diff --git a/keras/applications/efficientnet_v2.py b/keras/applications/efficientnet_v2.py
index 16444b93c..aafd71169 100644
--- a/keras/applications/efficientnet_v2.py
+++ b/keras/applications/efficientnet_v2.py
@@ -34,7 +34,7 @@ from keras.engine import training
 from keras.utils import data_utils
 from keras.utils import layer_utils
 
-BASE_WEIGHTS_PATH = "https://storage.googleapis.com/tensorflow/keras-applications/efficientnet_v2/"
+BASE_WEIGHTS_PATH = "https://storage.googleapis.com/tensorflow/keras-applications/efficientnet_v2/"  # noqa: E501
 
 WEIGHTS_HASHES = {
     "b0": (
diff --git a/keras/callbacks_test.py b/keras/callbacks_test.py
index 31adcc2a7..a9cee284c 100644
--- a/keras/callbacks_test.py
+++ b/keras/callbacks_test.py
@@ -1319,19 +1319,19 @@ class KerasCallbacksTest(test_combinations.TestCase):
 
         return func
 
-    test_model_checkpoint_load_weights_on_restart_true_save_weights_only_true = get_ModelCheckpoint_load_weights_on_restart_true_test.__func__(
+    test_model_checkpoint_load_weights_on_restart_true_save_weights_only_true = get_ModelCheckpoint_load_weights_on_restart_true_test.__func__(  # noqa: E501
         True
     )
 
-    test_model_checkpoint_load_weights_on_restart_true_save_weights_only_false = get_ModelCheckpoint_load_weights_on_restart_true_test.__func__(
+    test_model_checkpoint_load_weights_on_restart_true_save_weights_only_false = get_ModelCheckpoint_load_weights_on_restart_true_test.__func__(  # noqa: E501
         False
     )
 
-    test_model_checkpoint_load_weights_on_restart_false_save_weights_only_true = get_ModelCheckpoint_load_weights_on_restart_false_test.__func__(
+    test_model_checkpoint_load_weights_on_restart_false_save_weights_only_true = get_ModelCheckpoint_load_weights_on_restart_false_test.__func__(  # noqa: E501
         True
     )
 
-    test_model_checkpoint_load_weights_on_restart_false_save_weights_only_false = get_ModelCheckpoint_load_weights_on_restart_false_test.__func__(
+    test_model_checkpoint_load_weights_on_restart_false_save_weights_only_false = get_ModelCheckpoint_load_weights_on_restart_false_test.__func__(  # noqa: E501
         False
     )
 
diff --git a/keras/datasets/boston_housing.py b/keras/datasets/boston_housing.py
index 89a9bb220..22c806f47 100644
--- a/keras/datasets/boston_housing.py
+++ b/keras/datasets/boston_housing.py
@@ -59,7 +59,7 @@ def load_data(path="boston_housing.npz", test_split=0.2, seed=113):
     path = get_file(
         path,
         origin=origin_folder + "boston_housing.npz",
-        file_hash="f553886a1f8d56431e820c5b82552d9d95cfcb96d1e678153f8839538947dff5",
+        file_hash="f553886a1f8d56431e820c5b82552d9d95cfcb96d1e678153f8839538947dff5",  # noqa: E501
     )
     with np.load(
         path, allow_pickle=True
diff --git a/keras/datasets/cifar10.py b/keras/datasets/cifar10.py
index 0225ebb84..5e5d1cd7e 100644
--- a/keras/datasets/cifar10.py
+++ b/keras/datasets/cifar10.py
@@ -80,7 +80,7 @@ def load_data():
         dirname,
         origin=origin,
         untar=True,
-        file_hash="6d958be074577803d12ecdefd02955f39262c83c16fe9348329d7fe0b5c001ce",
+        file_hash="6d958be074577803d12ecdefd02955f39262c83c16fe9348329d7fe0b5c001ce",  # noqa: E501
     )
 
     num_train_samples = 50000
diff --git a/keras/datasets/cifar100.py b/keras/datasets/cifar100.py
index d0e8f9ff1..1eb5039c8 100644
--- a/keras/datasets/cifar100.py
+++ b/keras/datasets/cifar100.py
@@ -77,7 +77,7 @@ def load_data(label_mode="fine"):
         dirname,
         origin=origin,
         untar=True,
-        file_hash="85cd44d02ba6437773c5bbd22e183051d648de2e7d6b014e1ef29b855ba677a7",
+        file_hash="85cd44d02ba6437773c5bbd22e183051d648de2e7d6b014e1ef29b855ba677a7",  # noqa: E501
     )
 
     fpath = os.path.join(path, "train")
diff --git a/keras/datasets/imdb.py b/keras/datasets/imdb.py
index 0470666fd..9dae15010 100644
--- a/keras/datasets/imdb.py
+++ b/keras/datasets/imdb.py
@@ -109,7 +109,7 @@ def load_data(
     path = get_file(
         path,
         origin=origin_folder + "imdb.npz",
-        file_hash="69664113be75683a8fe16e3ed0ab59fda8886cb3cd7ada244f7d9544e4676b9f",
+        file_hash="69664113be75683a8fe16e3ed0ab59fda8886cb3cd7ada244f7d9544e4676b9f",  # noqa: E501
     )
     with np.load(
         path, allow_pickle=True
diff --git a/keras/datasets/mnist.py b/keras/datasets/mnist.py
index ed981de96..8d22076bd 100644
--- a/keras/datasets/mnist.py
+++ b/keras/datasets/mnist.py
@@ -73,7 +73,7 @@ def load_data(path="mnist.npz"):
     path = get_file(
         path,
         origin=origin_folder + "mnist.npz",
-        file_hash="731c5ac602752760c8e48fbffcf8c3b850d9dc2a2aedcf2cc48468fc17b673d1",
+        file_hash="731c5ac602752760c8e48fbffcf8c3b850d9dc2a2aedcf2cc48468fc17b673d1",  # noqa: E501
     )
     with np.load(
         path, allow_pickle=True
diff --git a/keras/datasets/reuters.py b/keras/datasets/reuters.py
index 2be188a36..3e3558361 100644
--- a/keras/datasets/reuters.py
+++ b/keras/datasets/reuters.py
@@ -115,7 +115,7 @@ def load_data(
     path = get_file(
         path,
         origin=origin_folder + "reuters.npz",
-        file_hash="d6586e694ee56d7a4e65172e12b3e987c03096cb01eab99753921ef915959916",
+        file_hash="d6586e694ee56d7a4e65172e12b3e987c03096cb01eab99753921ef915959916",  # noqa: E501
     )
     with np.load(
         path, allow_pickle=True
diff --git a/keras/distribute/checkpointing_test.py b/keras/distribute/checkpointing_test.py
index 2c378a620..f1f03dc3f 100644
--- a/keras/distribute/checkpointing_test.py
+++ b/keras/distribute/checkpointing_test.py
@@ -25,11 +25,11 @@ class TrainingCheckpointTests(tf.test.TestCase, parameterized.TestCase):
     @tf.__internal__.distribute.combinations.generate(
         tf.__internal__.test.combinations.combine(
             distribution=[
-                tf.__internal__.distribute.combinations.mirrored_strategy_with_one_cpu,
-                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
-                tf.__internal__.distribute.combinations.tpu_strategy,
-                tf.__internal__.distribute.combinations.tpu_strategy_packed_var,
-                tf.__internal__.distribute.combinations.central_storage_strategy_with_two_gpus,
+                tf.__internal__.distribute.combinations.mirrored_strategy_with_one_cpu,  # noqa: E501
+                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,  # noqa: E501
+                tf.__internal__.distribute.combinations.tpu_strategy,  # noqa: E501
+                tf.__internal__.distribute.combinations.tpu_strategy_packed_var,  # noqa: E501
+                tf.__internal__.distribute.combinations.central_storage_strategy_with_two_gpus,  # noqa: E501
             ],
             mode=["eager"],
         )
@@ -87,12 +87,12 @@ class TrainingCheckpointTests(tf.test.TestCase, parameterized.TestCase):
     @tf.__internal__.distribute.combinations.generate(
         tf.__internal__.test.combinations.combine(
             distribution=[
-                tf.__internal__.distribute.combinations.mirrored_strategy_with_one_cpu,
-                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
-                tf.__internal__.distribute.combinations.cloud_tpu_strategy,
-                tf.__internal__.distribute.combinations.tpu_strategy,
-                tf.__internal__.distribute.combinations.tpu_strategy_packed_var,
-                tf.__internal__.distribute.combinations.central_storage_strategy_with_two_gpus,
+                tf.__internal__.distribute.combinations.mirrored_strategy_with_one_cpu,  # noqa: E501
+                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,  # noqa: E501
+                tf.__internal__.distribute.combinations.cloud_tpu_strategy,  # noqa: E501
+                tf.__internal__.distribute.combinations.tpu_strategy,  # noqa: E501
+                tf.__internal__.distribute.combinations.tpu_strategy_packed_var,  # noqa: E501
+                tf.__internal__.distribute.combinations.central_storage_strategy_with_two_gpus,  # noqa: E501
             ],
             mode=["eager"],
         )
diff --git a/keras/distribute/collective_all_reduce_strategy_test.py b/keras/distribute/collective_all_reduce_strategy_test.py
index f16c1894c..906272982 100644
--- a/keras/distribute/collective_all_reduce_strategy_test.py
+++ b/keras/distribute/collective_all_reduce_strategy_test.py
@@ -29,8 +29,8 @@ from keras.testing_infra import test_utils
 @tf.__internal__.distribute.combinations.generate(
     tf.__internal__.test.combinations.combine(
         strategy=[
-            tf.__internal__.distribute.combinations.multi_worker_mirrored_2x1_cpu,
-            tf.__internal__.distribute.combinations.multi_worker_mirrored_2x1_gpu,
+            tf.__internal__.distribute.combinations.multi_worker_mirrored_2x1_cpu,  # noqa: E501
+            tf.__internal__.distribute.combinations.multi_worker_mirrored_2x1_gpu,  # noqa: E501
         ],
         mode=["eager"],
     )
diff --git a/keras/distribute/ctl_correctness_test.py b/keras/distribute/ctl_correctness_test.py
index af83d2216..10dbc19b8 100644
--- a/keras/distribute/ctl_correctness_test.py
+++ b/keras/distribute/ctl_correctness_test.py
@@ -271,7 +271,7 @@ class TestDistributionStrategyDnnCorrectness(
         + tf.__internal__.test.combinations.combine(
             distribution=[
                 tf.__internal__.distribute.combinations.one_device_strategy_gpu,
-                tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,
+                tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,  # noqa: E501
             ],
             optimizer_fn=[
                 optimizer_combinations.gradient_descent_optimizer_keras_v2_fn,
@@ -351,7 +351,7 @@ class TestDistributionStrategyDnnCorrectness(
     @tf.__internal__.distribute.combinations.generate(
         tf.__internal__.test.combinations.combine(
             distribution=[
-                tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,
+                tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,  # noqa: E501
             ],
             mode=["eager"],
         )
diff --git a/keras/distribute/custom_training_loop_optimizer_test.py b/keras/distribute/custom_training_loop_optimizer_test.py
index 8fb790b6e..2b8a90815 100644
--- a/keras/distribute/custom_training_loop_optimizer_test.py
+++ b/keras/distribute/custom_training_loop_optimizer_test.py
@@ -68,7 +68,7 @@ class OptimizerTest(tf.test.TestCase, parameterized.TestCase):
             def step_fn(grads):
                 optimizer.apply_gradients(
                     [(grads, v)],
-                    experimental_aggregate_gradients=experimental_aggregate_gradients,
+                    experimental_aggregate_gradients=experimental_aggregate_gradients,  # noqa: E501
                 )
                 return v.read_value()
 
@@ -80,7 +80,7 @@ class OptimizerTest(tf.test.TestCase, parameterized.TestCase):
 
