no message

deepmatch/layers/__init__.py

@@ -1,16 +1,15 @@
 from deepctr.layers import custom_objects
 from deepctr.layers.utils import reduce_sum
 
-from .core import PoolingLayer, SampledSoftmaxLayer, Similarity, LabelAwareAttention, CapsuleLayer,SampledSoftmaxLayerv2,EmbeddingIndex
+from .core import PoolingLayer, Similarity, LabelAwareAttention, CapsuleLayer,SampledSoftmaxLayer,EmbeddingIndex
 from ..utils import sampledsoftmaxloss
 
 _custom_objects = {'PoolingLayer': PoolingLayer,
-                   'SampledSoftmaxLayer': SampledSoftmaxLayer,
                    'Similarity': Similarity,
                    'LabelAwareAttention': LabelAwareAttention,
                    'CapsuleLayer': CapsuleLayer,
                    'reduce_sum':reduce_sum,
-                   'SampledSoftmaxLayerv2':SampledSoftmaxLayerv2,
+                   'SampledSoftmaxLayer':SampledSoftmaxLayer,
                    'sampledsoftmaxloss':sampledsoftmaxloss,
                    'EmbeddingIndex':EmbeddingIndex
                    }

deepmatch/layers/core.py

@@ -44,55 +44,11 @@ def get_config(self, ):
 
 
 class SampledSoftmaxLayer(Layer):
-    def __init__(self, item_embedding, num_sampled=5, **kwargs):
-        self.num_sampled = num_sampled
-        self.target_song_size = item_embedding.input_dim
-        self.item_embedding = item_embedding
-        super(SampledSoftmaxLayer, self).__init__(**kwargs)
-
-    def build(self, input_shape):
-        self.zero_bias = self.add_weight(shape=[self.target_song_size],
-                                         initializer=Zeros,
-                                         dtype=tf.float32,
-                                         trainable=False,
-                                         name="bias")
-        if not self.item_embedding.built:
-            self.item_embedding.build([])
-        self.trainable_weights.append(self.item_embedding.embeddings)
-        super(SampledSoftmaxLayer, self).build(input_shape)
-
-    def call(self, inputs_with_label_idx, training=None, **kwargs):
-        """
-        The first input should be the model as it were, and the second the
-        target (i.e., a repeat of the training data) to compute the labels
-        argument
-        """
-        inputs, label_idx = inputs_with_label_idx
-
-        loss = tf.nn.sampled_softmax_loss(weights=self.item_embedding.embeddings,
-                                          biases=self.zero_bias,
-                                          labels=label_idx,
-                                          inputs=inputs,
-                                          num_sampled=self.num_sampled,
-                                          num_classes=self.target_song_size
-                                          )
-        return tf.expand_dims(loss, axis=1)
-
-    def compute_output_shape(self, input_shape):
-        return (None, 1)
-
-    def get_config(self, ):
-        config = {'item_embedding': self.item_embedding, 'num_sampled': self.num_sampled}
-        base_config = super(SampledSoftmaxLayer, self).get_config()
-        return dict(list(base_config.items()) + list(config.items()))
-
-
-class SampledSoftmaxLayerv2(Layer):
     def __init__(self, num_sampled=5, **kwargs):
         self.num_sampled = num_sampled
         # self.target_song_size = item_embedding.input_dim
         # self.item_embedding = item_embedding
-        super(SampledSoftmaxLayerv2, self).__init__(**kwargs)
+        super(SampledSoftmaxLayer, self).__init__(**kwargs)
 
     def build(self, input_shape):
         self.size = input_shape[0][0]
@@ -104,7 +60,7 @@ def build(self, input_shape):
         # if not self.item_embedding.built:
         #     self.item_embedding.build([])
         # self.trainable_weights.append(self.item_embedding.embeddings)
-        super(SampledSoftmaxLayerv2, self).build(input_shape)
+        super(SampledSoftmaxLayer, self).build(input_shape)
 
     def call(self, inputs_with_label_idx, training=None, **kwargs):
         """
@@ -128,7 +84,7 @@ def compute_output_shape(self, input_shape):
 
     def get_config(self, ):
         config = {'num_sampled': self.num_sampled}
-        base_config = super(SampledSoftmaxLayerv2, self).get_config()
+        base_config = super(SampledSoftmaxLayer, self).get_config()
         return dict(list(base_config.items()) + list(config.items()))
 
