improve compatibility

improve compatibility with tensorflow 2.x

.github/workflows/ci.yml

@@ -17,28 +17,45 @@ jobs:
     timeout-minutes: 180
     strategy:
       matrix:
-        python-version: [3.6,3.7]
-        tf-version: [1.4.0,1.15.0,2.2.0,2.5.0]
+        python-version: [3.6,3.7,3.8]
+        tf-version: [1.4.0,1.15.0,2.5.0,2.6.0,2.7.0,2.8.0,2.9.0]
 
         exclude:
           - python-version: 3.7
             tf-version: 1.4.0
           - python-version: 3.7
             tf-version: 1.15.0
-
+          - python-version: 3.8
+            tf-version: 1.4.0
+          - python-version: 3.8
+            tf-version: 1.14.0
+          - python-version: 3.8
+            tf-version: 1.15.0
+          - python-version: 3.6
+            tf-version: 2.7.0
+          - python-version: 3.6
+            tf-version: 2.8.0
+          - python-version: 3.6
+            tf-version: 2.9.0
+          - python-version: 3.9
+            tf-version: 1.4.0
+          - python-version: 3.9
+            tf-version: 1.15.0
+          - python-version: 3.9
+            tf-version: 2.2.0
     steps:
 
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v3
 
     - name: Setup python environment
-      uses: actions/setup-python@v2.2.2
+      uses: actions/setup-python@v4
       with:
         python-version: ${{ matrix.python-version }}
 
     - name: Install dependencies
       run: |
         pip3 install -q tensorflow==${{ matrix.tf-version }}
-        pip install -q numpy==1.19.5
+        pip install -q protobuf==3.19.0
         pip install -q requests
         pip install -e .
     - name: Test with pytest
@@ -49,7 +66,7 @@ jobs:
         pip install -q python-coveralls
         pytest --cov=deepctr --cov-report=xml
     - name: Upload coverage to Codecov  
-      uses: codecov/codecov-action@v2.0.3
+      uses: codecov/codecov-action@v3.1.0
       with:
         token: ${{secrets.CODECOV_TOKEN}}
         file: ./coverage.xml

README.md

@@ -89,11 +89,12 @@ If you find this code useful in your research, please cite it using the followin
 
 ## DisscussionGroup
 
-- [Discussions](https://github.com/shenweichen/DeepCTR/discussions)
-- 公众号：**浅梦学习笔记**
-- wechat ID: **deepctrbot**
+- [Github Discussions](https://github.com/shenweichen/DeepCTR/discussions)
+- Wechat Discussions
 
-  ![wechat](./docs/pics/code.png)
+|公众号：浅梦学习笔记|微信：deepctrbot|学习小组 [加入](https://t.zsxq.com/026UJEuzv) [主题集合](https://mp.weixin.qq.com/mp/appmsgalbum?__biz=MjM5MzY4NzE3MA==&action=getalbum&album_id=1361647041096843265&scene=126#wechat_redirect)|
+|:--:|:--:|:--:|
+| [![公众号](./docs/pics/code.png)](https://github.com/shenweichen/AlgoNotes)| [![微信](./docs/pics/deepctrbot.png)](https://github.com/shenweichen/AlgoNotes)|[![学习小组](./docs/pics/planet_github.png)](https://t.zsxq.com/026UJEuzv)|
 
 ## Main contributors([welcome to join us!](./CONTRIBUTING.md))
 
@@ -119,12 +120,12 @@ If you find this code useful in your research, please cite it using the followin
       <td>
         ​ <a href="https://github.com/morningsky"><img width="70" height="70" src="https://github.com/morningsky.png?s=40" alt="pic"></a><br>
         ​ <a href="https://github.com/morningsky">Lai Mincai</a>
-        <p> ShanghaiTech University </p>​
+        <p> ByteDance </p>​
       </td>
       <td>
         ​ <a href="https://github.com/codewithzichao"><img width="70" height="70" src="https://github.com/codewithzichao.png?s=40" alt="pic"></a><br>
         ​ <a href="https://github.com/codewithzichao">Li Zichao</a>
-        <p> Peking University   </p>​
+        <p> ByteDance   </p>​
       </td>
       <td>
         ​ <a href="https://github.com/TanTingyi"><img width="70" height="70" src="https://github.com/TanTingyi.png?s=40" alt="pic"></a><br>