     @tf.__internal__.distribute.combinations.generate(
         tf.__internal__.test.combinations.combine(
-            distribution=tf.__internal__.distribute.combinations.one_device_strategy,
+            distribution=tf.__internal__.distribute.combinations.one_device_strategy,  # noqa: E501
             mode=["eager"],
             experimental_aggregate_gradients=[True, False],
         )
@@ -100,7 +100,7 @@ class OptimizerTest(tf.test.TestCase, parameterized.TestCase):
             def step_fn(grads):
                 optimizer.apply_gradients(
                     [(grads, v)],
-                    experimental_aggregate_gradients=experimental_aggregate_gradients,
+                    experimental_aggregate_gradients=experimental_aggregate_gradients,  # noqa: E501
                 )
                 return v.read_value()
 
@@ -113,7 +113,7 @@ class OptimizerTest(tf.test.TestCase, parameterized.TestCase):
     @tf.__internal__.distribute.combinations.generate(
         tf.__internal__.test.combinations.combine(
             distribution=[
-                tf.__internal__.distribute.combinations.central_storage_strategy_with_gpu_and_cpu
+                tf.__internal__.distribute.combinations.central_storage_strategy_with_gpu_and_cpu  # noqa: E501
             ]
         )
     )
diff --git a/keras/distribute/distribute_strategy_test.py b/keras/distribute/distribute_strategy_test.py
index d8ede979d..4ba617eed 100644
--- a/keras/distribute/distribute_strategy_test.py
+++ b/keras/distribute/distribute_strategy_test.py
@@ -254,8 +254,8 @@ def all_strategy_minus_default_and_tpu_combinations():
         distribution=[
             tf.__internal__.distribute.combinations.one_device_strategy,
             tf.__internal__.distribute.combinations.one_device_strategy_gpu,
-            tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
-            tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,
+            tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,  # noqa: E501
+            tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,  # noqa: E501
         ],
         mode=["graph", "eager"],
     )
@@ -1434,7 +1434,7 @@ class TestDistributionStrategyWithDatasets(
     @tf.__internal__.distribute.combinations.generate(
         tf.__internal__.test.combinations.combine(
             distribution=[
-                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
+                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,  # noqa: E501
                 tf.__internal__.distribute.combinations.one_device_strategy,
             ],
             mode=["graph", "eager"],
@@ -1467,7 +1467,7 @@ class TestDistributionStrategyWithDatasets(
     @tf.__internal__.distribute.combinations.generate(
         tf.__internal__.test.combinations.combine(
             distribution=[
-                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu
+                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu  # noqa: E501
             ],
             mode=["graph", "eager"],
         )
@@ -1492,8 +1492,8 @@ class TestDistributionStrategyWithDatasets(
     @tf.__internal__.distribute.combinations.generate(
         tf.__internal__.test.combinations.combine(
             distribution=[
-                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
-                tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,
+                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,  # noqa: E501
+                tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,  # noqa: E501
             ],
             mode=["graph", "eager"],
         )
@@ -2309,8 +2309,8 @@ class TestDistributionStrategyWithKerasModels(
     @tf.__internal__.distribute.combinations.generate(
         tf.__internal__.test.combinations.combine(
             distribution=[
-                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
-                tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,
+                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,  # noqa: E501
+                tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,  # noqa: E501
             ],
             mode=["graph", "eager"],
             reduction=[
@@ -2476,8 +2476,8 @@ class TestDistributionStrategyWithKerasModels(
             distribution=[
                 tf.__internal__.distribute.combinations.one_device_strategy,
                 tf.__internal__.distribute.combinations.one_device_strategy_gpu,
-                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
-                tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,
+                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,  # noqa: E501
+                tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,  # noqa: E501
             ],
             mode=["eager"],
         )
@@ -3011,7 +3011,7 @@ class TestModelCapturesStrategy(tf.test.TestCase, parameterized.TestCase):
 
     @tf.__internal__.distribute.combinations.generate(
         tf.__internal__.test.combinations.combine(
-            distribution=tf.__internal__.distribute.combinations.mirrored_strategy_with_one_cpu,
+            distribution=tf.__internal__.distribute.combinations.mirrored_strategy_with_one_cpu,  # noqa: E501
             mode=["eager"],
         )
     )
diff --git a/keras/distribute/keras_dnn_correctness_test.py b/keras/distribute/keras_dnn_correctness_test.py
index 8dffca153..a08b4c7c9 100644
--- a/keras/distribute/keras_dnn_correctness_test.py
+++ b/keras/distribute/keras_dnn_correctness_test.py
@@ -115,7 +115,7 @@ class TestDistributionStrategyDnnCorrectness(
         self.run_correctness_test(distribution, use_numpy, use_validation_data)
 
     @tf.__internal__.distribute.combinations.generate(
-        keras_correctness_test_base.test_combinations_with_tpu_strategies_graph()
+        keras_correctness_test_base.test_combinations_with_tpu_strategies_graph()  # noqa: E501
         + keras_correctness_test_base.multi_worker_mirrored_eager()
     )
     def test_dnn_correctness_with_partial_last_batch_eval(
@@ -129,7 +129,7 @@ class TestDistributionStrategyDnnCorrectness(
         )
 
     @tf.__internal__.distribute.combinations.generate(
-        keras_correctness_test_base.strategy_minus_tpu_and_input_config_combinations_eager()
+        keras_correctness_test_base.strategy_minus_tpu_and_input_config_combinations_eager()  # noqa: E501
         + keras_correctness_test_base.multi_worker_mirrored_eager()
     )
     def test_dnn_correctness_with_partial_last_batch(
@@ -354,7 +354,7 @@ class TestDistributionStrategyDnnCorrectnessWithSubclassedModel(
                 self.run_dynamic_lr_test(distribution)
 
     @tf.__internal__.distribute.combinations.generate(
-        keras_correctness_test_base.test_combinations_with_tpu_strategies_graph()
+        keras_correctness_test_base.test_combinations_with_tpu_strategies_graph()  # noqa: E501
     )
     def test_dnn_correctness_with_partial_last_batch_eval(
         self, distribution, use_numpy, use_validation_data
diff --git a/keras/distribute/keras_embedding_model_correctness_test.py b/keras/distribute/keras_embedding_model_correctness_test.py
index a6d3cf368..06e7ee7c4 100644
--- a/keras/distribute/keras_embedding_model_correctness_test.py
+++ b/keras/distribute/keras_embedding_model_correctness_test.py
@@ -25,7 +25,7 @@ from keras.optimizers.optimizer_v2 import (
 
 
 class DistributionStrategyEmbeddingModelCorrectnessTest(
-    keras_correctness_test_base.TestDistributionStrategyEmbeddingModelCorrectnessBase
+    keras_correctness_test_base.TestDistributionStrategyEmbeddingModelCorrectnessBase  # noqa: E501
 ):
     def get_model(
         self,
@@ -83,7 +83,7 @@ class DistributionStrategyEmbeddingModelCorrectnessTest(
 
 
 class DistributionStrategySiameseEmbeddingModelCorrectnessTest(
-    keras_correctness_test_base.TestDistributionStrategyEmbeddingModelCorrectnessBase
+    keras_correctness_test_base.TestDistributionStrategyEmbeddingModelCorrectnessBase  # noqa: E501
 ):
     def get_model(
         self,
diff --git a/keras/distribute/keras_image_model_correctness_test.py b/keras/distribute/keras_image_model_correctness_test.py
index e8f265c41..bd096490f 100644
--- a/keras/distribute/keras_image_model_correctness_test.py
+++ b/keras/distribute/keras_image_model_correctness_test.py
@@ -106,7 +106,7 @@ class DistributionStrategyCnnCorrectnessTest(
     ):
         if (
             distribution
-            == tf.__internal__.distribute.combinations.central_storage_strategy_with_gpu_and_cpu
+            == tf.__internal__.distribute.combinations.central_storage_strategy_with_gpu_and_cpu  # noqa: E501
         ):
             self.skipTest("b/183958183")
         self.run_correctness_test(distribution, use_numpy, use_validation_data)
@@ -140,9 +140,9 @@ class DistributionStrategyCnnCorrectnessTest(
         )
 
     @tf.__internal__.distribute.combinations.generate(
-        keras_correctness_test_base.all_strategy_and_input_config_combinations_eager()
+        keras_correctness_test_base.all_strategy_and_input_config_combinations_eager()  # noqa: E501
         + keras_correctness_test_base.multi_worker_mirrored_eager()
-        + keras_correctness_test_base.test_combinations_with_tpu_strategies_graph()
+        + keras_correctness_test_base.test_combinations_with_tpu_strategies_graph()  # noqa: E501
     )
     def test_cnn_correctness_with_partial_last_batch_eval(
         self, distribution, use_numpy, use_validation_data
@@ -156,9 +156,9 @@ class DistributionStrategyCnnCorrectnessTest(
         )
 
     @tf.__internal__.distribute.combinations.generate(
-        keras_correctness_test_base.all_strategy_and_input_config_combinations_eager()
+        keras_correctness_test_base.all_strategy_and_input_config_combinations_eager()  # noqa: E501
         + keras_correctness_test_base.multi_worker_mirrored_eager()
-        + keras_correctness_test_base.test_combinations_with_tpu_strategies_graph()
+        + keras_correctness_test_base.test_combinations_with_tpu_strategies_graph()  # noqa: E501
     )
     def test_cnn_with_batch_norm_correctness_and_partial_last_batch_eval(
         self, distribution, use_numpy, use_validation_data
diff --git a/keras/distribute/keras_optimizer_v2_test.py b/keras/distribute/keras_optimizer_v2_test.py
index afd0de071..2f28519fa 100644
--- a/keras/distribute/keras_optimizer_v2_test.py
+++ b/keras/distribute/keras_optimizer_v2_test.py
@@ -34,7 +34,7 @@ class MirroredStrategyOptimizerV2Test(tf.test.TestCase, parameterized.TestCase):
     @tf.__internal__.distribute.combinations.generate(
         tf.__internal__.test.combinations.combine(
             distribution=[
-                tf.__internal__.distribute.combinations.central_storage_strategy_with_two_gpus,
+                tf.__internal__.distribute.combinations.central_storage_strategy_with_two_gpus,  # noqa: E501
             ],
             mode=["graph", "eager"],
         )
@@ -96,7 +96,7 @@ class MirroredStrategyOptimizerV2Test(tf.test.TestCase, parameterized.TestCase):
     @tf.__internal__.distribute.combinations.generate(
         tf.__internal__.test.combinations.combine(
             distribution=[
-                tf.__internal__.distribute.combinations.central_storage_strategy_with_two_gpus,
+                tf.__internal__.distribute.combinations.central_storage_strategy_with_two_gpus,  # noqa: E501
             ],
             mode=["graph", "eager"],
         )
diff --git a/keras/distribute/keras_premade_models_test.py b/keras/distribute/keras_premade_models_test.py
index 238f16602..8768fb372 100644
--- a/keras/distribute/keras_premade_models_test.py
+++ b/keras/distribute/keras_premade_models_test.py
@@ -33,14 +33,14 @@ def strategy_combinations_eager_data_fn():
             tf.__internal__.distribute.combinations.default_strategy,
             tf.__internal__.distribute.combinations.one_device_strategy,
             tf.__internal__.distribute.combinations.one_device_strategy_gpu,
-            tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
-            tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,
-            tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus_no_merge_call,
-            tf.__internal__.distribute.combinations.multi_worker_mirrored_2x1_cpu,
-            tf.__internal__.distribute.combinations.multi_worker_mirrored_2x1_gpu,
-            tf.__internal__.distribute.combinations.multi_worker_mirrored_2x2_gpu,
-            tf.__internal__.distribute.combinations.parameter_server_strategy_1worker_2ps_cpu,
-            tf.__internal__.distribute.combinations.parameter_server_strategy_1worker_2ps_1gpu,
+            tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,  # noqa: E501
+            tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,  # noqa: E501
+            tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus_no_merge_call,  # noqa: E501
+            tf.__internal__.distribute.combinations.multi_worker_mirrored_2x1_cpu,  # noqa: E501
+            tf.__internal__.distribute.combinations.multi_worker_mirrored_2x1_gpu,  # noqa: E501
+            tf.__internal__.distribute.combinations.multi_worker_mirrored_2x2_gpu,  # noqa: E501
+            tf.__internal__.distribute.combinations.parameter_server_strategy_1worker_2ps_cpu,  # noqa: E501
+            tf.__internal__.distribute.combinations.parameter_server_strategy_1worker_2ps_1gpu,  # noqa: E501
             # NOTE: TPUStrategy not tested because the models in this test are
             # sparse and do not work with TPUs.
         ],
diff --git a/keras/distribute/keras_rnn_model_correctness_test.py b/keras/distribute/keras_rnn_model_correctness_test.py
index 14fe31c2e..0db1c58e1 100644
--- a/keras/distribute/keras_rnn_model_correctness_test.py
+++ b/keras/distribute/keras_rnn_model_correctness_test.py
@@ -31,7 +31,7 @@ from keras.testing_infra import test_utils
 
 
 class _DistributionStrategyRnnModelCorrectnessTest(
-    keras_correctness_test_base.TestDistributionStrategyEmbeddingModelCorrectnessBase
+    keras_correctness_test_base.TestDistributionStrategyEmbeddingModelCorrectnessBase  # noqa: E501
 ):
     def _get_layer_class(self):
         raise NotImplementedError
diff --git a/keras/distribute/keras_stateful_lstm_model_correctness_test.py b/keras/distribute/keras_stateful_lstm_model_correctness_test.py
index e7ad3057d..7896a468d 100644
--- a/keras/distribute/keras_stateful_lstm_model_correctness_test.py
+++ b/keras/distribute/keras_stateful_lstm_model_correctness_test.py
@@ -42,7 +42,7 @@ def test_combinations_for_stateful_embedding_model():
 
 
 class DistributionStrategyStatefulLstmModelCorrectnessTest(
-    keras_correctness_test_base.TestDistributionStrategyEmbeddingModelCorrectnessBase
+    keras_correctness_test_base.TestDistributionStrategyEmbeddingModelCorrectnessBase  # noqa: E501
 ):
     def get_model(
         self,
@@ -97,7 +97,7 @@ class DistributionStrategyStatefulLstmModelCorrectnessTest(
 