 

deepmatch/models/dssm.py

@@ -13,8 +13,8 @@
 from ..layers.core import Similarity
 
 
-def DSSM(user_feature_columns, item_feature_columns, user_dnn_hidden_units=(64, 16),
-         item_dnn_hidden_units=(64, 16),
+def DSSM(user_feature_columns, item_feature_columns, user_dnn_hidden_units=(64, 32),
+         item_dnn_hidden_units=(64, 32),
          dnn_activation='tanh', dnn_use_bn=False,
          l2_reg_dnn=0, l2_reg_embedding=1e-6, dnn_dropout=0, init_std=0.0001, seed=1024, metric='cos'):
     """Instantiates the Deep Structured Semantic Model architecture.

deepmatch/models/mind.py

@@ -12,12 +12,12 @@
     combined_dnn_input
 from deepctr.layers.core import DNN
 from deepctr.layers.utils import NoMask
-from tensorflow.python.keras.layers import Concatenate,Input,Lambda
+from tensorflow.python.keras.layers import Concatenate
 from tensorflow.python.keras.models import Model
 
-from deepmatch.utils import get_item_embedding,get_item_embeddingv2
+from deepmatch.utils import get_item_embedding
 from ..inputs import create_embedding_matrix
-from ..layers.core import CapsuleLayer, SampledSoftmaxLayer, PoolingLayer, LabelAwareAttention,SampledSoftmaxLayerv2,EmbeddingIndex
+from ..layers.core import CapsuleLayer, PoolingLayer, LabelAwareAttention,SampledSoftmaxLayer,EmbeddingIndex
 
 
 def shape_target(target_emb_tmp, target_emb_size):
@@ -143,14 +143,14 @@ def MIND(user_feature_columns, item_feature_columns, num_sampled=5, k_max=2, p=1
     else:
         user_embedding_final = LabelAwareAttention(k_max=k_max, pow_p=p, )((user_embeddings, target_emb))
 
-    output = SampledSoftmaxLayerv2( num_sampled=num_sampled)(
+    output = SampledSoftmaxLayer(num_sampled=num_sampled)(
         inputs=(pooling_item_embedding_weight,user_embedding_final, item_features[item_feature_name]))
     model = Model(inputs=inputs_list + item_inputs_list, outputs=output)
 
     model.__setattr__("user_input", inputs_list)
     model.__setattr__("user_embedding", user_embeddings)
 
     model.__setattr__("item_input", item_inputs_list)
-    model.__setattr__("item_embedding", get_item_embeddingv2(pooling_item_embedding_weight, item_features[item_feature_name]))
+    model.__setattr__("item_embedding", get_item_embedding(pooling_item_embedding_weight, item_features[item_feature_name]))
 
     return model

deepmatch/models/ncf.py

@@ -16,7 +16,7 @@
 
 def NCF(user_feature_columns, item_feature_columns, user_gmf_embedding_dim=20, item_gmf_embedding_dim=20,
         user_mlp_embedding_dim=20, item_mlp_embedding_dim=20, dnn_use_bn=False,
-        dnn_hidden_units=(64, 16), dnn_activation='relu', l2_reg_dnn=0, l2_reg_embedding=1e-6, dnn_dropout=0,
+        dnn_hidden_units=(64, 32), dnn_activation='relu', l2_reg_dnn=0, l2_reg_embedding=1e-6, dnn_dropout=0,
         init_std=0.0001, seed=1024):
     """Instantiates the NCF Model architecture.
 

deepmatch/models/youtubednn.py

@@ -9,14 +9,14 @@
 from deepctr.layers.utils import NoMask
 from tensorflow.python.keras.models import Model
 
