +47,7 @@ def main():
         print('Generating training dataset...')
 
         assert len(os.listdir(tmp_dir)) == CHASE_DB1_LEN, \
-            'len(os.listdir(tmp_dir)) != {}'.format(CHASE_DB1_LEN)
+            f'len(os.listdir(tmp_dir)) != {CHASE_DB1_LEN}'
 
         for img_name in sorted(os.listdir(tmp_dir))[:TRAINING_LEN]:
             img = mmcv.imread(osp.join(tmp_dir, img_name))
diff --git a/tools/dataset_converters/hrf.py b/tools/dataset_converters/hrf.py
index 2dd8c2296..3bfd80c9e 100644
--- a/tools/dataset_converters/hrf.py
+++ b/tools/dataset_converters/hrf.py
@@ -63,7 +63,7 @@ def main():
             zip_file.extractall(tmp_dir)
 
             assert len(os.listdir(tmp_dir)) == HRF_LEN, \
-                'len(os.listdir(tmp_dir)) != {}'.format(HRF_LEN)
+                f'len(os.listdir(tmp_dir)) != {HRF_LEN}'
 
             for filename in sorted(os.listdir(tmp_dir))[:TRAINING_LEN]:
                 img = mmcv.imread(osp.join(tmp_dir, filename))
@@ -85,7 +85,7 @@ def main():
             zip_file.extractall(tmp_dir)
 
             assert len(os.listdir(tmp_dir)) == HRF_LEN, \
-                'len(os.listdir(tmp_dir)) != {}'.format(HRF_LEN)
+                f'len(os.listdir(tmp_dir)) != {HRF_LEN}'
 
             for filename in sorted(os.listdir(tmp_dir))[:TRAINING_LEN]:
                 img = mmcv.imread(osp.join(tmp_dir, filename))
diff --git a/tools/dataset_converters/isaid.py b/tools/dataset_converters/isaid.py
index 738e2a368..1da264d97 100644
--- a/tools/dataset_converters/isaid.py
+++ b/tools/dataset_converters/isaid.py
@@ -188,17 +188,17 @@ def main():
     mkdir_or_exist(osp.join(out_dir, 'ann_dir', 'test'))
 
     assert os.path.exists(os.path.join(dataset_path, 'train')), \
-        'train is not in {}'.format(dataset_path)
+        f'train is not in {dataset_path}'
     assert os.path.exists(os.path.join(dataset_path, 'val')), \
-        'val is not in {}'.format(dataset_path)
+        f'val is not in {dataset_path}'
     assert os.path.exists(os.path.join(dataset_path, 'test')), \
-        'test is not in {}'.format(dataset_path)
+        f'test is not in {dataset_path}'
 
     with tempfile.TemporaryDirectory(dir=args.tmp_dir) as tmp_dir:
         for dataset_mode in ['train', 'val', 'test']:
 
             # for dataset_mode in [ 'test']:
-            print('Extracting  {}ing.zip...'.format(dataset_mode))
+            print(f'Extracting  {dataset_mode}ing.zip...')
             img_zipp_list = glob.glob(
                 os.path.join(dataset_path, dataset_mode, 'images', '*.zip'))
             print('Find the data', img_zipp_list)
diff --git a/tools/dataset_converters/loveda.py b/tools/dataset_converters/loveda.py
index b54ff0b14..5b0ef4bb8 100644
--- a/tools/dataset_converters/loveda.py
+++ b/tools/dataset_converters/loveda.py
@@ -38,11 +38,11 @@ def main():
     mkdir_or_exist(osp.join(out_dir, 'ann_dir', 'val'))
 
     assert 'Train.zip' in os.listdir(dataset_path), \
-        'Train.zip is not in {}'.format(dataset_path)
+        f'Train.zip is not in {dataset_path}'
     assert 'Val.zip' in os.listdir(dataset_path), \
-        'Val.zip is not in {}'.format(dataset_path)
+        f'Val.zip is not in {dataset_path}'
     assert 'Test.zip' in os.listdir(dataset_path), \
-        'Test.zip is not in {}'.format(dataset_path)
+        f'Test.zip is not in {dataset_path}'
 
     with tempfile.TemporaryDirectory(dir=args.tmp_dir) as tmp_dir:
         for dataset in ['Train', 'Val', 'Test']:
diff --git a/tools/dataset_converters/stare.py b/tools/dataset_converters/stare.py
index e5e180f40..4a23ba4dd 100644
--- a/tools/dataset_converters/stare.py
+++ b/tools/dataset_converters/stare.py
@@ -68,7 +68,7 @@ def main():
         now_dir = osp.join(tmp_dir, 'files')
 
         assert len(os.listdir(now_dir)) == STARE_LEN, \
-            'len(os.listdir(now_dir)) != {}'.format(STARE_LEN)
+            f'len(os.listdir(now_dir)) != {STARE_LEN}'
 
         for filename in sorted(os.listdir(now_dir))[:TRAINING_LEN]:
             img = mmcv.imread(osp.join(now_dir, filename))
@@ -103,7 +103,7 @@ def main():
         now_dir = osp.join(tmp_dir, 'files')
 
         assert len(os.listdir(now_dir)) == STARE_LEN, \
-            'len(os.listdir(now_dir)) != {}'.format(STARE_LEN)
+            f'len(os.listdir(now_dir)) != {STARE_LEN}'
 
         for filename in sorted(os.listdir(now_dir))[:TRAINING_LEN]:
             img = mmcv.imread(osp.join(now_dir, filename))
@@ -142,7 +142,7 @@ def main():
         now_dir = osp.join(tmp_dir, 'files')
 
         assert len(os.listdir(now_dir)) == STARE_LEN, \
-            'len(os.listdir(now_dir)) != {}'.format(STARE_LEN)
+            f'len(os.listdir(now_dir)) != {STARE_LEN}'
 
         for filename in sorted(os.listdir(now_dir))[:TRAINING_LEN]:
             img = mmcv.imread(osp.join(now_dir, filename))
diff --git a/tools/deployment/pytorch2torchscript.py b/tools/deployment/pytorch2torchscript.py
index 05022326a..e69e705bb 100644
--- a/tools/deployment/pytorch2torchscript.py
+++ b/tools/deployment/pytorch2torchscript.py
@@ -126,7 +126,7 @@ def pytorch2libtorch(model,
         print(traced_model.graph)
 
     traced_model.save(output_file)
-    print('Successfully exported TorchScript model: {}'.format(output_file))
+    print(f'Successfully exported TorchScript model: {output_file}')
 
 
 def parse_args():
diff --git a/tools/misc/publish_model.py b/tools/misc/publish_model.py
index e2660578a..c1bbc9ac1 100644
--- a/tools/misc/publish_model.py
+++ b/tools/misc/publish_model.py
@@ -23,7 +23,7 @@ def process_checkpoint(in_file, out_file):
     # 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])
+    final_file = out_file.rstrip('.pth') + f'-{sha[:8]}.pth'
     subprocess.Popen(['mv', out_file, final_file])