     @tf.__internal__.distribute.combinations.generate(
         tf.__internal__.test.combinations.times(
-            keras_correctness_test_base.test_combinations_with_tpu_strategies_graph()
+            keras_correctness_test_base.test_combinations_with_tpu_strategies_graph()  # noqa: E501
         )
     )
     def test_incorrectly_use_multiple_cores_for_stateful_lstm_model(
diff --git a/keras/distribute/keras_utils_test.py b/keras/distribute/keras_utils_test.py
index 659c5201f..8925801ea 100644
--- a/keras/distribute/keras_utils_test.py
+++ b/keras/distribute/keras_utils_test.py
@@ -197,7 +197,7 @@ class TestDistributionStrategyErrorCases(
     @tf.__internal__.distribute.combinations.generate(
         tf.__internal__.test.combinations.combine(
             distribution=[
-                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
+                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,  # noqa: E501
             ],
             mode=["graph"],
         )
@@ -227,14 +227,14 @@ class TestDistributionStrategyErrorCases(
                 "PerReplica:.+",
             ):
                 with distribution.scope():
-                    distributed_training_utils_v1.validate_distributed_dataset_inputs(
+                    distributed_training_utils_v1.validate_distributed_dataset_inputs(  # noqa: E501
                         distribution, x, None
                     )
 
     @tf.__internal__.distribute.combinations.generate(
         tf.__internal__.test.combinations.combine(
             distribution=[
-                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
+                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,  # noqa: E501
             ],
             mode=["graph", "eager"],
         )
@@ -264,14 +264,14 @@ class TestDistributionStrategyErrorCases(
                 "PerReplica:.+",
             ):
                 with distribution.scope():
-                    distributed_training_utils_v1.validate_distributed_dataset_inputs(
+                    distributed_training_utils_v1.validate_distributed_dataset_inputs(  # noqa: E501
                         distribution, x, None
                     )
 
     @tf.__internal__.distribute.combinations.generate(
         tf.__internal__.test.combinations.combine(
             distribution=[
-                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
+                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,  # noqa: E501
             ],
             mode=["graph", "eager"],
         )
@@ -322,7 +322,7 @@ class TestDistributionStrategyErrorCases(
     @tf.__internal__.distribute.combinations.generate(
         tf.__internal__.test.combinations.combine(
             distribution=[
-                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
+                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,  # noqa: E501
                 tf.__internal__.distribute.combinations.one_device_strategy,
             ],
             mode=["graph", "eager"],
@@ -355,7 +355,7 @@ class TestDistributionStrategyErrorCases(
     @tf.__internal__.distribute.combinations.generate(
         tf.__internal__.test.combinations.combine(
             distribution=[
-                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
+                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,  # noqa: E501
                 tf.__internal__.distribute.combinations.one_device_strategy,
             ],
             mode=["graph", "eager"],
@@ -406,10 +406,10 @@ class TestDistributionStrategyWithLossMasking(
     @tf.__internal__.distribute.combinations.generate(
         tf.__internal__.test.combinations.combine(
             distribution=[
-                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
+                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,  # noqa: E501
             ],
             mode=["graph", "eager"],
-            optimizer=optimizer_combinations.gradient_descent_optimizer_keras_v2_fn,
+            optimizer=optimizer_combinations.gradient_descent_optimizer_keras_v2_fn,  # noqa: E501
         )
     )
     def test_masking(self, distribution, optimizer):
@@ -443,7 +443,7 @@ class TestDistributionStrategyWithNormalizationLayer(
             keras_test_lib.all_strategy_combinations(),
             tf.__internal__.test.combinations.combine(
                 fused=[True, False],
-                optimizer=optimizer_combinations.gradient_descent_optimizer_keras_v2_fn,
+                optimizer=optimizer_combinations.gradient_descent_optimizer_keras_v2_fn,  # noqa: E501
             ),
         )
     )
@@ -489,7 +489,7 @@ class TestDistributionStrategyWithNormalizationLayer(
         tf.__internal__.test.combinations.times(
             keras_test_lib.tpu_strategy_combinations(),
             tf.__internal__.test.combinations.combine(
-                optimizer=optimizer_combinations.gradient_descent_optimizer_keras_v2_fn
+                optimizer=optimizer_combinations.gradient_descent_optimizer_keras_v2_fn  # noqa: E501
             ),
         )
     )
@@ -653,7 +653,7 @@ class TestDistributionStrategyWithStaticShapes(
     @tf.__internal__.distribute.combinations.generate(
         tf.__internal__.test.combinations.combine(
             distribution=[
-                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
+                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,  # noqa: E501
             ],
             mode=["graph", "eager"],
         )
@@ -670,7 +670,7 @@ class TestDistributionStrategyWithStaticShapes(
     @tf.__internal__.distribute.combinations.generate(
         tf.__internal__.test.combinations.combine(
             distribution=[
-                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
+                tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,  # noqa: E501
             ],
             mode=["graph", "eager"],
         )
diff --git a/keras/distribute/minimize_loss_test.py b/keras/distribute/minimize_loss_test.py
index 7f6ee3538..3f5b087a1 100644
--- a/keras/distribute/minimize_loss_test.py
+++ b/keras/distribute/minimize_loss_test.py
@@ -388,15 +388,15 @@ class MinimizeLossStepTest(tf.test.TestCase, parameterized.TestCase):
             tf.__internal__.test.combinations.times(
                 tf.__internal__.test.combinations.combine(
                     distribution=[
-                        tf.__internal__.distribute.combinations.one_device_strategy,
-                        tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
-                        tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,
-                        tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus_no_merge_call,
+                        tf.__internal__.distribute.combinations.one_device_strategy,  # noqa: E501
+                        tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,  # noqa: E501
+                        tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,  # noqa: E501
+                        tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus_no_merge_call,  # noqa: E501
                     ]
                 ),
                 tf.__internal__.test.combinations.times(
                     tf.__internal__.test.combinations.combine(
-                        optimizer_fn=optimizer_combinations.gradient_descent_optimizer_v1_fn
+                        optimizer_fn=optimizer_combinations.gradient_descent_optimizer_v1_fn  # noqa: E501
                     ),
                     tf.__internal__.test.combinations.combine(
                         mode=["graph"], use_callable_loss=[True, False]
@@ -407,7 +407,7 @@ class MinimizeLossStepTest(tf.test.TestCase, parameterized.TestCase):
                 )
                 + tf.__internal__.test.combinations.times(
                     tf.__internal__.test.combinations.combine(
-                        optimizer_fn=optimizer_combinations.gradient_descent_optimizer_keras_v2_fn
+                        optimizer_fn=optimizer_combinations.gradient_descent_optimizer_keras_v2_fn  # noqa: E501
                     ),
                     tf.__internal__.test.combinations.combine(
                         mode=["graph", "eager"], use_callable_loss=[True]
@@ -418,7 +418,7 @@ class MinimizeLossStepTest(tf.test.TestCase, parameterized.TestCase):
                 distribution=[
                     tf.__internal__.distribute.combinations.tpu_strategy
                 ],
-                optimizer_fn=optimizer_combinations.gradient_descent_optimizer_v1_fn,
+                optimizer_fn=optimizer_combinations.gradient_descent_optimizer_v1_fn,  # noqa: E501
                 mode=["graph"],
                 use_callable_loss=[True, False],
             )
@@ -426,7 +426,7 @@ class MinimizeLossStepTest(tf.test.TestCase, parameterized.TestCase):
                 distribution=[
                     tf.__internal__.distribute.combinations.tpu_strategy
                 ],
-                optimizer_fn=optimizer_combinations.gradient_descent_optimizer_keras_v2_fn,
+                optimizer_fn=optimizer_combinations.gradient_descent_optimizer_keras_v2_fn,  # noqa: E501
                 mode=["graph"],
                 use_callable_loss=[True],
             ),
diff --git a/keras/distribute/mirrored_strategy_test.py b/keras/distribute/mirrored_strategy_test.py
index 39b61f592..f4476c309 100644
--- a/keras/distribute/mirrored_strategy_test.py
+++ b/keras/distribute/mirrored_strategy_test.py
@@ -49,7 +49,7 @@ class MiniModel(keras_training.Model):
 @tf.__internal__.distribute.combinations.generate(
     tf.__internal__.test.combinations.combine(
         distribution=[
-            tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
+            tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,  # noqa: E501
         ],
         mode=["eager"],
     )
diff --git a/keras/distribute/mirrored_variable_test.py b/keras/distribute/mirrored_variable_test.py
index 192f18b06..e6a198f8b 100644
--- a/keras/distribute/mirrored_variable_test.py
+++ b/keras/distribute/mirrored_variable_test.py
@@ -51,7 +51,7 @@ def get_strategy_with_mimicing_cpus():
             filter(
                 None.__ne__,
                 [
-                    tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
+                    tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,  # noqa: E501
                     get_strategy_with_mimicing_cpus(),
                 ],
             )
diff --git a/keras/distribute/multi_worker_callback_tf2_test.py b/keras/distribute/multi_worker_callback_tf2_test.py
index 21ec37b5a..d107d9b5b 100644
--- a/keras/distribute/multi_worker_callback_tf2_test.py
+++ b/keras/distribute/multi_worker_callback_tf2_test.py
@@ -159,7 +159,7 @@ class KerasCallbackMultiProcessTest(parameterized.TestCase, tf.test.TestCase):
 
         tf.__internal__.distribute.multi_process_runner.run(
             proc_model_checkpoint_saves_on_chief_but_not_otherwise,
-            cluster_spec=tf.__internal__.distribute.multi_process_runner.create_cluster_spec(
+            cluster_spec=tf.__internal__.distribute.multi_process_runner.create_cluster_spec(  # noqa: E501
                 num_workers=2
             ),
             args=(self, file_format),
@@ -192,7 +192,7 @@ class KerasCallbackMultiProcessTest(parameterized.TestCase, tf.test.TestCase):
 
         tf.__internal__.distribute.multi_process_runner.run(
             proc_model_checkpoint_works_with_same_file_path,
-            cluster_spec=tf.__internal__.distribute.multi_process_runner.create_cluster_spec(
+            cluster_spec=tf.__internal__.distribute.multi_process_runner.create_cluster_spec(  # noqa: E501
                 num_workers=2
             ),
             args=(self, saving_filepath),
@@ -263,7 +263,7 @@ class KerasCallbackMultiProcessTest(parameterized.TestCase, tf.test.TestCase):
 
