diff --git a/.github/workflows/code-formatting.yml b/.github/workflows/code-formatting.yml
index 54bdbe23e0608..598b7a5df9aa8 100644
--- a/.github/workflows/code-formatting.yml
+++ b/.github/workflows/code-formatting.yml
@@ -25,7 +25,7 @@ jobs:
 
   python-types:
     name: Python static type checking with Pyright
-    runs-on: ubuntu-18.04
+    runs-on: ubuntu-20.04
 
     # Timeout: https://stackoverflow.com/a/59076067/4521646
     timeout-minutes: 15
@@ -71,3 +71,24 @@ jobs:
       - name: Run type checking
         run: |
           $(npm bin)/pyright --project .pyrightconfig.json
+
+  python-pep8:
+    name: Python formatting PEP8
+    runs-on: ubuntu-20.04
+
+    # Timeout: https://stackoverflow.com/a/59076067/4521646
+    timeout-minutes: 10
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+      - uses: actions/setup-python@v2
+        with:
+          python-version: 3.7
+
+      - name: Install dependencies
+        run: |
+          pip install flake8
+
+      - name: Run checking
+        run: |
+          flake8 .
diff --git a/pytorch_lightning/accelerators/ddp2_accelerator.py b/pytorch_lightning/accelerators/ddp2_accelerator.py
index e51ddc2eba48c..f4d3eb40232b4 100644
--- a/pytorch_lightning/accelerators/ddp2_accelerator.py
+++ b/pytorch_lightning/accelerators/ddp2_accelerator.py
@@ -16,7 +16,9 @@
 
 import torch
 import torch.distributed as torch_distrib
+
 from pytorch_lightning.utilities.exceptions import MisconfigurationException
+from pytorch_lightning.core.lightning import LightningModule
 from pytorch_lightning.core.step_result import Result
 from pytorch_lightning.distributed.dist import LightningDistributed
 from pytorch_lightning import _logger as log
@@ -191,14 +193,14 @@ def ddp_train(self, process_idx, mp_queue, model):
         return results
 
     def configure_ddp(
-        self, model: "LightningModule", device_ids: List[int]
+        self, model: LightningModule, device_ids: List[int]
     ) -> DistributedDataParallel:
         model = LightningDistributedDataParallel(
             model, device_ids=device_ids, find_unused_parameters=True
         )
         return model
 
-    def configure_sync_batchnorm(self, model: "LightningModule") -> "LightningModule":
+    def configure_sync_batchnorm(self, model: LightningModule) -> LightningModule:
         """
         Add global batchnorm for a model spread across multiple GPUs and nodes.
 
diff --git a/pytorch_lightning/accelerators/ddp_accelerator.py b/pytorch_lightning/accelerators/ddp_accelerator.py
index 9c8ed93c3f57a..9439c7656ac9e 100644
--- a/pytorch_lightning/accelerators/ddp_accelerator.py
+++ b/pytorch_lightning/accelerators/ddp_accelerator.py
@@ -18,21 +18,21 @@
 import sys
 from os.path import abspath
 from time import sleep
-from typing import Optional
-import numpy as np
+from typing import Optional, List
 
+import numpy as np
 
 from pytorch_lightning import _logger as log
-from pytorch_lightning.utilities.distributed import find_free_network_port
 from pytorch_lightning.accelerators.accelerator import Accelerator
-from pytorch_lightning.utilities.distributed import rank_zero_only
-from pytorch_lightning.utilities import AMPType
-from pytorch_lightning.utilities.seed import seed_everything
+from pytorch_lightning.core.lightning import LightningModule
 from pytorch_lightning.distributed.dist import LightningDistributed
-from pytorch_lightning.utilities.exceptions import MisconfigurationException
 from pytorch_lightning.overrides.data_parallel import LightningDistributedDataParallel
+from pytorch_lightning.utilities import AMPType
+from pytorch_lightning.utilities.distributed import find_free_network_port
+from pytorch_lightning.utilities.distributed import rank_zero_only
+from pytorch_lightning.utilities.exceptions import MisconfigurationException
+from pytorch_lightning.utilities.seed import seed_everything
 from torch.nn.parallel import DistributedDataParallel
-from typing import List
 
 
 try:
@@ -284,14 +284,14 @@ def ddp_train(self, process_idx, model):
         return results
 
     def configure_ddp(
-        self, model: "LightningModule", device_ids: List[int]
+        self, model: LightningModule, device_ids: List[int]
     ) -> DistributedDataParallel:
         model = LightningDistributedDataParallel(
             model, device_ids=device_ids, find_unused_parameters=True
         )
         return model
 
-    def configure_sync_batchnorm(self, model: "LightningModule") -> "LightningModule":
+    def configure_sync_batchnorm(self, model: LightningModule) -> LightningModule:
         """
         Add global batchnorm for a model spread across multiple GPUs and nodes.
 
