Remove bare returns

official/vision/beta/projects/yolo/common/registry_imports.py

@@ -27,6 +27,3 @@ from official.vision.beta.projects.yolo.configs.darknet_classification import im
 from official.vision.beta.projects.yolo.configs.darknet_classification import ImageClassificationTask
 
 from official.vision.beta.projects.yolo.tasks.image_classification import ImageClassificationTask
-
-# task_factory.register_task_cls(ImageClassificationTask)(ImageClassificationTask)
-# print(task_factory._REGISTERED_TASK_CLS)
\ No newline at end of file

official/vision/beta/projects/yolo/modeling/backbones/Darknet.py

@@ -378,7 +378,6 @@ class Darknet(ks.Model):
         "use_sync_bn": self._use_sync_bn,
         "activation": self._activation
     }
-    #layer_config.update(super().get_config())
     return layer_config
 
 @factory.register_backbone_builder('darknet')

official/vision/beta/projects/yolo/modeling/building_blocks/_CSPConnect.py

@@ -36,7 +36,6 @@ class CSPConnect(ks.layers.Layer):
     self._use_sync_bn = use_sync_bn
     self._norm_moment = norm_momentum
     self._norm_epsilon = norm_epsilon
-    return
 
   def build(self, input_shape):
     self._conv1 = DarkConv(filters=self._filters // self._filter_reduce,
@@ -64,7 +63,6 @@ class CSPConnect(ks.layers.Layer):
                            norm_momentum=self._norm_moment,
                            norm_epsilon=self._norm_epsilon,
                            activation=self._activation)
-    return
 
   def call(self, inputs):
     x_prev, x_csp = inputs

official/vision/beta/projects/yolo/modeling/building_blocks/_CSPDownSample.py

@@ -36,7 +36,6 @@ class CSPDownSample(ks.layers.Layer):
     self._use_sync_bn = use_sync_bn
     self._norm_moment = norm_momentum
     self._norm_epsilon = norm_epsilon
-    return
 
   def build(self, input_shape):
     self._conv1 = DarkConv(filters=self._filters,
@@ -76,7 +75,6 @@ class CSPDownSample(ks.layers.Layer):
                            norm_momentum=self._norm_moment,
                            norm_epsilon=self._norm_epsilon,
                            activation=self._activation)
-    return
 
   def call(self, inputs):
     x = self._conv1(inputs)

official/vision/beta/projects/yolo/modeling/building_blocks/_CSPTiny.py

@@ -48,7 +48,6 @@ class CSPTiny(ks.layers.Layer):
     self._leaky_alpha = leaky_alpha
 
     super().__init__(**kwargs)
-    return
 
   def build(self, input_shape):
     self._convlayer1 = DarkConv(filters=self._filters,
@@ -121,7 +120,6 @@ class CSPTiny(ks.layers.Layer):
                                               data_format=None)
 
     super().build(input_shape)
-    return
 
   def call(self, inputs):
     x1 = self._convlayer1(inputs)

official/vision/beta/projects/yolo/modeling/building_blocks/_DarkConv.py

@@ -92,7 +92,6 @@ class DarkConv(ks.layers.Layer):
     self._leaky_alpha = leaky_alpha
 
     super(DarkConv, self).__init__(**kwargs)
-    return
 
   def build(self, input_shape):
     kernel_size = self._kernel_size if type(
@@ -136,7 +135,6 @@ class DarkConv(ks.layers.Layer):
       self._activation_fn = mish()
     else:
       self._activation_fn = ks.layers.Activation(activation=self._activation)
-    return
 
   def call(self, inputs):
     x = self._zeropad(inputs)

official/vision/beta/projects/yolo/modeling/building_blocks/_DarkResidual.py

@@ -71,7 +71,6 @@ class DarkResidual(ks.layers.Layer):
     self._sc_activation = sc_activation
 
     super().__init__(**kwargs)
-    return
 
   def build(self, input_shape):
     if self._downsample:
@@ -128,7 +127,6 @@ class DarkResidual(ks.layers.Layer):
     self._activation_fn = ks.layers.Activation(activation=self._sc_activation)
 
     super().build(input_shape)
-    return
 
   def call(self, inputs):
     shortcut = self._dconv(inputs)

official/vision/beta/projects/yolo/modeling/building_blocks/_DarkTiny.py

@@ -46,7 +46,6 @@ class DarkTiny(ks.layers.Layer):
     self._sc_activation = sc_activation
 
     super().__init__(**kwargs)
-    return
 
   def build(self, input_shape):
     self._maxpool = tf.keras.layers.MaxPool2D(pool_size=2,
@@ -71,7 +70,6 @@ class DarkTiny(ks.layers.Layer):
                                leaky_alpha=self._leaky_alpha)
 
