fix listwise model style and readme

README.md

@@ -177,7 +177,7 @@ python -m paddlerec.run -m ./models/rank/dnn/config.yaml -b backend.yaml
 |  多任务  |                  [ESMM](models/multitask/esmm/model.py)                   |      ✓      |      ✓      |       ✓       |
 |  多任务  |                  [MMOE](models/multitask/mmoe/model.py)                   |      ✓      |      ✓      |       ✓       |
 |  多任务  |           [ShareBottom](models/multitask/share-bottom/model.py)           |      ✓      |      ✓      |       ✓       |
-|  融合  |           [Listwise](models/rerank/listwise/model.py)           |      ✓      |      x      |       ✓       |
+|  重排序  |           [Listwise](models/rerank/listwise/model.py)           |      ✓      |      x      |       ✓       |
 
 
 

models/rerank/listwise/model.py

@@ -13,20 +13,28 @@
 # limitations under the License.
 
 import math
+import numpy as np
 import paddle.fluid as fluid
 
 from paddlerec.core.utils import envs
 from paddlerec.core.model import Model as ModelBase
-import numpy as np
 
 
 class Model(ModelBase):
     def __init__(self, config):
         ModelBase.__init__(self, config)
+        self.item_len = envs.get_global_env("hyper_parameters.self.item_len",
+                                            None, self._namespace)
+        self.hidden_size = envs.get_global_env("hyper_parameters.hidden_size",
+                                               None, self._namespace)
+        self.user_vocab = envs.get_global_env("hyper_parameters.user_vocab",
+                                              None, self._namespace)
+        self.item_vocab = envs.get_global_env("hyper_parameters.item_vocab",
+                                              None, self._namespace)
+        self.embed_size = envs.get_global_env("hyper_parameters.embed_size",
+                                              None, self._namespace)
 
     def input_data(self, is_infer=False):
-        item_len = envs.get_global_env("hyper_parameters.item_len", None,
-                                       self._namespace)
         user_slot_names = fluid.data(
             name='user_slot_names',
             shape=[None, 1],
@@ -34,14 +42,18 @@ class Model(ModelBase):
             lod_level=1)
         item_slot_names = fluid.data(
             name='item_slot_names',
-            shape=[None, item_len],
+            shape=[None, self.item_len],
             dtype='int64',
             lod_level=1)
         lens = fluid.data(name='lens', shape=[None], dtype='int64')
         labels = fluid.data(
-            name='labels', shape=[None, item_len], dtype='int64', lod_level=1)
+            name='labels',
+            shape=[None, self.item_len],
+            dtype='int64',
+            lod_level=1)
 
         inputs = [user_slot_names] + [item_slot_names] + [lens] + [labels]
+
         if is_infer:
             self._infer_data_var = inputs
             self._infer_data_loader = fluid.io.DataLoader.from_generator(
@@ -59,53 +71,7 @@ class Model(ModelBase):
 
         return inputs
 
-    def default_normal_initializer(self, nf=128):
-        return fluid.initializer.TruncatedNormal(
-            loc=0.0, scale=np.sqrt(1.0 / nf))
-
-    def default_regularizer(self):
-        return None
-
-    def default_fc(self, data, size, num_flatten_dims=1, act=None, name=None):
-        return fluid.layers.fc(
-            input=data,
-            size=size,
-            num_flatten_dims=num_flatten_dims,
-            param_attr=fluid.ParamAttr(
-                initializer=self.default_normal_initializer(size),
-                regularizer=self.default_regularizer()),
-            bias_attr=fluid.ParamAttr(
-                initializer=fluid.initializer.Constant(value=0.0),
-                regularizer=self.default_regularizer()),
-            act=act,
-            name=name)
-
-    def default_embedding(self, data, vocab_size, embed_size):
-        reg = fluid.regularizer.L2Decay(
-            1e-5)  # IMPORTANT, to prevent overfitting.
-        embed = fluid.embedding(
-            input=data,
-            size=[vocab_size, embed_size],
-            param_attr=fluid.ParamAttr(
-                initializer=fluid.initializer.Xavier(), regularizer=reg),
-            is_sparse=True)
-
-        return embed
-
-    def default_drnn(self, data, nf, is_reverse, h_0):
-        return fluid.layers.dynamic_gru(
-            input=data,
-            size=nf,
-            param_attr=fluid.ParamAttr(
-                initializer=self.default_normal_initializer(nf),
-                regularizer=self.default_regularizer()),
-            bias_attr=fluid.ParamAttr(
-                initializer=fluid.initializer.Constant(value=0.0),
-                regularizer=self.default_regularizer()),
-            is_reverse=is_reverse,
-            h_0=h_0)
-
-    def fluid_sequence_pad(self, input, pad_value, maxlen=None):
+    def _fluid_sequence_pad(self, input, pad_value, maxlen=None):
         """
         args:
             input: (batch*seq_len, dim)
@@ -121,7 +87,7 @@ class Model(ModelBase):
         # TODO, maxlen=300, used to solve issues: https://github.com/PaddlePaddle/Paddle/issues/14164
         return input_padded
 