diff --git a/pytorch_lightning/accelerators/ddp_cpu_slurm_accelerator.py b/pytorch_lightning/accelerators/ddp_cpu_slurm_accelerator.py
index 6e1a42c708476..f194c2c1e6d72 100644
--- a/pytorch_lightning/accelerators/ddp_cpu_slurm_accelerator.py
+++ b/pytorch_lightning/accelerators/ddp_cpu_slurm_accelerator.py
@@ -12,19 +12,20 @@
 # See the License for the specific language governing permissions and
 # limitations under the License
 import os
+from typing import List, Optional
+
 import torch
 import torch.distributed as torch_distrib
 import torch.distributed as dist
+from torch.nn.parallel import DistributedDataParallel
 
-from pytorch_lightning.accelerators.accelerator import Accelerator
 from pytorch_lightning import _logger as log
+from pytorch_lightning.accelerators.accelerator import Accelerator
+from pytorch_lightning.core.lightning import LightningModule
 from pytorch_lightning.utilities import AMPType
 from pytorch_lightning.utilities.distributed import rank_zero_only
-from pytorch_lightning.utilities.seed import seed_everything
 from pytorch_lightning.distributed.dist import LightningDistributed
 from pytorch_lightning.overrides.data_parallel import LightningDistributedDataParallel
-from torch.nn.parallel import DistributedDataParallel
-from typing import List, Optional
 
 
 try:
@@ -177,14 +178,14 @@ def ddp_train(self, process_idx, model):
         return results
 
     def configure_ddp(
-        self, model: "LightningModule", device_ids: List[int]
+        self, model: LightningModule, device_ids: List[int]
     ) -> DistributedDataParallel:
         model = LightningDistributedDataParallel(
             model, device_ids=device_ids, find_unused_parameters=True
         )
         return model
 
-    def configure_sync_batchnorm(self, model: "LightningModule") -> "LightningModule":
+    def configure_sync_batchnorm(self, model: LightningModule) -> LightningModule:
         """
         Add global batchnorm for a model spread across multiple GPUs and nodes.
 
diff --git a/pytorch_lightning/accelerators/ddp_cpu_spawn_accelerator.py b/pytorch_lightning/accelerators/ddp_cpu_spawn_accelerator.py
index 8241d96695d1c..8f897b01a8cd1 100644
--- a/pytorch_lightning/accelerators/ddp_cpu_spawn_accelerator.py
+++ b/pytorch_lightning/accelerators/ddp_cpu_spawn_accelerator.py
@@ -12,23 +12,22 @@
 # See the License for the specific language governing permissions and
 # limitations under the License
 import os
-import re
+from typing import List, Optional
 
 import torch
 import torch.distributed as torch_distrib
 import torch.distributed as dist
 import torch.multiprocessing as mp
+from torch.nn.parallel import DistributedDataParallel
 
 from pytorch_lightning import _logger as log
 from pytorch_lightning.accelerators.accelerator import Accelerator
+from pytorch_lightning.core.lightning import LightningModule
+from pytorch_lightning.overrides.data_parallel import LightningDistributedDataParallel
 from pytorch_lightning.utilities import AMPType
-from pytorch_lightning.utilities.cloud_io import atomic_save, load as pl_load
 from pytorch_lightning.utilities.distributed import rank_zero_only, rank_zero_warn
 from pytorch_lightning.utilities.distributed import find_free_network_port
 from pytorch_lightning.distributed.dist import LightningDistributed
-from pytorch_lightning.overrides.data_parallel import LightningDistributedDataParallel
-from torch.nn.parallel import DistributedDataParallel
-from typing import List, Optional
 
 try:
     from hydra.core.hydra_config import HydraConfig
@@ -210,14 +209,14 @@ def transfer_distrib_spawn_state_on_fit_end(self, model, mp_queue, results):
             mp_queue.put(results)
 
     def configure_ddp(
-        self, model: "LightningModule", device_ids: List[int]
+        self, model: LightningModule, device_ids: List[int]
     ) -> DistributedDataParallel:
         model = LightningDistributedDataParallel(
             model, device_ids=device_ids, find_unused_parameters=True
         )
         return model
 
-    def configure_sync_batchnorm(self, model: "LightningModule") -> "LightningModule":
+    def configure_sync_batchnorm(self, model: LightningModule) -> LightningModule:
         """
         Add global batchnorm for a model spread across multiple GPUs and nodes.
 
diff --git a/pytorch_lightning/accelerators/ddp_cpu_torchelastic_accelerator.py b/pytorch_lightning/accelerators/ddp_cpu_torchelastic_accelerator.py
index 91735c2bcefdc..300512e3fc2f9 100644
--- a/pytorch_lightning/accelerators/ddp_cpu_torchelastic_accelerator.py
+++ b/pytorch_lightning/accelerators/ddp_cpu_torchelastic_accelerator.py
@@ -12,19 +12,20 @@
 # See the License for the specific language governing permissions and
 # limitations under the License
 import os
+from typing import List, Optional
+
 import torch
 import torch.distributed as torch_distrib
 import torch.distributed as dist
+from torch.nn.parallel import DistributedDataParallel
 