     super().build(input_shape)
-    return
 
   def call(self, inputs):
     output = self._maxpool(inputs)

official/vision/beta/projects/yolo/modeling/building_blocks/_Identity.py

@@ -7,8 +7,6 @@ import tensorflow.keras as ks
 class Identity(ks.layers.Layer):
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
-        return
 
     def call(self, input):
         return input
-

official/vision/beta/projects/yolo/modeling/functions/mish_activation.py

@@ -4,7 +4,6 @@ import tensorflow.keras as ks
 class mish(ks.layers.Layer):
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
-        return
 
     def call(self, x):
         return x * tf.math.tanh(ks.activations.softplus(x))

official/vision/beta/projects/yolo/modeling/tests/test_CSPConnect.py

@@ -23,7 +23,6 @@ class CSPConnect(tf.test.TestCase, parameterized.TestCase):
         outx.shape.as_list(),
         [None, np.ceil(width // 2),
          np.ceil(height // 2), (filters)])
-    return
 
   @parameterized.named_parameters(("same", 224, 224, 64, 1),
                                   ("downsample", 224, 224, 128, 2))
@@ -49,7 +48,6 @@ class CSPConnect(tf.test.TestCase, parameterized.TestCase):
     optimizer.apply_gradients(zip(grad, test_layer.trainable_variables))
 
     self.assertNotIn(None, grad)
-    return
 
 
 if __name__ == "__main__":

official/vision/beta/projects/yolo/modeling/tests/test_CSPDownSample.py

@@ -21,7 +21,6 @@ class CSPDownSample(tf.test.TestCase, parameterized.TestCase):
         outx.shape.as_list(),
         [None, np.ceil(width // 2),
          np.ceil(height // 2), (filters / mod)])
-    return
 
   @parameterized.named_parameters(("same", 224, 224, 64, 1),
                                   ("downsample", 224, 224, 128, 2))
@@ -47,7 +46,6 @@ class CSPDownSample(tf.test.TestCase, parameterized.TestCase):
     optimizer.apply_gradients(zip(grad, test_layer.trainable_variables))
 
     self.assertNotIn(None, grad)
-    return
 
 
 if __name__ == "__main__":

official/vision/beta/projects/yolo/modeling/tests/test_DarkConv.py

@@ -31,7 +31,6 @@ class DarkConvTest(tf.test.TestCase, parameterized.TestCase):
     ]
     print(test)
     self.assertAllEqual(outx.shape.as_list(), test)
-    return
 
   @parameterized.named_parameters(("filters", 3))
   def test_gradient_pass_though(self, filters):
@@ -52,7 +51,6 @@ class DarkConvTest(tf.test.TestCase, parameterized.TestCase):
     grad = tape.gradient(grad_loss, test_layer.trainable_variables)
     optimizer.apply_gradients(zip(grad, test_layer.trainable_variables))
     self.assertNotIn(None, grad)
-    return
 
 if __name__ == "__main__":
   tf.test.main()

official/vision/beta/projects/yolo/modeling/tests/test_DarkResidual.py

@@ -24,7 +24,6 @@ class DarkResidualTest(tf.test.TestCase, parameterized.TestCase):
         outx.shape.as_list(),
         [None, np.ceil(width / mod),
          np.ceil(height / mod), filters])
-    return
 
   @parameterized.named_parameters(("same", 64, 224, 224, False),
                                   ("downsample", 32, 223, 223, True),
@@ -54,7 +53,6 @@ class DarkResidualTest(tf.test.TestCase, parameterized.TestCase):
     optimizer.apply_gradients(zip(grad, test_layer.trainable_variables))
 
     self.assertNotIn(None, grad)
-    return
 
 
 if __name__ == "__main__":

official/vision/beta/projects/yolo/modeling/tests/test_DarkTiny.py

@@ -20,7 +20,6 @@ class DarkTinyTest(tf.test.TestCase, parameterized.TestCase):
     self.assertEqual(height % strides, 0, msg="height % strides != 0")
     self.assertAllEqual(outx.shape.as_list(),
                         [None, width // strides, height // strides, filters])
-    return
 
   @parameterized.named_parameters(("middle", 224, 224, 64, 2),
                                   ("last", 224, 224, 1024, 1))
@@ -43,7 +42,6 @@ class DarkTinyTest(tf.test.TestCase, parameterized.TestCase):
     optimizer.apply_gradients(zip(grad, test_layer.trainable_variables))
 
     self.assertNotIn(None, grad)
-    return
 
 
 if __name__ == "__main__":