-from deepmatch.utils import get_item_embedding, get_item_embeddingv2
+from deepmatch.utils import get_item_embedding
 from deepmatch.layers import PoolingLayer
 from ..inputs import input_from_feature_columns
-from ..layers.core import SampledSoftmaxLayer, SampledSoftmaxLayerv2,EmbeddingIndex
+from ..layers.core import  SampledSoftmaxLayer,EmbeddingIndex
 
 
 def YoutubeDNN(user_feature_columns, item_feature_columns, num_sampled=5,
-               user_dnn_hidden_units=(64, 16),
+               user_dnn_hidden_units=(64, 32),
                dnn_activation='relu', dnn_use_bn=False,
                l2_reg_dnn=0, l2_reg_embedding=1e-6, dnn_dropout=0, init_std=0.0001, seed=1024, ):
     """Instantiates the YoutubeDNN Model architecture.
@@ -66,14 +66,14 @@ def YoutubeDNN(user_feature_columns, item_feature_columns, num_sampled=5,
 
     pooling_item_embedding_weight = PoolingLayer()([item_embedding_weight])
 
-    output = SampledSoftmaxLayerv2(num_sampled=num_sampled)(
+    output = SampledSoftmaxLayer(num_sampled=num_sampled)(
         inputs=(pooling_item_embedding_weight, user_dnn_out, item_features[item_feature_name]))
     model = Model(inputs=user_inputs_list + item_inputs_list , outputs=output)
 
     model.__setattr__("user_input", user_inputs_list)
     model.__setattr__("user_embedding", user_dnn_out)
 
     model.__setattr__("item_input", item_inputs_list)
-    model.__setattr__("item_embedding", get_item_embeddingv2(pooling_item_embedding_weight, item_features[item_feature_name]))
+    model.__setattr__("item_embedding", get_item_embedding(pooling_item_embedding_weight, item_features[item_feature_name]))
 
     return model

deepmatch/utils.py

@@ -29,12 +29,7 @@ def recall_N(y_true, y_pred, N=50):
 def sampledsoftmaxloss(y_true, y_pred):
     return K.mean(y_pred)
 
-
-def get_item_embedding(item_embedding_layer, item_input_layer):
-    return Lambda(lambda x: tf.squeeze(tf.gather(item_embedding_layer.embeddings, x), axis=1))(
-        item_input_layer)
-
-def get_item_embeddingv2(item_embedding, item_input_layer):
+def get_item_embedding(item_embedding, item_input_layer):
     return Lambda(lambda x: tf.squeeze(tf.gather(item_embedding, x), axis=1))(
         item_input_layer)
 

docs/source/History.md

@@ -1,3 +1,3 @@
 # History
-- 04/10/2020 : DeepMatch first version  is released on [PyPi](https://pypi.org/project/deepmatch/)
+- 04/10/2020 : [v0.1.2](https://github.com/shenweichen/DeepMatch/releases/tag/v0.1.2) released.Support [saving and loading model](./FAQ.html#save-or-load-weights-models). 
 - 04/06/2020 : DeepMatch first version  is released on [PyPi](https://pypi.org/project/deepmatch/)

docs/source/index.rst

@@ -18,6 +18,8 @@ You can read the latest code at https://github.com/shenweichen/DeepMatch
 News
 -----
 
+04/10/2020 : Support `saving and loading model <./FAQ.html#save-or-load-weights-models>`_  . `Changelog <https://github.com/shenweichen/DeepMatch/releases/tag/v0.1.2>`_
+
 04/06/2020 : DeepMatch first version .
 
 DisscussionGroup

examples/run_dssm_negsampling.py

@@ -38,7 +38,7 @@
 
     # 2.count #unique features for each sparse field and generate feature config for sequence feature
 
-    embedding_dim = 16
+    embedding_dim = 8
 
     user_feature_columns = [SparseFeat('user_id', feature_max_idx['user_id'], embedding_dim),
                             SparseFeat("gender", feature_max_idx['gender'], embedding_dim),