-from pytorch_lightning.accelerators.accelerator import Accelerator
 from pytorch_lightning import _logger as log
-from pytorch_lightning.utilities import AMPType
-from pytorch_lightning.utilities.distributed import rank_zero_only
-from pytorch_lightning.utilities.seed import seed_everything
+from pytorch_lightning.accelerators.accelerator import Accelerator
+from pytorch_lightning.core.lightning import LightningModule
 from pytorch_lightning.distributed.dist import LightningDistributed
 from pytorch_lightning.overrides.data_parallel import LightningDistributedDataParallel
-from torch.nn.parallel import DistributedDataParallel
-from typing import List, Optional
+from pytorch_lightning.utilities import AMPType
+from pytorch_lightning.utilities.distributed import rank_zero_only
 
 try:
     from hydra.utils import to_absolute_path, get_original_cwd
@@ -176,14 +177,14 @@ def ddp_train(self, process_idx, model):
         return results
 
     def configure_ddp(
-        self, model: "LightningModule", device_ids: List[int]
+        self, model: LightningModule, device_ids: List[int]
     ) -> DistributedDataParallel:
         model = LightningDistributedDataParallel(
             model, device_ids=device_ids, find_unused_parameters=True
         )
         return model
 
-    def configure_sync_batchnorm(self, model: "LightningModule") -> "LightningModule":
+    def configure_sync_batchnorm(self, model: LightningModule) -> LightningModule:
         """
         Add global batchnorm for a model spread across multiple GPUs and nodes.
 
diff --git a/pytorch_lightning/accelerators/ddp_slurm_accelerator.py b/pytorch_lightning/accelerators/ddp_slurm_accelerator.py
index b556f0858d448..bc7920c36457a 100644
--- a/pytorch_lightning/accelerators/ddp_slurm_accelerator.py
+++ b/pytorch_lightning/accelerators/ddp_slurm_accelerator.py
@@ -12,19 +12,21 @@
 # See the License for the specific language governing permissions and
 # limitations under the License
 import os
+from typing import List
+
 import torch
 import torch.distributed as torch_distrib
 import torch.distributed as dist
+from torch.nn.parallel import DistributedDataParallel
 
-from pytorch_lightning.accelerators.accelerator import Accelerator
 from pytorch_lightning import _logger as log
+from pytorch_lightning.accelerators.accelerator import Accelerator
+from pytorch_lightning.core.lightning import LightningModule
+from pytorch_lightning.distributed.dist import LightningDistributed
+from pytorch_lightning.overrides.data_parallel import LightningDistributedDataParallel
 from pytorch_lightning.utilities import AMPType
 from pytorch_lightning.utilities.distributed import rank_zero_only
 from pytorch_lightning.utilities.seed import seed_everything
-from pytorch_lightning.distributed.dist import LightningDistributed
-from pytorch_lightning.overrides.data_parallel import LightningDistributedDataParallel
-from torch.nn.parallel import DistributedDataParallel
-from typing import List
 
 try:
     from hydra.utils import to_absolute_path, get_original_cwd
@@ -182,14 +184,14 @@ def ddp_train(self, process_idx, model):
         return results
 
     def configure_ddp(
-        self, model: "LightningModule", device_ids: List[int]
+        self, model: LightningModule, device_ids: List[int]
     ) -> DistributedDataParallel:
         model = LightningDistributedDataParallel(
             model, device_ids=device_ids, find_unused_parameters=True
         )
         return model
 
-    def configure_sync_batchnorm(self, model: "LightningModule") -> "LightningModule":
+    def configure_sync_batchnorm(self, model: LightningModule) -> LightningModule:
         """
         Add global batchnorm for a model spread across multiple GPUs and nodes.
 
diff --git a/pytorch_lightning/accelerators/ddp_spawn_accelerator.py b/pytorch_lightning/accelerators/ddp_spawn_accelerator.py
index fba819096ad10..272fcda932a8e 100644
--- a/pytorch_lightning/accelerators/ddp_spawn_accelerator.py
+++ b/pytorch_lightning/accelerators/ddp_spawn_accelerator.py
@@ -13,23 +13,23 @@
 # limitations under the License
 import os
 import re
+from typing import List, Optional
 
 import torch
 import torch.multiprocessing as mp
 import torch.distributed as torch_distrib
 import torch.distributed as dist
+from torch.nn.parallel import DistributedDataParallel
 