deepctr/__init__.py

@@ -1,4 +1,4 @@
 from .utils import check_version
 
-__version__ = '0.9.0'
+__version__ = '0.9.1'
 check_version(__version__)

deepctr/layers/__init__.py

@@ -11,7 +11,7 @@
                        KMaxPooling, SequencePoolingLayer, WeightedSequenceLayer,
                        Transformer, DynamicGRU,PositionEncoding)
 
-from .utils import NoMask, Hash, Linear, Add, combined_dnn_input, softmax, reduce_sum
+from .utils import NoMask, Hash, Linear, _Add, combined_dnn_input, softmax, reduce_sum
 
 custom_objects = {'tf': tf,
                   'InnerProductLayer': InnerProductLayer,
@@ -42,7 +42,7 @@
                   'SENETLayer': SENETLayer,
                   'BilinearInteraction': BilinearInteraction,
                   'WeightedSequenceLayer': WeightedSequenceLayer,
-                  'Add': Add,
+                  '_Add': _Add,
                   'FieldWiseBiInteraction': FieldWiseBiInteraction,
                   'FwFMLayer': FwFMLayer,
                   'softmax': softmax,

deepctr/layers/activation.py

@@ -7,8 +7,17 @@
 """
 
 import tensorflow as tf
-from tensorflow.python.keras.initializers import Zeros
-from tensorflow.python.keras.layers import Layer
+
+try:
+    from tensorflow.python.ops.init_ops import Zeros
+except ImportError:
+    from tensorflow.python.ops.init_ops_v2 import Zeros
+from tensorflow.python.keras.layers import Layer, Activation
+
+try:
+    from tensorflow.python.keras.layers import BatchNormalization
+except ImportError:
+    BatchNormalization = tf.keras.layers.BatchNormalization
 
 try:
     unicode
@@ -40,7 +49,7 @@ def __init__(self, axis=-1, epsilon=1e-9, **kwargs):
         super(Dice, self).__init__(**kwargs)
 
     def build(self, input_shape):
-        self.bn = tf.keras.layers.BatchNormalization(
+        self.bn = BatchNormalization(
             axis=self.axis, epsilon=self.epsilon, center=False, scale=False)
         self.alphas = self.add_weight(shape=(input_shape[-1],), initializer=Zeros(
         ), dtype=tf.float32, name='dice_alpha')  # name='alpha_'+self.name
@@ -67,7 +76,7 @@ def activation_layer(activation):
     if activation in ("dice", "Dice"):
         act_layer = Dice()
     elif isinstance(activation, (str, unicode)):
-        act_layer = tf.keras.layers.Activation(activation)
+        act_layer = Activation(activation)
     elif issubclass(activation, Layer):
         act_layer = activation()
     else:

deepctr/layers/core.py

@@ -8,8 +8,18 @@
 
 import tensorflow as tf
 from tensorflow.python.keras import backend as K
-from tensorflow.python.keras.initializers import Zeros, glorot_normal
-from tensorflow.python.keras.layers import Layer
+
+try:
+    from tensorflow.python.ops.init_ops_v2 import Zeros, glorot_normal
+except ImportError:
+    from tensorflow.python.ops.init_ops import Zeros, glorot_normal_initializer as glorot_normal
+
+from tensorflow.python.keras.layers import Layer, Dropout
+
+try:
+    from tensorflow.python.keras.layers import BatchNormalization
+except ImportError:
+    BatchNormalization = tf.keras.layers.BatchNormalization
 from tensorflow.python.keras.regularizers import l2
 