         tf.__internal__.distribute.multi_process_runner.run(
             proc_model_checkpoint_works_with_same_file_path,
-            cluster_spec=tf.__internal__.distribute.multi_process_runner.create_cluster_spec(
+            cluster_spec=tf.__internal__.distribute.multi_process_runner.create_cluster_spec(  # noqa: E501
                 num_workers=2
             ),
             args=(self, saving_filepath),
@@ -306,7 +306,7 @@ class KerasCallbackMultiProcessTest(parameterized.TestCase, tf.test.TestCase):
 
         tf.__internal__.distribute.multi_process_runner.run(
             proc_profiler_saves_on_both_chief_and_non_chief,
-            cluster_spec=tf.__internal__.distribute.multi_process_runner.create_cluster_spec(
+            cluster_spec=tf.__internal__.distribute.multi_process_runner.create_cluster_spec(  # noqa: E501
                 num_workers=2
             ),
             args=(self,),
@@ -357,7 +357,7 @@ class KerasCallbackMultiProcessTest(parameterized.TestCase, tf.test.TestCase):
 
         tf.__internal__.distribute.multi_process_runner.run(
             proc_tensorboard_saves_on_chief_but_not_otherwise,
-            cluster_spec=tf.__internal__.distribute.multi_process_runner.create_cluster_spec(
+            cluster_spec=tf.__internal__.distribute.multi_process_runner.create_cluster_spec(  # noqa: E501
                 num_workers=2
             ),
             args=(self,),
@@ -395,7 +395,7 @@ class KerasCallbackMultiProcessTest(parameterized.TestCase, tf.test.TestCase):
 
         tf.__internal__.distribute.multi_process_runner.run(
             proc_tensorboard_can_still_save_to_temp_even_if_it_exists,
-            cluster_spec=tf.__internal__.distribute.multi_process_runner.create_cluster_spec(
+            cluster_spec=tf.__internal__.distribute.multi_process_runner.create_cluster_spec(  # noqa: E501
                 num_workers=2
             ),
             args=(self,),
@@ -432,7 +432,7 @@ class KerasCallbackMultiProcessTest(parameterized.TestCase, tf.test.TestCase):
 
         tf.__internal__.distribute.multi_process_runner.run(
             proc_tensorboard_works_with_same_file_path,
-            cluster_spec=tf.__internal__.distribute.multi_process_runner.create_cluster_spec(
+            cluster_spec=tf.__internal__.distribute.multi_process_runner.create_cluster_spec(  # noqa: E501
                 num_workers=2
             ),
             args=(self, saving_filepath),
@@ -466,7 +466,7 @@ class KerasCallbackMultiProcessTest(parameterized.TestCase, tf.test.TestCase):
 
         tf.__internal__.distribute.multi_process_runner.run(
             proc_early_stopping,
-            cluster_spec=tf.__internal__.distribute.multi_process_runner.create_cluster_spec(
+            cluster_spec=tf.__internal__.distribute.multi_process_runner.create_cluster_spec(  # noqa: E501
                 num_workers=2
             ),
             args=(self,),
diff --git a/keras/distribute/multi_worker_test.py b/keras/distribute/multi_worker_test.py
index 571294757..8bdd6782e 100644
--- a/keras/distribute/multi_worker_test.py
+++ b/keras/distribute/multi_worker_test.py
@@ -194,8 +194,8 @@ class KerasMultiWorkerTestIndependentWorker(
         tf.__internal__.test.combinations.combine(
             mode=["eager"],
             strategy=[
-                tf.__internal__.distribute.combinations.multi_worker_mirrored_2x1_cpu,
-                tf.__internal__.distribute.combinations.multi_worker_mirrored_2x1_gpu,
+                tf.__internal__.distribute.combinations.multi_worker_mirrored_2x1_cpu,  # noqa: E501
+                tf.__internal__.distribute.combinations.multi_worker_mirrored_2x1_gpu,  # noqa: E501
             ],
         )
     )
@@ -236,7 +236,7 @@ class KPLMultiWorkerTest(tf.test.TestCase, parameterized.TestCase):
             mode=["eager"],
             use_adapt=[False],  # TODO(b/180742437): Add tests for using adapt.
             strategy=[
-                tf.__internal__.distribute.combinations.multi_worker_mirrored_2x1_gpu,
+                tf.__internal__.distribute.combinations.multi_worker_mirrored_2x1_gpu,  # noqa: E501
                 # TODO(b/183956672): Re-enable
                 # strategy_combinations.multi_worker_mirrored_2x2_gpu,
             ],
diff --git a/keras/distribute/optimizer_combinations.py b/keras/distribute/optimizer_combinations.py
index 30005886a..8f8390448 100644
--- a/keras/distribute/optimizer_combinations.py
+++ b/keras/distribute/optimizer_combinations.py
@@ -100,9 +100,9 @@ def distributions_and_v1_optimizers():
     return tf.__internal__.test.combinations.combine(
         distribution=[
             tf.__internal__.distribute.combinations.one_device_strategy,
-            tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
-            tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,
-            tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus_no_merge_call,
+            tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,  # noqa: E501
+            tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,  # noqa: E501
+            tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus_no_merge_call,  # noqa: E501
         ],
         optimizer_fn=optimizers_v1,
     )
@@ -114,9 +114,9 @@ def distributions_and_v2_optimizers():
     return tf.__internal__.test.combinations.combine(
         distribution=[
             tf.__internal__.distribute.combinations.one_device_strategy,
-            tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
-            tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,
-            tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus_no_merge_call,
+            tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,  # noqa: E501
+            tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,  # noqa: E501
+            tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus_no_merge_call,  # noqa: E501
         ],
         optimizer_fn=optimizers_v2,
     )
@@ -128,9 +128,9 @@ def distributions_and_v1_and_v2_optimizers():
     return tf.__internal__.test.combinations.combine(
         distribution=[
             tf.__internal__.distribute.combinations.one_device_strategy,
-            tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
-            tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,
-            tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus_no_merge_call,
+            tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,  # noqa: E501
+            tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,  # noqa: E501
+            tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus_no_merge_call,  # noqa: E501
         ],
         optimizer_fn=optimizers_v1_and_v2,
     )
diff --git a/keras/distribute/saved_model_test_base.py b/keras/distribute/saved_model_test_base.py
index c61ca361a..09e8e5aff 100644
--- a/keras/distribute/saved_model_test_base.py
+++ b/keras/distribute/saved_model_test_base.py
@@ -49,7 +49,7 @@ strategies = [
     tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,
     tf.__internal__.distribute.combinations.tpu_strategy,
     tf.__internal__.distribute.combinations.tpu_strategy_packed_var,
-    tf.__internal__.distribute.combinations.central_storage_strategy_with_two_gpus,
+    tf.__internal__.distribute.combinations.central_storage_strategy_with_two_gpus,  # noqa: E501
 ]
 
 
diff --git a/keras/distribute/sharded_variable_test.py b/keras/distribute/sharded_variable_test.py
index 11d29b8b1..bcd1250c1 100644
--- a/keras/distribute/sharded_variable_test.py
+++ b/keras/distribute/sharded_variable_test.py
@@ -30,7 +30,7 @@ class ShardedVariableTest(tf.test.TestCase, parameterized.TestCase):
         super().setUpClass()
         cls.strategy = tf.distribute.experimental.ParameterServerStrategy(
             multi_worker_testing_utils.make_parameter_server_cluster(3, 2),
-            variable_partitioner=tf.distribute.experimental.partitioners.FixedShardsPartitioner(
+            variable_partitioner=tf.distribute.experimental.partitioners.FixedShardsPartitioner(  # noqa: E501
                 2
             ),
         )
@@ -184,7 +184,7 @@ class ShardedVariableTest(tf.test.TestCase, parameterized.TestCase):
         if shard_config[0] > 2:
             strategy = tf.distribute.experimental.ParameterServerStrategy(
                 multi_worker_testing_utils.make_parameter_server_cluster(3, 3),
-                variable_partitioner=tf.distribute.experimental.partitioners.FixedShardsPartitioner(
+                variable_partitioner=tf.distribute.experimental.partitioners.FixedShardsPartitioner(  # noqa: E501
                     shard_config[0]
                 ),
             )
@@ -217,7 +217,7 @@ class ShardedVariableTest(tf.test.TestCase, parameterized.TestCase):
         if shard_config[1] > 2:
             strategy2 = tf.distribute.experimental.ParameterServerStrategy(
                 multi_worker_testing_utils.make_parameter_server_cluster(3, 3),
-                variable_partitioner=tf.distribute.experimental.partitioners.FixedShardsPartitioner(
+                variable_partitioner=tf.distribute.experimental.partitioners.FixedShardsPartitioner(  # noqa: E501
                     shard_config[1]
                 ),
             )
@@ -384,7 +384,7 @@ class ShardedVariableTest(tf.test.TestCase, parameterized.TestCase):
         # Create new strategy with different number of shards
         strategy2 = tf.distribute.experimental.ParameterServerStrategy(
             multi_worker_testing_utils.make_parameter_server_cluster(3, 2),
-            variable_partitioner=tf.distribute.experimental.partitioners.FixedShardsPartitioner(
+            variable_partitioner=tf.distribute.experimental.partitioners.FixedShardsPartitioner(  # noqa: E501
                 3
             ),
         )
diff --git a/keras/distribute/strategy_combinations.py b/keras/distribute/strategy_combinations.py
index ea7c0016a..8261e2386 100644
--- a/keras/distribute/strategy_combinations.py
+++ b/keras/distribute/strategy_combinations.py
@@ -33,7 +33,7 @@ strategies_minus_default_minus_tpu = [
     tf.__internal__.distribute.combinations.one_device_strategy_gpu,
     tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
     tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,
-    tf.__internal__.distribute.combinations.central_storage_strategy_with_gpu_and_cpu,
+    tf.__internal__.distribute.combinations.central_storage_strategy_with_gpu_and_cpu,  # noqa: E501
 ]
 
 strategies_minus_tpu = [
@@ -42,7 +42,7 @@ strategies_minus_tpu = [
     tf.__internal__.distribute.combinations.one_device_strategy_gpu,
     tf.__internal__.distribute.combinations.mirrored_strategy_with_gpu_and_cpu,
     tf.__internal__.distribute.combinations.mirrored_strategy_with_two_gpus,
-    tf.__internal__.distribute.combinations.central_storage_strategy_with_gpu_and_cpu,
+    tf.__internal__.distribute.combinations.central_storage_strategy_with_gpu_and_cpu,  # noqa: E501
 ]
 
 multi_worker_mirrored_strategies = [
@@ -56,13 +56,13 @@ tpu_strategies = [
 ]
 
 parameter_server_strategies_single_worker = [
-    tf.__internal__.distribute.combinations.parameter_server_strategy_1worker_2ps_cpu,
-    tf.__internal__.distribute.combinations.parameter_server_strategy_1worker_2ps_1gpu,
+    tf.__internal__.distribute.combinations.parameter_server_strategy_1worker_2ps_cpu,  # noqa: E501
+    tf.__internal__.distribute.combinations.parameter_server_strategy_1worker_2ps_1gpu,  # noqa: E501
 ]
 
 parameter_server_strategies_multi_worker = [
-    tf.__internal__.distribute.combinations.parameter_server_strategy_3worker_2ps_cpu,
-    tf.__internal__.distribute.combinations.parameter_server_strategy_3worker_2ps_1gpu,
+    tf.__internal__.distribute.combinations.parameter_server_strategy_3worker_2ps_cpu,  # noqa: E501
+    tf.__internal__.distribute.combinations.parameter_server_strategy_3worker_2ps_1gpu,  # noqa: E501
 ]
 
 all_strategies = strategies_minus_tpu + tpu_strategies
diff --git a/keras/dtensor/optimizers.py b/keras/dtensor/optimizers.py
index 79c5cb9de..a6af0f7c8 100644
--- a/keras/dtensor/optimizers.py
+++ b/keras/dtensor/optimizers.py
@@ -153,7 +153,7 @@ class Optimizer(optimizer_lib._BaseOptimizer):
     def _overwrite_model_variables_with_average_value_helper(self, var_list):
         """Helper function to _overwrite_model_variables_with_average_value."""
         (
-            optimizer_lib._BaseOptimizer._overwrite_model_variables_with_average_value_helper(
+            optimizer_lib._BaseOptimizer._overwrite_model_variables_with_average_value_helper(  # noqa: E501
                 self, var_list
             )
         )
diff --git a/keras/engine/training.py b/keras/engine/training.py
index bca7fafaa..b627d0eaf 100644
--- a/keras/engine/training.py
+++ b/keras/engine/training.py
@@ -1498,7 +1498,7 @@ class Model(base_layer.Layer, version_utils.ModelVersionSelector):
                 )
             )
 