 from pytorch_lightning import _logger as log
 from pytorch_lightning.accelerators.accelerator import Accelerator
+from pytorch_lightning.core.lightning import LightningModule
+from pytorch_lightning.overrides.data_parallel import LightningDistributedDataParallel
 from pytorch_lightning.utilities import AMPType
 from pytorch_lightning.utilities.cloud_io import atomic_save, load as pl_load
-from pytorch_lightning.utilities.distributed import rank_zero_only, rank_zero_warn
+from pytorch_lightning.utilities.distributed import rank_zero_only, rank_zero_warn, find_free_network_port
 from pytorch_lightning.utilities.seed import seed_everything
 from pytorch_lightning.distributed.dist import LightningDistributed
-from pytorch_lightning.utilities.distributed import find_free_network_port
-from pytorch_lightning.overrides.data_parallel import LightningDistributedDataParallel
-from torch.nn.parallel import DistributedDataParallel
-from typing import List, Optional
 
 try:
     from hydra.core.hydra_config import HydraConfig
@@ -237,14 +237,14 @@ def transfer_distrib_spawn_state_on_fit_end(self, model, mp_queue, results):
             mp_queue.put(last_path)
 
     def configure_ddp(
-        self, model: "LightningModule", device_ids: List[int]
+        self, model: LightningModule, device_ids: List[int]
     ) -> DistributedDataParallel:
         model = LightningDistributedDataParallel(
             model, device_ids=device_ids, find_unused_parameters=True
         )
         return model
 
-    def configure_sync_batchnorm(self, model: "LightningModule") -> "LightningModule":
+    def configure_sync_batchnorm(self, model: LightningModule) -> LightningModule:
         """
         Add global batchnorm for a model spread across multiple GPUs and nodes.
 
diff --git a/pytorch_lightning/accelerators/ddp_torchelastic_accelerator.py b/pytorch_lightning/accelerators/ddp_torchelastic_accelerator.py
index 282a1d6d35582..df7693f521ddd 100644
--- a/pytorch_lightning/accelerators/ddp_torchelastic_accelerator.py
+++ b/pytorch_lightning/accelerators/ddp_torchelastic_accelerator.py
@@ -12,19 +12,20 @@
 # See the License for the specific language governing permissions and
 # limitations under the License
 import os
+from typing import List, Optional
+
 import torch
 import torch.distributed as torch_distrib
 import torch.distributed as dist
+from torch.nn.parallel import DistributedDataParallel
 
-from pytorch_lightning.accelerators.accelerator import Accelerator
 from pytorch_lightning import _logger as log
-from pytorch_lightning.utilities import AMPType
-from pytorch_lightning.utilities.distributed import rank_zero_only
-from pytorch_lightning.utilities.seed import seed_everything
+from pytorch_lightning.accelerators.accelerator import Accelerator
+from pytorch_lightning.core.lightning import LightningModule
 from pytorch_lightning.distributed.dist import LightningDistributed
 from pytorch_lightning.overrides.data_parallel import LightningDistributedDataParallel
-from torch.nn.parallel import DistributedDataParallel
-from typing import List, Optional
+from pytorch_lightning.utilities import AMPType
+from pytorch_lightning.utilities.distributed import rank_zero_only
 
 
 try:
@@ -179,14 +180,14 @@ def ddp_train(self, process_idx, model):
         return results
 
     def configure_ddp(
-        self, model: "LightningModule", device_ids: List[int]
+        self, model: LightningModule, device_ids: List[int]
     ) -> DistributedDataParallel:
         model = LightningDistributedDataParallel(
             model, device_ids=device_ids, find_unused_parameters=True
         )
         return model
 
-    def configure_sync_batchnorm(self, model: "LightningModule") -> "LightningModule":
+    def configure_sync_batchnorm(self, model: LightningModule) -> LightningModule:
         """
         Add global batchnorm for a model spread across multiple GPUs and nodes.
 
diff --git a/pytorch_lightning/accelerators/horovod_accelerator.py b/pytorch_lightning/accelerators/horovod_accelerator.py
index ea5faad0e0cb8..3267e1d7f14b4 100644
--- a/pytorch_lightning/accelerators/horovod_accelerator.py
+++ b/pytorch_lightning/accelerators/horovod_accelerator.py
@@ -152,7 +152,7 @@ def test_step(self, args):
         return output
 
     def backward(self, closure_loss, optimizer, opt_idx, *args, **kwargs):
-        super().backward(closure_loss, optimizer, opt_idx,  *args, **kwargs)
+        super().backward(closure_loss, optimizer, opt_idx, *args, **kwargs)
         optimizer.synchronize()
 
     def on_train_epoch_end(self, outputs):
diff --git a/pytorch_lightning/callbacks/early_stopping.py b/pytorch_lightning/callbacks/early_stopping.py
index 9566542f2ece4..864d3d836ec43 100644
--- a/pytorch_lightning/callbacks/early_stopping.py
+++ b/pytorch_lightning/callbacks/early_stopping.py
@@ -35,8 +35,6 @@
 torch_inf = torch.tensor(np.Inf)
 
