Use feature detection instead of version detection

Python porting best practice [___use feature detection instead of version detection___](https://docs.python.org/3/howto/pyporting.html#use-feature-detection-instead-of-version-detection).

Author: cclauss

deepctr/layers/activation.py

@@ -6,12 +6,15 @@
 
 """
 
-import sys
-
 import tensorflow as tf
 from tensorflow.python.keras.initializers import Zeros
 from tensorflow.python.keras.layers import Layer
 
+try:
+    unicode
+except NameError:
+    unicode = str
+
 
 class Dice(Layer):
     """The Data Adaptive Activation Function in DIN,which can be viewed as a generalization of PReLu and can adaptively adjust the rectified point according to distribution of input data.
@@ -61,9 +64,9 @@ def get_config(self, ):
 
 
 def activation_layer(activation):
-    if activation == "dice" or activation == "Dice":
+    if activation in ("dice", "Dice"):
         act_layer = Dice()
-    elif (isinstance(activation, str)) or (sys.version_info.major == 2 and isinstance(activation, (str, unicode))):
+    elif isinstance(activation, (str, unicode)):
         act_layer = tf.keras.layers.Activation(activation)
     elif issubclass(activation, Layer):
         act_layer = activation()