-        with self.distribute_strategy.scope(), training_utils.RespectCompiledTrainableState(
+        with self.distribute_strategy.scope(), training_utils.RespectCompiledTrainableState(  # noqa: E501
             self
         ):
             # Creates a `tf.data.Dataset` and handles batch and epoch iteration.
@@ -2377,7 +2377,7 @@ class Model(base_layer.Layer, version_utils.ModelVersionSelector):
         _disallow_inside_tf_function("train_on_batch")
         if reset_metrics:
             self.reset_metrics()
-        with self.distribute_strategy.scope(), training_utils.RespectCompiledTrainableState(
+        with self.distribute_strategy.scope(), training_utils.RespectCompiledTrainableState(  # noqa: E501
             self
         ):
             iterator = data_adapter.single_batch_iterator(
diff --git a/keras/engine/training_arrays_v1.py b/keras/engine/training_arrays_v1.py
index 298714c9c..f44bdc483 100644
--- a/keras/engine/training_arrays_v1.py
+++ b/keras/engine/training_arrays_v1.py
@@ -306,7 +306,7 @@ def model_iteration(
                     # case.
                     if not callable(ins) or (
                         model._distribution_strategy
-                        and not distributed_training_utils_v1.is_distributing_by_cloning(
+                        and not distributed_training_utils_v1.is_distributing_by_cloning(  # noqa: E501
                             model
                         )
                     ):
@@ -353,7 +353,7 @@ def model_iteration(
                     batch_outs = [batch_outs]
 
                 if model._distribution_strategy:
-                    batch_outs = distributed_training_utils_v1._per_replica_aggregate_batch(
+                    batch_outs = distributed_training_utils_v1._per_replica_aggregate_batch(  # noqa: E501
                         model._distribution_strategy, batch_outs, model, mode
                     )
 
diff --git a/keras/engine/training_dataset_test.py b/keras/engine/training_dataset_test.py
index 4aab91231..500c48d58 100644
--- a/keras/engine/training_dataset_test.py
+++ b/keras/engine/training_dataset_test.py
@@ -346,7 +346,7 @@ class TestTrainingWithDataset(test_combinations.TestCase):
         )
 
     def test_dataset_input_shape_validation(self):
-        with tf.compat.v1.get_default_graph().as_default(), self.cached_session():
+        with tf.compat.v1.get_default_graph().as_default(), self.cached_session():  # noqa: E501
             model = test_utils.get_small_functional_mlp(1, 4, input_dim=3)
             model.compile(optimizer="rmsprop", loss="mse")
 
diff --git a/keras/engine/training_gpu_test.py b/keras/engine/training_gpu_test.py
index 1e99035fc..602b871e3 100644
--- a/keras/engine/training_gpu_test.py
+++ b/keras/engine/training_gpu_test.py
@@ -45,7 +45,7 @@ class TrainingGPUTest(tf.test.TestCase, parameterized.TestCase):
             num_channels = None
             activation = None
             if loss_name == "sparse_categorical_crossentropy":
-                loss = lambda y_true, y_pred: backend.sparse_categorical_crossentropy(
+                loss = lambda y_true, y_pred: backend.sparse_categorical_crossentropy(  # noqa: E501
                     y_true, y_pred, axis=axis
                 )
                 num_channels = int(np.amax(target) + 1)
diff --git a/keras/engine/training_v1.py b/keras/engine/training_v1.py
index 37e23962a..918a8829e 100644
--- a/keras/engine/training_v1.py
+++ b/keras/engine/training_v1.py
@@ -644,12 +644,12 @@ class Model(training_lib.Model):
         # Case 1: distribution strategy.
         if self._distribution_strategy:
             if self._in_multi_worker_mode():
-                return training_distributed_v1.DistributionMultiWorkerTrainingLoop(
-                    training_distributed_v1.DistributionSingleWorkerTrainingLoop()
+                return training_distributed_v1.DistributionMultiWorkerTrainingLoop(  # noqa: E501
+                    training_distributed_v1.DistributionSingleWorkerTrainingLoop()  # noqa: E501
                 )
             else:
                 return (
-                    training_distributed_v1.DistributionSingleWorkerTrainingLoop()
+                    training_distributed_v1.DistributionSingleWorkerTrainingLoop()  # noqa: E501
                 )
 
         # Case 2: generator-like. Input is Python generator, or Sequence object,
diff --git a/keras/feature_column/sequence_feature_column.py b/keras/feature_column/sequence_feature_column.py
index e96dd037b..cc9b96959 100644
--- a/keras/feature_column/sequence_feature_column.py
+++ b/keras/feature_column/sequence_feature_column.py
@@ -101,7 +101,7 @@ class SequenceFeatures(kfc._BaseFeaturesLayer):
             feature_columns=feature_columns,
             trainable=trainable,
             name=name,
-            expected_column_type=tf.__internal__.feature_column.SequenceDenseColumn,
+            expected_column_type=tf.__internal__.feature_column.SequenceDenseColumn,  # noqa: E501
             **kwargs
         )
 
diff --git a/keras/feature_column/sequence_feature_column_test.py b/keras/feature_column/sequence_feature_column_test.py
index 80d441138..0cc46cc7d 100644
--- a/keras/feature_column/sequence_feature_column_test.py
+++ b/keras/feature_column/sequence_feature_column_test.py
@@ -926,7 +926,7 @@ class SequenceFeaturesSavingTest(tf.test.TestCase, parameterized.TestCase):
         cols = [
             tf.feature_column.sequence_numeric_column("a"),
             tf.feature_column.indicator_column(
-                tf.feature_column.sequence_categorical_column_with_vocabulary_list(
+                tf.feature_column.sequence_categorical_column_with_vocabulary_list(  # noqa: E501
                     "b", ["one", "two"]
                 )
             ),
diff --git a/keras/integration_test/multi_worker_tutorial_test.py b/keras/integration_test/multi_worker_tutorial_test.py
index 9134d12b2..89df14576 100644
--- a/keras/integration_test/multi_worker_tutorial_test.py
+++ b/keras/integration_test/multi_worker_tutorial_test.py
@@ -242,7 +242,7 @@ class MultiWorkerTutorialTest(parameterized.TestCase, tf.test.TestCase):
         try:
             mpr_result = tf.__internal__.distribute.multi_process_runner.run(
                 fn,
-                tf.__internal__.distribute.multi_process_runner.create_cluster_spec(
+                tf.__internal__.distribute.multi_process_runner.create_cluster_spec(  # noqa: E501
                     num_workers=NUM_WORKERS
                 ),
                 args=(model_path, checkpoint_dir),
diff --git a/keras/layers/core/core_test.py b/keras/layers/core/core_test.py
index 6cecb3581..44f4d866f 100644
--- a/keras/layers/core/core_test.py
+++ b/keras/layers/core/core_test.py
@@ -352,11 +352,12 @@ class TestStatefulLambda(test_combinations.TestCase):
 
         expected_error = textwrap.dedent(
             r"""
-    (    )?The following Variables were created within a Lambda layer \(shift_and_scale\)
-    (    )?but are not tracked by said layer:
-    (    )?  <tf.Variable \'.*shift_and_scale/scale:0\'.+
-    (    )?  <tf.Variable \'.*shift_and_scale/shift:0\'.+
-    (    )?The layer cannot safely ensure proper Variable reuse.+"""
+(    )?The following Variables were created within a Lambda layer \(shift_and_scale\)"""  # noqa: E501
+            r"""
+(    )?but are not tracked by said layer:
+(    )?  <tf.Variable \'.*shift_and_scale/scale:0\'.+
+(    )?  <tf.Variable \'.*shift_and_scale/shift:0\'.+
+(    )?The layer cannot safely ensure proper Variable reuse.+"""
         )
 
         with self.assertRaisesRegex(ValueError, expected_error):
@@ -374,10 +375,10 @@ class TestStatefulLambda(test_combinations.TestCase):
 
         expected_error = textwrap.dedent(
             r"""
-    (    )?The following Variables were created within a Lambda layer \(bias_dense\)
-    (    )?but are not tracked by said layer:
-    (    )?  <tf.Variable \'.*bias_dense/dense/kernel:0\'.+
-    (    )?The layer cannot safely ensure proper Variable reuse.+"""
+(    )?The following Variables were created within a Lambda layer \(bias_dense\)
+(    )?but are not tracked by said layer:
+(    )?  <tf.Variable \'.*bias_dense/dense/kernel:0\'.+
+(    )?The layer cannot safely ensure proper Variable reuse.+"""
         )
 
         with self.assertRaisesRegex(ValueError, expected_error):
@@ -395,10 +396,10 @@ class TestStatefulLambda(test_combinations.TestCase):
 
         expected_warning = textwrap.dedent(
             r"""
-    (    )?The following Variables were used a Lambda layer\'s call \(lambda\), but
-    (    )?are not present in its tracked objects:
-    (    )?  <tf.Variable \'.*Variable:0\'.+
-    (    )?It is possible that this is intended behavior.+"""
+(    )?The following Variables were used a Lambda layer\'s call \(lambda\), but
+(    )?are not present in its tracked objects:
+(    )?  <tf.Variable \'.*Variable:0\'.+
+(    )?It is possible that this is intended behavior.+"""
         )
 
         layer = keras.layers.Lambda(lambda_fn)
diff --git a/keras/legacy_tf_layers/variable_scope_shim_test.py b/keras/legacy_tf_layers/variable_scope_shim_test.py
index 88c1077bd..0f38ca7de 100644
--- a/keras/legacy_tf_layers/variable_scope_shim_test.py
+++ b/keras/legacy_tf_layers/variable_scope_shim_test.py
@@ -958,7 +958,7 @@ class VariableScopeModule(tf.Module):
         `get_variable`&`compat.v1.layers`."""
         return {
             name: regularizer()
-            for name, regularizer in self._tf1_style_var_store._regularizers.items()
+            for name, regularizer in self._tf1_style_var_store._regularizers.items()  # noqa: E501
         }  # pylint: disable=protected-access
 
 
@@ -1148,7 +1148,7 @@ class TF1VariableScopeLayerTest(tf.test.TestCase, parameterized.TestCase):
                 """Dict w/ regularization losses from `get_variable`."""
                 return {
                     name: regularizer()
-                    for name, regularizer in self._variable_store._regularizers.items()
+                    for name, regularizer in self._variable_store._regularizers.items()  # noqa: E501
                 }  # pylint: disable=protected-access
 
             def __call__(self, inputs, training=None):
diff --git a/keras/metrics/base_metric.py b/keras/metrics/base_metric.py
index d16707f69..0aeeab32d 100644
--- a/keras/metrics/base_metric.py
+++ b/keras/metrics/base_metric.py
@@ -455,7 +455,7 @@ class Reduce(Metric):
         """
         [
             values
-        ], sample_weight = metrics_utils.ragged_assert_compatible_and_get_flat_values(
+        ], sample_weight = metrics_utils.ragged_assert_compatible_and_get_flat_values(  # noqa: E501
             [values], sample_weight
         )
         try:
@@ -687,7 +687,7 @@ class MeanMetricWrapper(Mean):
         [
             y_true,
             y_pred,
-        ], sample_weight = metrics_utils.ragged_assert_compatible_and_get_flat_values(
+        ], sample_weight = metrics_utils.ragged_assert_compatible_and_get_flat_values(  # noqa: E501
             [y_true, y_pred], sample_weight
         )
         y_pred, y_true = losses_utils.squeeze_or_expand_dimensions(
diff --git a/keras/metrics/base_metric_test.py b/keras/metrics/base_metric_test.py
index f02ced1f6..235ebb4d3 100644
--- a/keras/metrics/base_metric_test.py
+++ b/keras/metrics/base_metric_test.py
@@ -102,7 +102,7 @@ class KerasSumTest(tf.test.TestCase, parameterized.TestCase):
         self.assertAlmostEqual(self.evaluate(m.total), 63.75, 2)
 
     def test_sum_graph_with_placeholder(self):
-        with tf.compat.v1.get_default_graph().as_default(), self.cached_session() as sess:
+        with tf.compat.v1.get_default_graph().as_default(), self.cached_session() as sess:  # noqa: E501
             m = metrics.Sum()
             v = tf.compat.v1.placeholder(tf.float32)
             w = tf.compat.v1.placeholder(tf.float32)
@@ -261,7 +261,7 @@ class MeanTest(test_combinations.TestCase):
 