 
-
-
 class EarlyStopping(Callback):
     r"""
     Monitor a validation metric and stop training when it stops improving.
diff --git a/pytorch_lightning/core/__init__.py b/pytorch_lightning/core/__init__.py
index 51ec4acd5652b..bcab67d821e09 100644
--- a/pytorch_lightning/core/__init__.py
+++ b/pytorch_lightning/core/__init__.py
@@ -11,6 +11,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
 from pytorch_lightning.core.datamodule import LightningDataModule
 from pytorch_lightning.core.lightning import LightningModule
 
diff --git a/pytorch_lightning/core/lightning.py b/pytorch_lightning/core/lightning.py
index e7b8cf6f0cdee..d5523ef92f80a 100644
--- a/pytorch_lightning/core/lightning.py
+++ b/pytorch_lightning/core/lightning.py
@@ -233,7 +233,7 @@ def log(
                 m = f'on_step=True cannot be used on {self._current_fx_name} method'
                 raise MisconfigurationException(m)
 
-            if 'epoch_end' in self._current_fx_name and on_epoch == False:
+            if 'epoch_end' in self._current_fx_name and on_epoch is False:
                 m = f'on_epoch cannot be False when called from the {self._current_fx_name} method'
                 raise MisconfigurationException(m)
 
diff --git a/pytorch_lightning/plugins/apex.py b/pytorch_lightning/plugins/apex.py
index ec2e4c30a6291..59f724ec3d666 100644
--- a/pytorch_lightning/plugins/apex.py
+++ b/pytorch_lightning/plugins/apex.py
@@ -12,7 +12,10 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 from typing import List, Tuple
+
 from torch.optim.optimizer import Optimizer
+
+from pytorch_lightning.core.lightning import LightningModule
 from pytorch_lightning.utilities.distributed import rank_zero_warn
 from pytorch_lightning.utilities import AMPType
 
@@ -65,10 +68,10 @@ def backward(self, closure_loss, optimizer, opt_idx, *args, **kwargs):
     def configure_apex(
         self,
         amp: object,
-        model: "LightningModule",
+        model: LightningModule,
         optimizers: List[Optimizer],
         amp_level: str,
-    ) -> Tuple["LightningModule", List[Optimizer]]:
+    ) -> Tuple[LightningModule, List[Optimizer]]:
         r"""
         Override to init AMP your own way.
         Must return a model and list of optimizers.
diff --git a/pytorch_lightning/trainer/connectors/checkpoint_connector.py b/pytorch_lightning/trainer/connectors/checkpoint_connector.py
index 420cb6d3f5bf3..6a4e5820e05d9 100644
--- a/pytorch_lightning/trainer/connectors/checkpoint_connector.py
+++ b/pytorch_lightning/trainer/connectors/checkpoint_connector.py
@@ -24,15 +24,11 @@
 
 import pytorch_lightning
 from pytorch_lightning import _logger as log
-from pytorch_lightning.callbacks import EarlyStopping, ModelCheckpoint
 from pytorch_lightning.core.lightning import LightningModule
-from pytorch_lightning.loggers import LightningLoggerBase
-from pytorch_lightning.overrides.data_parallel import LightningDataParallel, LightningDistributedDataParallel
 from pytorch_lightning.utilities import AMPType, rank_zero_warn
 from pytorch_lightning.utilities.cloud_io import atomic_save, get_filesystem
 from pytorch_lightning.utilities.cloud_io import load as pl_load
 from pytorch_lightning.utilities.upgrade_checkpoint import KEYS_MAPPING as DEPRECATED_CHECKPOINT_KEYS
-from pytorch_lightning.accelerators.accelerator import Accelerator
 from pytorch_lightning.utilities.exceptions import MisconfigurationException
 
 try:
diff --git a/pytorch_lightning/trainer/model_hooks.py b/pytorch_lightning/trainer/model_hooks.py
index cbf71748aa77a..12225dd955ecb 100644
--- a/pytorch_lightning/trainer/model_hooks.py
+++ b/pytorch_lightning/trainer/model_hooks.py
@@ -15,7 +15,6 @@
 import inspect
 from abc import ABC, abstractmethod
 