-    def fluid_sequence_get_pos(self, lodtensor):
+    def _fluid_sequence_get_pos(self, lodtensor):
         """
         args:
             lodtensor: lod = [[0,4,7]]
@@ -134,7 +100,7 @@ class Model(ModelBase):
         assert lodtensor.shape == (-1, 1), (lodtensor.shape())
         ones = fluid.layers.cast(lodtensor * 0 + 1,
                                  'float32')  # (batch*seq_len, 1)
-        ones_padded = self.fluid_sequence_pad(ones,
+        ones_padded = self._fluid_sequence_pad(ones,
                                                0)  # (batch, max_seq_len, 1)
         ones_padded = fluid.layers.squeeze(ones_padded,
                                            [2])  # (batch, max_seq_len)
@@ -151,76 +117,106 @@ class Model(ModelBase):
         return pos
 
     def net(self, inputs, is_infer=False):
-        hidden_size = envs.get_global_env("hyper_parameters.hidden_size", None,
-                                          self._namespace)
-        user_vocab = envs.get_global_env("hyper_parameters.user_vocab", None,
-                                         self._namespace)
-        item_vocab = envs.get_global_env("hyper_parameters.item_vocab", None,
-                                         self._namespace)
-        embed_size = envs.get_global_env("hyper_parameters.embed_size", None,
-                                         self._namespace)
-        #encode
-        user_embedding = self.default_embedding(inputs[0], user_vocab,
-                                                embed_size)
-        user_feature = self.default_fc(
-            data=user_embedding,
-            size=hidden_size,
-            num_flatten_dims=1,
+        # user encode
+        user_embedding = fluid.embedding(
+            input=inputs[0],
+            size=[self.user_vocab, self.embed_size],
+            param_attr=fluid.ParamAttr(
+                initializer=fluid.initializer.Xavier(),
+                regularizer=fluid.regularizer.L2Decay(1e-5)),
+            is_sparse=True)
+
+        user_feature = fluid.layers.fc(
+            input=user_embedding,
+            size=self.hidden_size,
+            param_attr=fluid.ParamAttr(
+                initializer=fluid.initializer.TruncatedNormal(
+                    loc=0.0, scale=np.sqrt(1.0 / self.hidden_size))),
+            bias_attr=fluid.ParamAttr(initializer=fluid.initializer.Constant(
+                value=0.0)),
             act='relu',
             name='user_feature_fc')
+        # item encode
+        item_embedding = fluid.embedding(
+            input=inputs[1],
+            size=[self.item_vocab, self.embed_size],
+            param_attr=fluid.ParamAttr(
+                initializer=fluid.initializer.Xavier(),
+                regularizer=fluid.regularizer.L2Decay(1e-5)),
+            is_sparse=True)
 
-        item_embedding = self.default_embedding(inputs[1], item_vocab,
-                                                embed_size)
         item_embedding = fluid.layers.sequence_unpad(
             x=item_embedding, length=inputs[2])
 
-        item_fc = self.default_fc(
-            data=item_embedding,
-            size=hidden_size,
-            num_flatten_dims=1,
+        item_fc = fluid.layers.fc(
+            input=item_embedding,
+            size=self.hidden_size,
+            param_attr=fluid.ParamAttr(
+                initializer=fluid.initializer.TruncatedNormal(
+                    loc=0.0, scale=np.sqrt(1.0 / self.hidden_size))),
+            bias_attr=fluid.ParamAttr(initializer=fluid.initializer.Constant(
+                value=0.0)),
             act='relu',
             name='item_fc')
 
-        pos = self.fluid_sequence_get_pos(item_fc)
-        pos_embed = self.default_embedding(pos, user_vocab, embed_size)
+        pos = self._fluid_sequence_get_pos(item_fc)
+        pos_embed = fluid.embedding(
+            input=pos,
+            size=[self.user_vocab, self.embed_size],
+            param_attr=fluid.ParamAttr(
+                initializer=fluid.initializer.Xavier(),
+                regularizer=fluid.regularizer.L2Decay(1e-5)),
+            is_sparse=True)
+
         pos_embed = fluid.layers.squeeze(pos_embed, [1])
 