     @test_combinations.run_all_keras_modes
     def test_mean_graph_with_placeholder(self):
-        with tf.compat.v1.get_default_graph().as_default(), self.cached_session() as sess:
+        with tf.compat.v1.get_default_graph().as_default(), self.cached_session() as sess:  # noqa: E501
             m = metrics.Mean()
             v = tf.compat.v1.placeholder(tf.float32)
             w = tf.compat.v1.placeholder(tf.float32)
diff --git a/keras/metrics/metrics.py b/keras/metrics/metrics.py
index b2acaa6b9..5f3f63291 100644
--- a/keras/metrics/metrics.py
+++ b/keras/metrics/metrics.py
@@ -110,7 +110,7 @@ class MeanRelativeError(base_metric.Mean):
         [
             y_pred,
             y_true,
-        ], sample_weight = metrics_utils.ragged_assert_compatible_and_get_flat_values(
+        ], sample_weight = metrics_utils.ragged_assert_compatible_and_get_flat_values(  # noqa: E501
             [y_pred, y_true], sample_weight
         )
         y_pred, y_true = losses_utils.squeeze_or_expand_dimensions(
@@ -902,8 +902,8 @@ class Precision(base_metric.Metric):
         """
         return metrics_utils.update_confusion_matrix_variables(
             {
-                metrics_utils.ConfusionMatrix.TRUE_POSITIVES: self.true_positives,
-                metrics_utils.ConfusionMatrix.FALSE_POSITIVES: self.false_positives,
+                metrics_utils.ConfusionMatrix.TRUE_POSITIVES: self.true_positives,  # noqa: E501
+                metrics_utils.ConfusionMatrix.FALSE_POSITIVES: self.false_positives,  # noqa: E501
             },
             y_true,
             y_pred,
@@ -1048,8 +1048,8 @@ class Recall(base_metric.Metric):
         """
         return metrics_utils.update_confusion_matrix_variables(
             {
-                metrics_utils.ConfusionMatrix.TRUE_POSITIVES: self.true_positives,
-                metrics_utils.ConfusionMatrix.FALSE_NEGATIVES: self.false_negatives,
+                metrics_utils.ConfusionMatrix.TRUE_POSITIVES: self.true_positives,  # noqa: E501
+                metrics_utils.ConfusionMatrix.FALSE_NEGATIVES: self.false_negatives,  # noqa: E501
             },
             y_true,
             y_pred,
@@ -1144,10 +1144,10 @@ class SensitivitySpecificityBase(base_metric.Metric, metaclass=abc.ABCMeta):
         """
         return metrics_utils.update_confusion_matrix_variables(
             {
-                metrics_utils.ConfusionMatrix.TRUE_POSITIVES: self.true_positives,
-                metrics_utils.ConfusionMatrix.TRUE_NEGATIVES: self.true_negatives,
-                metrics_utils.ConfusionMatrix.FALSE_POSITIVES: self.false_positives,
-                metrics_utils.ConfusionMatrix.FALSE_NEGATIVES: self.false_negatives,
+                metrics_utils.ConfusionMatrix.TRUE_POSITIVES: self.true_positives,  # noqa: E501
+                metrics_utils.ConfusionMatrix.TRUE_NEGATIVES: self.true_negatives,  # noqa: E501
+                metrics_utils.ConfusionMatrix.FALSE_POSITIVES: self.false_positives,  # noqa: E501
+                metrics_utils.ConfusionMatrix.FALSE_NEGATIVES: self.false_negatives,  # noqa: E501
             },
             y_true,
             y_pred,
@@ -1918,10 +1918,10 @@ class AUC(base_metric.Metric):
 
         return metrics_utils.update_confusion_matrix_variables(
             {
-                metrics_utils.ConfusionMatrix.TRUE_POSITIVES: self.true_positives,
-                metrics_utils.ConfusionMatrix.TRUE_NEGATIVES: self.true_negatives,
-                metrics_utils.ConfusionMatrix.FALSE_POSITIVES: self.false_positives,
-                metrics_utils.ConfusionMatrix.FALSE_NEGATIVES: self.false_negatives,
+                metrics_utils.ConfusionMatrix.TRUE_POSITIVES: self.true_positives,  # noqa: E501
+                metrics_utils.ConfusionMatrix.TRUE_NEGATIVES: self.true_negatives,  # noqa: E501
+                metrics_utils.ConfusionMatrix.FALSE_POSITIVES: self.false_positives,  # noqa: E501
+                metrics_utils.ConfusionMatrix.FALSE_NEGATIVES: self.false_negatives,  # noqa: E501
             },
             y_true,
             y_pred,
diff --git a/keras/metrics/metrics_correctness_test.py b/keras/metrics/metrics_correctness_test.py
index 0987de4c6..6532a1512 100644
--- a/keras/metrics/metrics_correctness_test.py
+++ b/keras/metrics/metrics_correctness_test.py
@@ -709,7 +709,7 @@ class TestOutputLossMetrics(test_combinations.TestCase):
                 "output_2_loss": [116, 116],
             },
             losses_utils.ReductionV2.AUTO: sum_over_batch_size_fit_result,
-            losses_utils.ReductionV2.SUM_OVER_BATCH_SIZE: sum_over_batch_size_fit_result,
+            losses_utils.ReductionV2.SUM_OVER_BATCH_SIZE: sum_over_batch_size_fit_result,  # noqa: E501
         }
 
         # In the order: 'loss', 'output_1_loss', 'output_2_loss',
diff --git a/keras/metrics/metrics_test.py b/keras/metrics/metrics_test.py
index 8d8a71b3a..01ae71b6d 100644
--- a/keras/metrics/metrics_test.py
+++ b/keras/metrics/metrics_test.py
@@ -259,7 +259,7 @@ class KerasAccuracyTest(tf.test.TestCase):
         self.assertAlmostEqual(result, 0.93, 2)  # 2.5/2.7
 
     def test_sparse_categorical_accuracy_mismatched_dims_dynamic(self):
-        with tf.compat.v1.get_default_graph().as_default(), self.cached_session() as sess:
+        with tf.compat.v1.get_default_graph().as_default(), self.cached_session() as sess:  # noqa: E501
             acc_obj = metrics.SparseCategoricalAccuracy(name="my_acc")
             self.evaluate(tf.compat.v1.variables_initializer(acc_obj.variables))
 
diff --git a/keras/mixed_precision/autocast_variable_test.py b/keras/mixed_precision/autocast_variable_test.py
index f4ad021d8..6c39cfd64 100644
--- a/keras/mixed_precision/autocast_variable_test.py
+++ b/keras/mixed_precision/autocast_variable_test.py
@@ -36,7 +36,7 @@ from keras.optimizers.optimizer_v2 import rmsprop
 maybe_distribute = tf.__internal__.test.combinations.combine(
     distribution=[
         tf.__internal__.distribute.combinations.default_strategy,
-        tf.__internal__.distribute.combinations.mirrored_strategy_with_cpu_1_and_2,
+        tf.__internal__.distribute.combinations.mirrored_strategy_with_cpu_1_and_2,  # noqa: E501
     ]
 )
 
diff --git a/keras/mixed_precision/loss_scale_optimizer.py b/keras/mixed_precision/loss_scale_optimizer.py
index a888dd848..3d79b1db8 100644
--- a/keras/mixed_precision/loss_scale_optimizer.py
+++ b/keras/mixed_precision/loss_scale_optimizer.py
@@ -106,7 +106,7 @@ def _maybe_warn_about_scaling(
             "LossScaleOptimizer.apply_gradients(). This will likely result in "
             "worse model quality, so please call them in the correct places! "
             f"For example:{example_code}\nFor more information, see "
-            "https://www.tensorflow.org/api_docs/python/tf/keras/mixed_precision/LossScaleOptimizer"
+            "https://www.tensorflow.org/api_docs/python/tf/keras/mixed_precision/LossScaleOptimizer"  # noqa: E501
         )
     elif not loss_has_been_scaled:
         tf_logging.warning(
@@ -116,7 +116,7 @@ def _maybe_warn_about_scaling(
             "worse model quality, so please call get_scaled_loss() in the "
             f"correct place! For example:{example_code}\nFor more information, "
             "see "
-            "https://www.tensorflow.org/api_docs/python/tf/keras/mixed_precision/LossScaleOptimizer"
+            "https://www.tensorflow.org/api_docs/python/tf/keras/mixed_precision/LossScaleOptimizer"  # noqa: E501
         )
     elif not gradients_have_been_unscaled:
         tf_logging.warning(
@@ -126,7 +126,7 @@ def _maybe_warn_about_scaling(
             "model quality, so please call get_unscaled_gradients() in the "
             f"correct place! For example:{example_code}\nFor more information, "
             "see "
-            "https://www.tensorflow.org/api_docs/python/tf/keras/mixed_precision/LossScaleOptimizer"
+            "https://www.tensorflow.org/api_docs/python/tf/keras/mixed_precision/LossScaleOptimizer"  # noqa: E501
         )
 
 
@@ -899,8 +899,8 @@ class LossScaleOptimizer(
             loss_scale = generic_utils.deserialize_keras_object(
                 config.pop("loss_scale"),
                 module_objects={
-                    "FixedLossScale": tf.compat.v1.mixed_precision.FixedLossScale,
-                    "DynamicLossScale": tf.compat.v1.mixed_precision.DynamicLossScale,
+                    "FixedLossScale": tf.compat.v1.mixed_precision.FixedLossScale,  # noqa: E501
+                    "DynamicLossScale": tf.compat.v1.mixed_precision.DynamicLossScale,  # noqa: E501
                 },
                 printable_module_name="loss scale",
             )
diff --git a/keras/mixed_precision/mixed_precision_graph_rewrite_test.py b/keras/mixed_precision/mixed_precision_graph_rewrite_test.py
index 487f66f0d..dca280ebf 100644
--- a/keras/mixed_precision/mixed_precision_graph_rewrite_test.py
+++ b/keras/mixed_precision/mixed_precision_graph_rewrite_test.py
@@ -164,7 +164,7 @@ class MixedPrecisionTest(test_combinations.TestCase):
             with self.assertRaisesRegex(
                 ValueError, "the global Keras dtype Policy has been set"
             ):
-                tf.compat.v1.mixed_precision.enable_mixed_precision_graph_rewrite(
+                tf.compat.v1.mixed_precision.enable_mixed_precision_graph_rewrite(  # noqa: E501
                     gradient_descent_v2.SGD(1.0)
                 )
         # Test no error is thrown when the policy is currently the default.
diff --git a/keras/optimizers/optimizer_experimental/ftrl.py b/keras/optimizers/optimizer_experimental/ftrl.py
index 34ff0a991..04f3cfe14 100644
--- a/keras/optimizers/optimizer_experimental/ftrl.py
+++ b/keras/optimizers/optimizer_experimental/ftrl.py
@@ -240,7 +240,7 @@ class Ftrl(optimizer.Optimizer):
                 "initial_accumulator_value": self.initial_accumulator_value,
                 "l1_regularization_strength": self.l1_regularization_strength,
                 "l2_regularization_strength": self.l2_regularization_strength,
-                "l2_shrinkage_regularization_strength": self.l2_shrinkage_regularization_strength,
+                "l2_shrinkage_regularization_strength": self.l2_shrinkage_regularization_strength,  # noqa: E501
                 "beta": self.beta,
             }
         )
diff --git a/keras/optimizers/optimizer_experimental/optimizer.py b/keras/optimizers/optimizer_experimental/optimizer.py
index f38984da8..3cf374f60 100644
--- a/keras/optimizers/optimizer_experimental/optimizer.py
+++ b/keras/optimizers/optimizer_experimental/optimizer.py
@@ -605,20 +605,20 @@ base_optimizer_keyword_args = """name: String. The name to use
         average of the weights of the model (as the weight values change after
         each training batch), and periodically overwriting the weights with
         their moving average.
-      ema_momentum: Float, defaults to 0.99. Only used if `use_ema=True`. This is
+      ema_momentum: Float, defaults to 0.99. Only used if `use_ema=True`. This is  # noqa: E501
         the momentum to use when computing the EMA of the model's weights:
         `new_average = ema_momentum * old_average + (1 - ema_momentum) *
         current_variable_value`.
       ema_overwrite_frequency: Int or None, defaults to None. Only used if
         `use_ema=True`. Every `ema_overwrite_frequency` steps of iterations, we
-        overwrite the model variable by its moving average. If None, the optimizer
+        overwrite the model variable by its moving average. If None, the optimizer  # noqa: E501
          does not overwrite model variables in the middle of training, and you
         need to explicitly overwrite the variables at the end of training
-        by calling `optimizer.finalize_variable_values()` (which updates the model
+        by calling `optimizer.finalize_variable_values()` (which updates the model  # noqa: E501
         variables in-place). When using the built-in `fit()` training loop, this
         happens automatically after the last epoch, and you don't need to do
         anything.
-      jit_compile: Boolean, defaults to True. If True, the optimizer will use XLA
+      jit_compile: Boolean, defaults to True. If True, the optimizer will use XLA  # noqa: E501
         compilation. If no GPU device is found, this flag will be ignored.
       **kwargs: keyword arguments only used for backward compatibility."""
 