-from pytorch_lightning.core.datamodule import LightningDataModule
 from pytorch_lightning.core.lightning import LightningModule
 
 
diff --git a/pytorch_lightning/trainer/properties.py b/pytorch_lightning/trainer/properties.py
index 56b6c6e67094f..afb2f4cb5eb91 100644
--- a/pytorch_lightning/trainer/properties.py
+++ b/pytorch_lightning/trainer/properties.py
@@ -11,20 +11,21 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-from pytorch_lightning.utilities.cloud_io import get_filesystem
-from pytorch_lightning.trainer.connectors.logger_connector import LoggerConnector
-from pytorch_lightning.trainer.states import TrainerState
-from typing import List, Optional, Union, Type, TypeVar
-from pytorch_lightning.utilities import argparse_utils
-from argparse import ArgumentParser, Namespace
-from abc import ABC
 import inspect
 import os
-from pytorch_lightning.utilities.model_utils import is_overridden
-from pytorch_lightning.core.lightning import LightningModule
+from abc import ABC
+from argparse import ArgumentParser, Namespace
+from typing import List, Optional, Union, Type, TypeVar
+
 from pytorch_lightning.callbacks import ProgressBarBase
-from pytorch_lightning.trainer.connectors.model_connector import ModelConnector
+from pytorch_lightning.core.lightning import LightningModule
 from pytorch_lightning.trainer.connectors.checkpoint_connector import CheckpointConnector
+from pytorch_lightning.trainer.connectors.logger_connector import LoggerConnector
+from pytorch_lightning.trainer.connectors.model_connector import ModelConnector
+from pytorch_lightning.trainer.states import TrainerState
+from pytorch_lightning.utilities import argparse_utils
+from pytorch_lightning.utilities.cloud_io import get_filesystem
+from pytorch_lightning.utilities.model_utils import is_overridden
 
 
 class TrainerProperties(ABC):
diff --git a/pytorch_lightning/trainer/trainer.py b/pytorch_lightning/trainer/trainer.py
index 96954733c15b9..68eafe45ba392 100644
--- a/pytorch_lightning/trainer/trainer.py
+++ b/pytorch_lightning/trainer/trainer.py
@@ -19,10 +19,9 @@
 import torch
 from torch.utils.data import DataLoader
 
-from pytorch_lightning.callbacks import Callback, EarlyStopping, ModelCheckpoint
+from pytorch_lightning.callbacks import Callback, ModelCheckpoint
 from pytorch_lightning.core.datamodule import LightningDataModule
 from pytorch_lightning.core.lightning import LightningModule
-from pytorch_lightning.core.memory import ModelSummary
 from pytorch_lightning.core.step_result import EvalResult
 from pytorch_lightning.loggers import LightningLoggerBase
 from pytorch_lightning.profiler import BaseProfiler
diff --git a/pytorch_lightning/trainer/training_tricks.py b/pytorch_lightning/trainer/training_tricks.py
index 3dbab4a78e6f8..471bfe6d47e3b 100644
--- a/pytorch_lightning/trainer/training_tricks.py
+++ b/pytorch_lightning/trainer/training_tricks.py
@@ -18,7 +18,6 @@
 from torch import Tensor
 
 from pytorch_lightning import _logger as log
-from pytorch_lightning.callbacks import GradientAccumulationScheduler
 from pytorch_lightning.core.lightning import LightningModule
 
 try:
diff --git a/pytorch_lightning/tuner/batch_size_scaling.py b/pytorch_lightning/tuner/batch_size_scaling.py
index e7c031fce8e3b..87783fbde5d1f 100644
--- a/pytorch_lightning/tuner/batch_size_scaling.py
+++ b/pytorch_lightning/tuner/batch_size_scaling.py
@@ -12,6 +12,8 @@
 # See the License for the specific language governing permissions and
 # limitations under the License
 import os
+from typing import Optional, Tuple
+
 from pytorch_lightning.core.lightning import LightningModule
 from pytorch_lightning.utilities.data import has_len
 from pytorch_lightning.utilities.parsing import lightning_hasattr, lightning_getattr, lightning_setattr
@@ -20,7 +22,6 @@
 from pytorch_lightning.utilities.memory import is_oom_error, garbage_collection_cuda
 from pytorch_lightning.loggers.base import DummyLogger
 from pytorch_lightning import _logger as log
-from typing import Optional, Tuple
 
 
 def scale_batch_size(trainer,
diff --git a/pytorch_lightning/tuner/tuning.py b/pytorch_lightning/tuner/tuning.py
index 2e7fcf087bd13..9929249804309 100644
--- a/pytorch_lightning/tuner/tuning.py
+++ b/pytorch_lightning/tuner/tuning.py
@@ -11,13 +11,16 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
+from typing import Optional, List, Union
+
+from torch.utils.data import DataLoader
+
 from pytorch_lightning.tuner.batch_size_scaling import scale_batch_size
 from pytorch_lightning.tuner.auto_gpu_select import pick_multiple_gpus
 from pytorch_lightning.tuner.lr_finder import _run_lr_finder_internally, lr_find
 from pytorch_lightning.core.lightning import LightningModule
 from pytorch_lightning.core.datamodule import LightningDataModule
-from typing import Optional, List, Union
-from torch.utils.data import DataLoader
 