 from .activation import activation_layer
@@ -68,8 +78,8 @@ def build(self, input_shape):
                              'inputs of a two inputs with shape (None,1,embedding_size) and (None,T,embedding_size)'
                              'Got different shapes: %s,%s' % (input_shape[0], input_shape[1]))
         size = 4 * \
-            int(input_shape[0][-1]
-                ) if len(self.hidden_units) == 0 else self.hidden_units[-1]
+               int(input_shape[0][-1]
+                   ) if len(self.hidden_units) == 0 else self.hidden_units[-1]
         self.kernel = self.add_weight(shape=(size, 1),
                                       initializer=glorot_normal(
                                           seed=self.seed),
@@ -164,9 +174,9 @@ def build(self, input_shape):
                                      initializer=Zeros(),
                                      trainable=True) for i in range(len(self.hidden_units))]
         if self.use_bn:
-            self.bn_layers = [tf.keras.layers.BatchNormalization() for _ in range(len(self.hidden_units))]
+            self.bn_layers = [BatchNormalization() for _ in range(len(self.hidden_units))]
 
-        self.dropout_layers = [tf.keras.layers.Dropout(self.dropout_rate, seed=self.seed + i) for i in
+        self.dropout_layers = [Dropout(self.dropout_rate, seed=self.seed + i) for i in
                                range(len(self.hidden_units))]
 
         self.activation_layers = [activation_layer(self.activation) for _ in range(len(self.hidden_units))]

deepctr/layers/interaction.py

@@ -12,9 +12,15 @@
 import tensorflow as tf
 from tensorflow.python.keras import backend as K
 from tensorflow.python.keras.backend import batch_dot
-from tensorflow.python.keras.initializers import (Zeros, glorot_normal,
-                                                  glorot_uniform, TruncatedNormal)
-from tensorflow.python.keras.layers import Layer
+
+try:
+    from tensorflow.python.ops.init_ops import Zeros, Ones, Constant, TruncatedNormal, \
+        glorot_normal_initializer as glorot_normal, \
+        glorot_uniform_initializer as glorot_uniform
+except ImportError:
+    from tensorflow.python.ops.init_ops_v2 import Zeros, Ones, Constant, TruncatedNormal, glorot_normal, glorot_uniform
+
+from tensorflow.python.keras.layers import Layer, MaxPooling2D, Conv2D, Dropout, Lambda, Dense, Flatten
 from tensorflow.python.keras.regularizers import l2
 from tensorflow.python.layers import utils
 
@@ -90,10 +96,10 @@ def build(self, input_shape):
                                             initializer=glorot_normal(seed=self.seed), name="projection_h")
         self.projection_p = self.add_weight(shape=(
             embedding_size, 1), initializer=glorot_normal(seed=self.seed), name="projection_p")
-        self.dropout = tf.keras.layers.Dropout(
+        self.dropout = Dropout(
             self.dropout_rate, seed=self.seed)
 
-        self.tensordot = tf.keras.layers.Lambda(
+        self.tensordot = Lambda(
             lambda x: tf.tensordot(x[0], x[1], axes=(-1, 0)))
 
         # Be sure to call this somewhere!
@@ -244,7 +250,7 @@ def build(self, input_shape):
                                                 regularizer=l2(self.l2_reg)))
 
             self.bias.append(self.add_weight(name='bias' + str(i), shape=[size], dtype=tf.float32,
-                                             initializer=tf.keras.initializers.Zeros()))
+                                             initializer=Zeros()))
 
             if self.split_half:
                 if i != len(self.layer_size) - 1 and size % 2 > 0:
@@ -485,7 +491,7 @@ def build(self, input_shape):
                                        regularizer=l2(self.l2_reg),
                                        trainable=True) for i in range(self.layer_num)]
 
-        self.gating = [tf.keras.layers.Dense(1, use_bias=False) for i in range(self.num_experts)]
+        self.gating = [Dense(1, use_bias=False) for i in range(self.num_experts)]
 