@@ -943,7 +943,7 @@ class Optimizer(_BaseOptimizer):
                 )
                 tf.cond(
                     tf.cast(should_overwrite_model_vars, tf.bool),
-                    true_fn=lambda: self._overwrite_model_variables_with_average_value(
+                    true_fn=lambda: self._overwrite_model_variables_with_average_value(  # noqa: E501
                         var_list
                     ),
                     false_fn=lambda: None,
diff --git a/keras/optimizers/optimizer_v2/ftrl.py b/keras/optimizers/optimizer_v2/ftrl.py
index eb41aec74..3192db40d 100644
--- a/keras/optimizers/optimizer_v2/ftrl.py
+++ b/keras/optimizers/optimizer_v2/ftrl.py
@@ -300,7 +300,7 @@ class Ftrl(optimizer_v2.OptimizerV2):
                     "l2_regularization_strength"
                 ),
                 "beta": self._serialize_hyperparameter("beta"),
-                "l2_shrinkage_regularization_strength": self._l2_shrinkage_regularization_strength,
+                "l2_shrinkage_regularization_strength": self._l2_shrinkage_regularization_strength,  # noqa: E501
             }
         )
         return config
diff --git a/keras/optimizers/optimizer_v2/optimizer_v2.py b/keras/optimizers/optimizer_v2/optimizer_v2.py
index 0d645b347..83d4c0794 100644
--- a/keras/optimizers/optimizer_v2/optimizer_v2.py
+++ b/keras/optimizers/optimizer_v2/optimizer_v2.py
@@ -606,7 +606,8 @@ class OptimizerV2(tf.__internal__.tracking.Trackable):
           gradient can be `None`.
 
         Raises:
-          TypeError: If `var_list` contains anything else than `Variable` objects.
+          TypeError: If `var_list` contains anything else than `Variable`
+            objects.
           ValueError: If some arguments are invalid, or var_list is None.
         """
         # TODO(joshl): Test that we handle weight decay in a reasonable way.
@@ -713,10 +714,10 @@ class OptimizerV2(tf.__internal__.tracking.Trackable):
                 and isinstance(
                     strategy,
                     (
-                        tf.compat.v1.distribute.experimental.ParameterServerStrategy,
+                        tf.compat.v1.distribute.experimental.ParameterServerStrategy,  # noqa: E501
                         tf.distribute.experimental.ParameterServerStrategy,
                         tf.distribute.experimental.CentralStorageStrategy,
-                        tf.compat.v1.distribute.experimental.CentralStorageStrategy,
+                        tf.compat.v1.distribute.experimental.CentralStorageStrategy,  # noqa: E501
                     ),
                 )
             ):
diff --git a/keras/optimizers/optimizer_v2/rmsprop_test.py b/keras/optimizers/optimizer_v2/rmsprop_test.py
index 14603e9c6..a16a7fcaa 100644
--- a/keras/optimizers/optimizer_v2/rmsprop_test.py
+++ b/keras/optimizers/optimizer_v2/rmsprop_test.py
@@ -115,7 +115,7 @@ class RMSpropOptimizerTest(tf.test.TestCase, parameterized.TestCase):
             epsilon,
             centered,
         ) in _TESTPARAMS:
-            with tf.compat.v1.get_default_graph().as_default(), test_utils.use_gpu():
+            with tf.compat.v1.get_default_graph().as_default(), test_utils.use_gpu():  # noqa: E501
                 # Initialize variables for numpy implementation.
                 var0_np = np.array([1.0, 2.0], dtype=dtype.as_numpy_dtype)
                 grads0_np = np.array([0.1, 0.2], dtype=dtype.as_numpy_dtype)
@@ -504,7 +504,7 @@ class RMSpropOptimizerTest(tf.test.TestCase, parameterized.TestCase):
             epsilon,
             centered,
         ) in _TESTPARAMS:
-            with tf.compat.v1.get_default_graph().as_default(), test_utils.use_gpu():
+            with tf.compat.v1.get_default_graph().as_default(), test_utils.use_gpu():  # noqa: E501
                 # Initialize variables for numpy implementation.
                 var0_np = np.array([1.0, 2.0], dtype=dtype.as_numpy_dtype)
                 grads0_np = np.array([0.1], dtype=dtype.as_numpy_dtype)
diff --git a/keras/optimizers/optimizer_v2/utils.py b/keras/optimizers/optimizer_v2/utils.py
index b4cf8fe50..5abde9c07 100644
--- a/keras/optimizers/optimizer_v2/utils.py
+++ b/keras/optimizers/optimizer_v2/utils.py
@@ -130,7 +130,8 @@ def make_global_gradient_clipnorm_fn(clipnorm):
             ),
         ):
             raise ValueError(
-                "`global_clipnorm` is not supported with `CenteralStorageStrategy`. "
+                "`global_clipnorm` is not supported with "
+                "`CenteralStorageStrategy`. "
                 f"The strategy used is {tf.distribute.get_strategy()}."
             )
 
diff --git a/keras/saving/save_test.py b/keras/saving/save_test.py
index 44b9a2e76..4997064ef 100644
--- a/keras/saving/save_test.py
+++ b/keras/saving/save_test.py
@@ -343,7 +343,7 @@ class TestJson(test_combinations.TestCase):
         cols = [
             tf.feature_column.sequence_numeric_column("a"),
             tf.feature_column.indicator_column(
-                tf.feature_column.sequence_categorical_column_with_vocabulary_list(
+                tf.feature_column.sequence_categorical_column_with_vocabulary_list(  # noqa: E501
                     "b", ["one", "two"]
                 )
             ),
diff --git a/keras/saving/saved_model/revive_test.py b/keras/saving/saved_model/revive_test.py
index 37039f5fd..b002e133e 100644
--- a/keras/saving/saved_model/revive_test.py
+++ b/keras/saving/saved_model/revive_test.py
@@ -463,7 +463,7 @@ if __name__ == "__main__":
             "CustomNetworkWithConfigName": CustomNetworkWithConfigName,
             "SubclassedModelWithConfig": SubclassedModelWithConfig,
             "FunctionalSubclassModel": FunctionalSubclassModel,
-            "FunctionalSubclassModelWrongConfig": FunctionalSubclassModelWrongConfig,
+            "FunctionalSubclassModelWrongConfig": FunctionalSubclassModelWrongConfig,  # noqa: E501
             "WideDeepModel": WideDeepModel,
         }
     ):
diff --git a/keras/saving/saved_model/save_impl.py b/keras/saving/saved_model/save_impl.py
index ceedb8918..0a1b2d1e3 100644
--- a/keras/saving/saved_model/save_impl.py
+++ b/keras/saving/saved_model/save_impl.py
@@ -311,7 +311,7 @@ def _replace_child_layer_functions(layer, serialization_cache):
             continue
 
         if child_layer not in serialization_cache[constants.KERAS_CACHE_KEY]:
-            serialized_functions = child_layer._trackable_saved_model_saver._get_serialized_attributes(
+            serialized_functions = child_layer._trackable_saved_model_saver._get_serialized_attributes(  # noqa: E501
                 serialization_cache
             ).functions
         else:
diff --git a/keras/saving/saved_model/saved_model_test.py b/keras/saving/saved_model/saved_model_test.py
index 7f099ac1c..f0c70e9b6 100644
--- a/keras/saving/saved_model/saved_model_test.py
+++ b/keras/saving/saved_model/saved_model_test.py
@@ -1250,7 +1250,7 @@ class TestLayerCallTracing(tf.test.TestCase, parameterized.TestCase):
             {(2, 3), (4, 5)},
             set(
                 tuple(c.structured_input_signature[0][0].shape.as_list())
-                for c in fn2.wrapped_call._list_all_concrete_functions_for_serialization()
+                for c in fn2.wrapped_call._list_all_concrete_functions_for_serialization()  # noqa: E501
             ),
         )
 
@@ -1263,13 +1263,13 @@ class TestLayerCallTracing(tf.test.TestCase, parameterized.TestCase):
             with keras_save.tracing_scope():
                 fn(np.ones((2, 3)), training=True)
             self.assertLen(
-                fn.wrapped_call._list_all_concrete_functions_for_serialization(),
+                fn.wrapped_call._list_all_concrete_functions_for_serialization(),  # noqa: E501
                 2,
             )
             with keras_save.tracing_scope():
                 fn(np.ones((2, 4)), training=False)
             self.assertLen(
-                fn.wrapped_call._list_all_concrete_functions_for_serialization(),
+                fn.wrapped_call._list_all_concrete_functions_for_serialization(),  # noqa: E501
                 4,
             )
 
@@ -1277,13 +1277,13 @@ class TestLayerCallTracing(tf.test.TestCase, parameterized.TestCase):
                 with keras_save.tracing_scope():
                     fn(np.ones((2, 5)), True)
                 self.assertLen(
-                    fn.wrapped_call._list_all_concrete_functions_for_serialization(),
+                    fn.wrapped_call._list_all_concrete_functions_for_serialization(),  # noqa: E501
                     6,
                 )
                 with keras_save.tracing_scope():
                     fn(np.ones((2, 6)))
                 self.assertLen(
-                    fn.wrapped_call._list_all_concrete_functions_for_serialization(),
+                    fn.wrapped_call._list_all_concrete_functions_for_serialization(),  # noqa: E501
                     8,
                 )
 
diff --git a/keras/tests/automatic_outside_compilation_test.py b/keras/tests/automatic_outside_compilation_test.py
index f9a31bc7b..7c3ef1e18 100644
--- a/keras/tests/automatic_outside_compilation_test.py
+++ b/keras/tests/automatic_outside_compilation_test.py
@@ -235,7 +235,7 @@ class AutoOutsideCompilationWithKerasTest(tf.test.TestCase):
             # every 2 batches, we should see total of 5 event logs for each
             # summary.
             expected_event_counts = {
-                "sequential/layer_for_histogram_summary/custom_histogram_summary_v2": 5
+                "sequential/layer_for_histogram_summary/custom_histogram_summary_v2": 5  # noqa: E501
                 if enable_histograms
                 else 0,
                 "sequential/layer_for_image_summary/custom_image_summary_v2": 5,
diff --git a/keras/tests/model_subclassing_test.py b/keras/tests/model_subclassing_test.py
index 4af19e435..01c9892b9 100644
--- a/keras/tests/model_subclassing_test.py
+++ b/keras/tests/model_subclassing_test.py
@@ -593,7 +593,7 @@ class GraphSpecificModelSubclassingTests(tf.test.TestCase):
             def call(self, x):
                 return self.bn(self.fc(x))
 