 
 class Tuner:
diff --git a/pytorch_lightning/utilities/model_utils.py b/pytorch_lightning/utilities/model_utils.py
index cd2e454c2f96c..876f546312902 100644
--- a/pytorch_lightning/utilities/model_utils.py
+++ b/pytorch_lightning/utilities/model_utils.py
@@ -11,9 +11,11 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
+from typing import Union
+
 from pytorch_lightning.core.lightning import LightningModule
 from pytorch_lightning.core.datamodule import LightningDataModule
-from typing import Union
 
 
 def is_overridden(method_name: str, model: Union[LightningModule, LightningDataModule]) -> bool:
diff --git a/tests/backends/test_accelerator_connector.py b/tests/backends/test_accelerator_connector.py
index d2166a2e5b149..cbc96b0793062 100644
--- a/tests/backends/test_accelerator_connector.py
+++ b/tests/backends/test_accelerator_connector.py
@@ -310,9 +310,7 @@ def on_fit_start(self, trainer, pl_module):
 @mock.patch('torch.cuda.device_count', return_value=0)
 def test_custom_accelerator(tmpdir):
     class Accel(Accelerator):
-        def init_ddp_connection(
-        self, global_rank: int, world_size: int, is_slurm_managing_tasks: bool = True
-    ) -> None:
+        def init_ddp_connection(self, global_rank: int, world_size: int, is_slurm_managing_tasks: bool = True) -> None:
             pass
 
     class CB(Callback):
diff --git a/tests/base/models.py b/tests/base/models.py
index 2be5a4690eb05..a7c1196198017 100644
--- a/tests/base/models.py
+++ b/tests/base/models.py
@@ -19,9 +19,8 @@
 import torch.nn.functional as F
 from torch.utils.data import DataLoader
 
-from tests.base.datasets import TrialMNIST, AverageDataset, MNIST
-
 from pytorch_lightning.core.lightning import LightningModule
+from tests.base.datasets import TrialMNIST, AverageDataset, MNIST
 
 
 class Generator(nn.Module):
diff --git a/tests/loggers/test_mlflow.py b/tests/loggers/test_mlflow.py
index 69534132647f0..db2c353dc4e2c 100644
--- a/tests/loggers/test_mlflow.py
+++ b/tests/loggers/test_mlflow.py
@@ -121,7 +121,7 @@ def test_mlflow_log_dir(client, mlflow, tmpdir):
 def test_mlflow_logger_dirs_creation(tmpdir):
     """ Test that the logger creates the folders and files in the right place. """
     if not importlib.util.find_spec('mlflow'):
-        pytest.xfail(f"test for explicit file creation requires mlflow dependency to be installed.")
+        pytest.xfail("test for explicit file creation requires mlflow dependency to be installed.")
 