         self.bias = [self.add_weight(name='bias' + str(i),
                                      shape=(dim, 1),
@@ -717,17 +723,17 @@ def build(self, input_shape):
         embedding_size = int(input_shape[-1])
         self.W_Query = self.add_weight(name='query', shape=[embedding_size, self.att_embedding_size * self.head_num],
                                        dtype=tf.float32,
-                                       initializer=tf.keras.initializers.TruncatedNormal(seed=self.seed))
+                                       initializer=TruncatedNormal(seed=self.seed))
         self.W_key = self.add_weight(name='key', shape=[embedding_size, self.att_embedding_size * self.head_num],
                                      dtype=tf.float32,
-                                     initializer=tf.keras.initializers.TruncatedNormal(seed=self.seed + 1))
+                                     initializer=TruncatedNormal(seed=self.seed + 1))
         self.W_Value = self.add_weight(name='value', shape=[embedding_size, self.att_embedding_size * self.head_num],
                                        dtype=tf.float32,
-                                       initializer=tf.keras.initializers.TruncatedNormal(seed=self.seed + 2))
+                                       initializer=TruncatedNormal(seed=self.seed + 2))
         if self.use_res:
             self.W_Res = self.add_weight(name='res', shape=[embedding_size, self.att_embedding_size * self.head_num],
                                          dtype=tf.float32,
-                                         initializer=tf.keras.initializers.TruncatedNormal(seed=self.seed))
+                                         initializer=TruncatedNormal(seed=self.seed))
 
         # Be sure to call this somewhere!
         super(InteractingLayer, self).build(input_shape)
@@ -964,15 +970,15 @@ def build(self, input_shape):
                 pooling_shape, (width, 1))
             pooling_shape = self._pooling_output_shape(
                 conv_output_shape, (pooling_width, 1))
-            self.conv_layers.append(tf.keras.layers.Conv2D(filters=filters, kernel_size=(width, 1), strides=(1, 1),
-                                                           padding='same',
-                                                           activation='tanh', use_bias=True, ))
+            self.conv_layers.append(Conv2D(filters=filters, kernel_size=(width, 1), strides=(1, 1),
+                                           padding='same',
+                                           activation='tanh', use_bias=True, ))
             self.pooling_layers.append(
-                tf.keras.layers.MaxPooling2D(pool_size=(pooling_width, 1)))
-            self.dense_layers.append(tf.keras.layers.Dense(pooling_shape[1] * embedding_size * new_filters,
-                                                           activation='tanh', use_bias=True))
+                MaxPooling2D(pool_size=(pooling_width, 1)))
+            self.dense_layers.append(Dense(pooling_shape[1] * embedding_size * new_filters,
+                                           activation='tanh', use_bias=True))
 
-        self.flatten = tf.keras.layers.Flatten()
+        self.flatten = Flatten()
 
         super(FGCNNLayer, self).build(
             input_shape)  # Be sure to call this somewhere!
@@ -1090,7 +1096,7 @@ def build(self, input_shape):
         self.W_2 = self.add_weight(shape=(
             reduction_size, self.filed_size), initializer=glorot_normal(seed=self.seed), name="W_2")
 
-        self.tensordot = tf.keras.layers.Lambda(
+        self.tensordot = Lambda(
             lambda x: tf.tensordot(x[0], x[1], axes=(-1, 0)))
 
         # Be sure to call this somewhere!
@@ -1245,14 +1251,14 @@ def build(self, input_shape):
         self.kernel_mf = self.add_weight(
             name='kernel_mf',
             shape=(int(self.num_fields * (self.num_fields - 1) / 2), 1),
-            initializer=tf.keras.initializers.Ones(),
+            initializer=Ones(),
             regularizer=None,
             trainable=True)
 
         self.kernel_fm = self.add_weight(
             name='kernel_fm',
             shape=(self.num_fields, 1),
-            initializer=tf.keras.initializers.Constant(value=0.5),
+            initializer=Constant(value=0.5),
             regularizer=None,
             trainable=True)
         if self.use_bias:

deepctr/layers/normalization.py

@@ -7,9 +7,13 @@
 """
 
 from tensorflow.python.keras import backend as K
-from tensorflow.python.keras.initializers import Ones, Zeros
 from tensorflow.python.keras.layers import Layer
 
+try:
+    from tensorflow.python.ops.init_ops import Zeros, Ones
+except ImportError:
+    from tensorflow.python.ops.init_ops_v2 import Zeros, Ones
+
 
 class LayerNormalization(Layer):
     def __init__(self, axis=-1, eps=1e-9, center=True,