-        with tf.compat.v1.get_default_graph().as_default(), self.cached_session():
+        with tf.compat.v1.get_default_graph().as_default(), self.cached_session():  # noqa: E501
             model = TestModel1()
 
             x = tf.ones(shape=[100, 784], dtype="float32")
@@ -615,7 +615,7 @@ class GraphSpecificModelSubclassingTests(tf.test.TestCase):
             def call(self, x):
                 return self.bn(self.fc(x))
 
-        with tf.compat.v1.get_default_graph().as_default(), self.cached_session():
+        with tf.compat.v1.get_default_graph().as_default(), self.cached_session():  # noqa: E501
             model = TestModel2()
 
             x = tf.ones(shape=[100, 784], dtype="float32")
diff --git a/keras/tests/tracking_util_with_v1_optimizers_test.py b/keras/tests/tracking_util_with_v1_optimizers_test.py
index 43b1e98ff..2eba187c7 100644
--- a/keras/tests/tracking_util_with_v1_optimizers_test.py
+++ b/keras/tests/tracking_util_with_v1_optimizers_test.py
@@ -341,7 +341,7 @@ class CheckpointingTests(test_combinations.TestCase):
                 root = tf.train.Checkpoint(
                     optimizer=optimizer,
                     model=model,
-                    optimizer_step=tf.compat.v1.train.get_or_create_global_step(),
+                    optimizer_step=tf.compat.v1.train.get_or_create_global_step(),  # noqa: E501
                 )
                 root.restore(tf.train.latest_checkpoint(checkpoint_directory))
 
@@ -377,7 +377,7 @@ class CheckpointingTests(test_combinations.TestCase):
                     root = tf.train.Checkpoint(
                         optimizer=optimizer,
                         model=model,
-                        optimizer_step=tf.compat.v1.train.get_or_create_global_step(),
+                        optimizer_step=tf.compat.v1.train.get_or_create_global_step(),  # noqa: E501
                     )
                     status = root.restore(
                         tf.train.latest_checkpoint(checkpoint_directory)
@@ -410,7 +410,7 @@ class CheckpointingTests(test_combinations.TestCase):
                     root = tf.compat.v1.train.Checkpoint(
                         optimizer=optimizer,
                         model=model,
-                        global_step=tf.compat.v1.train.get_or_create_global_step(),
+                        global_step=tf.compat.v1.train.get_or_create_global_step(),  # noqa: E501
                     )
                     input_value = tf.constant([[3.0]])
                     train_op = optimizer.minimize(
@@ -464,7 +464,7 @@ class CheckpointingTests(test_combinations.TestCase):
                     root = tf.train.Checkpoint(
                         optimizer=optimizer,
                         model=model,
-                        global_step=tf.compat.v1.train.get_or_create_global_step(),
+                        global_step=tf.compat.v1.train.get_or_create_global_step(),  # noqa: E501
                     )
                     manager = tf.train.CheckpointManager(
                         root, checkpoint_directory, max_to_keep=1
@@ -508,7 +508,7 @@ class CheckpointingTests(test_combinations.TestCase):
                     root = tf.train.Checkpoint(
                         optimizer=optimizer,
                         model=model,
-                        global_step=tf.compat.v1.train.get_or_create_global_step(),
+                        global_step=tf.compat.v1.train.get_or_create_global_step(),  # noqa: E501
                     )
                     checkpoint_path = tf.train.latest_checkpoint(
                         checkpoint_directory
diff --git a/keras/utils/audio_dataset_test.py b/keras/utils/audio_dataset_test.py
index d3e795584..e4a4f6617 100644
--- a/keras/utils/audio_dataset_test.py
+++ b/keras/utils/audio_dataset_test.py
@@ -312,7 +312,7 @@ class AudioDatasetFromDirectoryTest(test_combinations.TestCase):
         for seq_len in sequence_lengths:
             self.assertIn(seq_len, possible_sequence_lengths)
 
-    def test_audio_dataset_from_directory_no_output_sequence_length_same_lengths(
+    def test_audio_dataset_from_directory_no_output_sequence_length_same_lengths(  # noqa: E501
         self,
     ):
         # This test case tests `audio_dataset_from_directory` when `ragged` and
diff --git a/keras/utils/layer_utils_test.py b/keras/utils/layer_utils_test.py
index a87c48772..a65c2015b 100644
--- a/keras/utils/layer_utils_test.py
+++ b/keras/utils/layer_utils_test.py
@@ -127,30 +127,30 @@ class LayerUtilsTest(tf.test.TestCase):
             reader.close()
             check_str = (
                 'Model: "model_2"\n'
-                "_________________________________________________________________\n"
-                " Layer (type)                Output Shape              Param #   \n"
-                "=================================================================\n"
-                " input_3 (InputLayer)        [(None, None, None, 3)]   0         \n"
-                "                                                                 \n"
-                " model_1 (Functional)        (None, None, None, 3)     24        \n"
-                "|¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯|\n"
-                "| input_1 (InputLayer)      [(None, None, None, 3)]   0         |\n"
-                "|                                                               |\n"
-                "| model (Functional)        (None, None, None, 3)     24        |\n"
-                "||¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯||\n"
-                "|| input_2 (InputLayer)    [(None, None, None, 3)]   0         ||\n"
-                "||                                                             ||\n"
-                "|| conv2d (Conv2D)         (None, None, None, 3)     12        ||\n"
-                "||                                                             ||\n"
-                "|| batch_normalization (BatchN  (None, None, None, 3)  12      ||\n"
-                "|| ormalization)                                               ||\n"
-                "|¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯|\n"
-                "¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯\n"
-                "=================================================================\n"
+                "_________________________________________________________________\n"  # noqa: E501
+                " Layer (type)                Output Shape              Param #   \n"  # noqa: E501
+                "=================================================================\n"  # noqa: E501
+                " input_3 (InputLayer)        [(None, None, None, 3)]   0         \n"  # noqa: E501
+                "                                                                 \n"  # noqa: E501
+                " model_1 (Functional)        (None, None, None, 3)     24        \n"  # noqa: E501
+                "|¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯|\n"  # noqa: E501
+                "| input_1 (InputLayer)      [(None, None, None, 3)]   0         |\n"  # noqa: E501
+                "|                                                               |\n"  # noqa: E501
+                "| model (Functional)        (None, None, None, 3)     24        |\n"  # noqa: E501
+                "||¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯||\n"  # noqa: E501
+                "|| input_2 (InputLayer)    [(None, None, None, 3)]   0         ||\n"  # noqa: E501
+                "||                                                             ||\n"  # noqa: E501
+                "|| conv2d (Conv2D)         (None, None, None, 3)     12        ||\n"  # noqa: E501
+                "||                                                             ||\n"  # noqa: E501
+                "|| batch_normalization (BatchN  (None, None, None, 3)  12      ||\n"  # noqa: E501
+                "|| ormalization)                                               ||\n"  # noqa: E501
+                "|¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯|\n"  # noqa: E501
+                "¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯\n"  # noqa: E501
+                "=================================================================\n"  # noqa: E501
                 "Total params: 24\n"
                 "Trainable params: 18\n"
                 "Non-trainable params: 6\n"
-                "_________________________________________________________________\n"
+                "_________________________________________________________________\n"  # noqa: E501
             )
 
             fin_str = ""
@@ -269,23 +269,23 @@ class LayerUtilsTest(tf.test.TestCase):
             reader.close()
             check_str = (
                 "Model: "
-                '"trainable"\n____________________________________________________________________________\n'
-                " Layer (type)                Output Shape              Param #   "
+                '"trainable"\n____________________________________________________________________________\n'  # noqa: E501
+                " Layer (type)                Output Shape              Param #   "  # noqa: E501
                 "Trainable  "
-                "\n============================================================================\n"
-                " conv (Conv2D)               (None, 2, 3, 2)           62        N"
+                "\n============================================================================\n"  # noqa: E501
+                " conv (Conv2D)               (None, 2, 3, 2)           62        N"  # noqa: E501
                 "          \n"
-                "                                                                            "
-                "\n flat (Flatten)              (None, 12)                0         "
+                "                                                                            "  # noqa: E501
+                "\n flat (Flatten)              (None, 12)                0         "  # noqa: E501
                 "Y          \n"
-                "                                                                            "
-                "\n dense (Dense)               (None, 5)                 65        "
+                "                                                                            "  # noqa: E501
+                "\n dense (Dense)               (None, 5)                 65        "  # noqa: E501
                 "Y          \n"
-                "                                                                            "
-                "\n============================================================================\nTotal"
+                "                                                                            "  # noqa: E501
+                "\n============================================================================\nTotal"  # noqa: E501
                 " params: 127\nTrainable params: 65\nNon-trainable params: "
-                "62\n____________________________________________________________________________\n"
-                "____________________________________________________________________________\n"
+                "62\n____________________________________________________________________________\n"  # noqa: E501
+                "____________________________________________________________________________\n"  # noqa: E501
             )
 
             fin_str = ""
@@ -338,35 +338,35 @@ class LayerUtilsTest(tf.test.TestCase):
             reader.close()
             check_str = (
                 "Model: "
-                '"model_2"\n____________________________________________________________________________\n'
-                " Layer (type)                Output Shape              Param #   "
+                '"model_2"\n____________________________________________________________________________\n'  # noqa: E501
+                " Layer (type)                Output Shape              Param #   "  # noqa: E501
                 "Trainable  "
-                "\n============================================================================\n"
-                " input3 (InputLayer)         [(None, None, None, 3)]   0         Y"
+                "\n============================================================================\n"  # noqa: E501
+                " input3 (InputLayer)         [(None, None, None, 3)]   0         Y"  # noqa: E501
                 "          \n"
-                "                                                                            "
-                "\n model_1 (Functional)        (None, None, None, 3)     24        "
+                "                                                                            "  # noqa: E501
+                "\n model_1 (Functional)        (None, None, None, 3)     24        "  # noqa: E501
                 "Y          "
-                "\n|¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯|\n|"
-                " input1 (InputLayer)       [(None, None, None, 3)]   0         Y"
+                "\n|¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯|\n|"  # noqa: E501
+                " input1 (InputLayer)       [(None, None, None, 3)]   0         Y"  # noqa: E501
                 "          |\n|"
-                "                                                                          "
-                "|\n| model (Functional)        (None, None, None, 3)     24        "
+                "                                                                          "  # noqa: E501
+                "|\n| model (Functional)        (None, None, None, 3)     24        "  # noqa: E501
                 "Y          "
-                "|\n||¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯||\n||"
-                " input2 (InputLayer)     [(None, None, None, 3)]   0         Y"
+                "|\n||¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯||\n||"  # noqa: E501
+                " input2 (InputLayer)     [(None, None, None, 3)]   0         Y"  # noqa: E501
                 "          ||\n||"
-                "                                                                        "
-                "||\n|| conv2d (Conv2D)         (None, None, None, 3)     12        "
+                "                                                                        "  # noqa: E501
+                "||\n|| conv2d (Conv2D)         (None, None, None, 3)     12        "  # noqa: E501
                 "N          ||\n||"
-                "                                                                        "
-                "||\n|| batch_normalization (BatchN  (None, None, None, 3)  12      "
+                "                                                                        "  # noqa: E501
+                "||\n|| batch_normalization (BatchN  (None, None, None, 3)  12      "  # noqa: E501
                 "Y          ||\n|| ormalization)"
                 "                                                          "
-                "||\n|¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯|\n¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯\n============================================================================\nTotal"
+                "||\n|¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯|\n¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯\n============================================================================\nTotal"  # noqa: E501
                 " params: 24\nTrainable params: 6\nNon-trainable params: "
-                "18\n____________________________________________________________________________\n"
-                "____________________________________________________________________________\n"
+                "18\n____________________________________________________________________________\n"  # noqa: E501
+                "____________________________________________________________________________\n"  # noqa: E501
             )
 
             fin_str = ""
diff --git a/setup.cfg b/setup.cfg
index 20a4da27d..dc22eb0e1 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -2,4 +2,12 @@
 known_first_party = keras
 default_section = THIRDPARTY
 line_length = 80
-profile = black
\ No newline at end of file
+profile = black
+
+[flake8]
+# imported but unused in __init__.py, that's ok.
+per-file-ignores=**/__init__.py:F401
+ignore=E203,W503
+max-line-length=80
+# Only check line-too-long and ignore other errors.
+select=E501