     assert not os.listdir(tmpdir)
     logger = MLFlowLogger('test', save_dir=tmpdir)
diff --git a/tests/metrics/classification/test_accuracy.py b/tests/metrics/classification/test_accuracy.py
index 082f1bb3e40a9..a7bdf16a69c25 100644
--- a/tests/metrics/classification/test_accuracy.py
+++ b/tests/metrics/classification/test_accuracy.py
@@ -93,9 +93,9 @@ def test_accuracy_invalid_shape():
         (_multiclass_prob_inputs.preds, _multiclass_prob_inputs.target, _sk_accuracy_multiclass_prob),
         (_multiclass_inputs.preds, _multiclass_inputs.target, _sk_accuracy_multiclass),
         (
-                _multidim_multiclass_prob_inputs.preds,
-                _multidim_multiclass_prob_inputs.target,
-                _sk_accuracy_multidim_multiclass_prob,
+            _multidim_multiclass_prob_inputs.preds,
+            _multidim_multiclass_prob_inputs.target,
+            _sk_accuracy_multidim_multiclass_prob,
         ),
         (_multidim_multiclass_inputs.preds, _multidim_multiclass_inputs.target, _sk_accuracy_multidim_multiclass),
     ],
diff --git a/tests/metrics/classification/test_f_beta.py b/tests/metrics/classification/test_f_beta.py
index dbd0862349e2f..c7eda551ed1a5 100644
--- a/tests/metrics/classification/test_f_beta.py
+++ b/tests/metrics/classification/test_f_beta.py
@@ -90,18 +90,18 @@ def _sk_fbeta_multidim_multiclass(preds, target, average='micro', beta=1.0):
         (_multiclass_prob_inputs.preds, _multiclass_prob_inputs.target, _sk_fbeta_multiclass_prob, NUM_CLASSES, False),
         (_multiclass_inputs.preds, _multiclass_inputs.target, _sk_fbeta_multiclass, NUM_CLASSES, False),
         (
-                _multidim_multiclass_prob_inputs.preds,
-                _multidim_multiclass_prob_inputs.target,
-                _sk_fbeta_multidim_multiclass_prob,
-                NUM_CLASSES,
-                False,
+            _multidim_multiclass_prob_inputs.preds,
+            _multidim_multiclass_prob_inputs.target,
+            _sk_fbeta_multidim_multiclass_prob,
+            NUM_CLASSES,
+            False,
         ),
         (
-                _multidim_multiclass_inputs.preds,
-                _multidim_multiclass_inputs.target,
-                _sk_fbeta_multidim_multiclass,
-                NUM_CLASSES,
-                False,
+            _multidim_multiclass_inputs.preds,
+            _multidim_multiclass_inputs.target,
+            _sk_fbeta_multidim_multiclass,
+            NUM_CLASSES,
+            False,
         ),
     ],
 )
diff --git a/tests/metrics/classification/test_precision_recall.py b/tests/metrics/classification/test_precision_recall.py
index c2a096c4ab1a6..cf027ad279ead 100644
--- a/tests/metrics/classification/test_precision_recall.py
+++ b/tests/metrics/classification/test_precision_recall.py
@@ -90,18 +90,18 @@ def _sk_prec_recall_multidim_multiclass(preds, target, sk_fn=precision_score, av
         (_multiclass_prob_inputs.preds, _multiclass_prob_inputs.target, _sk_prec_recall_multiclass_prob, NUM_CLASSES, False),
         (_multiclass_inputs.preds, _multiclass_inputs.target, _sk_prec_recall_multiclass, NUM_CLASSES, False),
         (
-                _multidim_multiclass_prob_inputs.preds,
-                _multidim_multiclass_prob_inputs.target,
-                _sk_prec_recall_multidim_multiclass_prob,
-                NUM_CLASSES,
-                False,
+            _multidim_multiclass_prob_inputs.preds,
+            _multidim_multiclass_prob_inputs.target,
+            _sk_prec_recall_multidim_multiclass_prob,
+            NUM_CLASSES,
+            False,
         ),
         (
-                _multidim_multiclass_inputs.preds,
-                _multidim_multiclass_inputs.target,
-                _sk_prec_recall_multidim_multiclass,
-                NUM_CLASSES,
-                False,
+            _multidim_multiclass_inputs.preds,
+            _multidim_multiclass_inputs.target,
+            _sk_prec_recall_multidim_multiclass,
+            NUM_CLASSES,
+            False,
         ),
     ],
 )
diff --git a/tests/metrics/test_metric.py b/tests/metrics/test_metric.py
index ccb9b4ad0ad09..3c85a4c126a27 100644
--- a/tests/metrics/test_metric.py
+++ b/tests/metrics/test_metric.py
@@ -72,7 +72,6 @@ def test_add_state_persistent():
         assert "b" not in a.state_dict()
 
 
-
 def test_reset():
     class A(Dummy):
         pass
diff --git a/tests/models/test_hparams.py b/tests/models/test_hparams.py
index 7c147e3dd10a5..b7d0be01e9622 100644
--- a/tests/models/test_hparams.py
+++ b/tests/models/test_hparams.py
@@ -552,7 +552,7 @@ def test_args(tmpdir):
     trainer.fit(model)
 
     raw_checkpoint_path = _raw_checkpoint_path(trainer)
-    with pytest.raises(TypeError, match="__init__\(\) got an unexpected keyword argument 'test'"):
+    with pytest.raises(TypeError, match=r"__init__\(\) got an unexpected keyword argument 'test'"):
         SubClassVarArgs.load_from_checkpoint(raw_checkpoint_path)
 
 
diff --git a/tests/trainer/logging/test_train_loop_logging_1_0.py b/tests/trainer/logging/test_train_loop_logging_1_0.py
index 80b7e7e4b8f1d..64ca89842cc94 100644
--- a/tests/trainer/logging/test_train_loop_logging_1_0.py
+++ b/tests/trainer/logging/test_train_loop_logging_1_0.py
@@ -448,8 +448,8 @@ def __getitem__(self, index):
             x = {
                 'post_text': ['bird is fast', 'big cat'],
                 'dense_0': [
-                    torch.tensor([-0.1000,  0.2000], dtype=torch.float64),
-                    torch.tensor([1, 1], dtype=torch.uint8)
+                    torch.tensor([-0.1000, 0.2000], dtype=torch.float64),
+                    torch.tensor([1, 1], dtype=torch.uint8),
                 ],
                 'post_id': ['115', '116'],
                 'label': [torch.tensor([0, 1]), torch.tensor([1, 1], dtype=torch.uint8)]
diff --git a/tests/trainer/test_optimizers.py b/tests/trainer/test_optimizers.py
index 4a6dd99e9c8aa..d0af97c5b341c 100644
--- a/tests/trainer/test_optimizers.py
+++ b/tests/trainer/test_optimizers.py
@@ -147,6 +147,7 @@ def test_reduce_lr_on_plateau_scheduling_missing_monitor(tmpdir):
 
 def test_reduce_lr_on_plateau_scheduling(tmpdir):
     hparams = EvalModelTemplate.get_default_hparams()
+
     class TestModel(EvalModelTemplate):
 
         def configure_optimizers(self):