         # item gru
-        gru_input = self.default_fc(
-            data=fluid.layers.concat([item_fc, pos_embed], 1),
-            size=hidden_size * 3,
-            num_flatten_dims=1,
-            act='relu',
+        gru_input = fluid.layers.fc(
+            input=fluid.layers.concat([item_fc, pos_embed], 1),
+            size=self.hidden_size * 3,
             name='item_gru_fc')
 
-        item_gru_forward = self.default_drnn(
-            data=gru_input, nf=hidden_size, h_0=user_feature, is_reverse=False)
+        # forward gru
+        item_gru_forward = fluid.layers.dynamic_gru(
+            input=gru_input,
+            size=self.hidden_size,
+            is_reverse=False,
+            h_0=user_feature)
+        # backward gru
+        item_gru_backward = fluid.layers.dynamic_gru(
+            input=gru_input,
+            size=self.hidden_size,
+            is_reverse=True,
+            h_0=user_feature)
 
-        item_gru_backward = self.default_drnn(
-            data=gru_input, nf=hidden_size, h_0=user_feature, is_reverse=True)
         item_gru = fluid.layers.concat(
             [item_gru_forward, item_gru_backward], axis=1)
 
-        out_click_fc1 = self.default_fc(
-            data=item_gru,
-            size=hidden_size,
-            num_flatten_dims=1,
+        out_click_fc1 = fluid.layers.fc(
+            input=item_gru,
+            size=self.hidden_size,
+            param_attr=fluid.ParamAttr(
+                initializer=fluid.initializer.TruncatedNormal(
+                    loc=0.0, scale=np.sqrt(1.0 / self.hidden_size))),
+            bias_attr=fluid.ParamAttr(initializer=fluid.initializer.Constant(
+                value=0.0)),
             act='relu',
             name='out_click_fc1')
 
-        click_prob = self.default_fc(
-            data=out_click_fc1,
+        click_prob = fluid.layers.fc(input=out_click_fc1,
                                      size=2,
-            num_flatten_dims=1,
                                      act='softmax',
                                      name='out_click_fc2')
 
         labels = fluid.layers.sequence_unpad(x=inputs[3], length=inputs[2])
+
         auc_val, batch_auc, auc_states = fluid.layers.auc(input=click_prob,
                                                           label=labels)
+
         if is_infer:
             self._infer_results["AUC"] = auc_val
             return
+
         loss = fluid.layers.reduce_mean(
             fluid.layers.cross_entropy(
                 input=click_prob, label=labels))

models/rerank/listwise/random_infer_reader.py

@@ -13,11 +13,12 @@
 # limitations under the License.
 from __future__ import print_function
 
+import numpy as np
+import paddle.fluid as fluid
+
 from paddlerec.core.reader import Reader
 from paddlerec.core.utils import envs
 from collections import defaultdict
-import paddle.fluid as fluid
-import numpy as np
 
 
 class EvaluateReader(Reader):

models/rerank/listwise/random_reader.py

@@ -13,11 +13,12 @@
 # limitations under the License.
 from __future__ import print_function
 
+import numpy as np
+import paddle.fluid as fluid
+
 from paddlerec.core.reader import Reader
 from paddlerec.core.utils import envs
 from collections import defaultdict
-import paddle.fluid as fluid
-import numpy as np
 
 
 class TrainReader(Reader):

models/rerank/readme.md

-# 融合模型库
+# 重排序模型库
 
 ## 简介
-我们提供了常见的多路排序融合使用的模型算法的PaddleRec实现, 单机训练&预测效果指标以及分布式训练&预测性能指标等。目前实现的模型是 [Listwise](listwise)。
+我们提供了常见的重排序使用的模型算法的PaddleRec实现, 单机训练&预测效果指标以及分布式训练&预测性能指标等。目前实现的模型是 [Listwise](listwise)。
 
 模型算法库在持续添加中，欢迎关注。
 
 ## 目录
 * [整体介绍](#整体介绍)
-    * [融合模型列表](#融合模型列表)
+    * [重排序模型列表](#重排序模型列表)
 * [使用教程](#使用教程)
     * [训练 预测](#训练 预测)
 * [效果对比](#效果对比)