forked from PaddlePaddle/PaddleRec
-
Notifications
You must be signed in to change notification settings - Fork 1
/
net.py
125 lines (102 loc) · 4.87 KB
/
net.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import paddle
import paddle.nn as nn
import paddle.nn.functional as F
import math
class FMLayer(nn.Layer):
def __init__(self, sparse_feature_number, sparse_feature_dim,
dense_feature_dim, sparse_num_field):
super(FMLayer, self).__init__()
self.sparse_feature_number = sparse_feature_number
self.sparse_feature_dim = sparse_feature_dim
self.dense_feature_dim = dense_feature_dim
self.sparse_num_field = sparse_num_field
self.fm = FM(sparse_feature_number, sparse_feature_dim,
dense_feature_dim, sparse_num_field)
self.bias = paddle.create_parameter(
shape=[1],
dtype='float32',
default_initializer=paddle.nn.initializer.Constant(value=0.0))
def forward(self, sparse_inputs, dense_inputs):
y_first_order, y_second_order = self.fm(sparse_inputs, dense_inputs)
predict = F.sigmoid(y_first_order + y_second_order + self.bias)
return predict
class FM(nn.Layer):
def __init__(self, sparse_feature_number, sparse_feature_dim,
dense_feature_dim, sparse_num_field):
super(FM, self).__init__()
self.sparse_feature_number = sparse_feature_number
self.sparse_feature_dim = sparse_feature_dim
self.dense_feature_dim = dense_feature_dim
self.dense_emb_dim = self.sparse_feature_dim
self.sparse_num_field = sparse_num_field
self.init_value_ = 0.1
# sparse part coding
self.embedding_one = paddle.nn.Embedding(
sparse_feature_number,
1,
sparse=True,
weight_attr=paddle.ParamAttr(
initializer=paddle.nn.initializer.TruncatedNormal(
mean=0.0,
std=self.init_value_ /
math.sqrt(float(self.sparse_feature_dim)))))
self.embedding = paddle.nn.Embedding(
self.sparse_feature_number,
self.sparse_feature_dim,
sparse=True,
weight_attr=paddle.ParamAttr(
initializer=paddle.nn.initializer.TruncatedNormal(
mean=0.0,
std=self.init_value_ /
math.sqrt(float(self.sparse_feature_dim)))))
# dense part coding
self.dense_w_one = paddle.create_parameter(
shape=[self.dense_feature_dim],
dtype='float32',
default_initializer=paddle.nn.initializer.Constant(value=1.0))
self.dense_w = paddle.create_parameter(
shape=[1, self.dense_feature_dim, self.dense_emb_dim],
dtype='float32',
default_initializer=paddle.nn.initializer.Constant(value=1.0))
def forward(self, sparse_inputs, dense_inputs):
# -------------------- first order term --------------------
sparse_inputs_concat = paddle.concat(sparse_inputs, axis=1)
sparse_emb_one = self.embedding_one(sparse_inputs_concat)
dense_emb_one = paddle.multiply(dense_inputs, self.dense_w_one)
dense_emb_one = paddle.unsqueeze(dense_emb_one, axis=2)
y_first_order = paddle.sum(sparse_emb_one, 1) + paddle.sum(
dense_emb_one, 1)
# -------------------- second order term --------------------
sparse_embeddings = self.embedding(sparse_inputs_concat)
dense_inputs_re = paddle.unsqueeze(dense_inputs, axis=2)
dense_embeddings = paddle.multiply(dense_inputs_re, self.dense_w)
feat_embeddings = paddle.concat([sparse_embeddings, dense_embeddings],
1)
# sum_square part
summed_features_emb = paddle.sum(feat_embeddings,
1) # None * embedding_size
summed_features_emb_square = paddle.square(
summed_features_emb) # None * embedding_size
# square_sum part
squared_features_emb = paddle.square(
feat_embeddings) # None * num_field * embedding_size
squared_sum_features_emb = paddle.sum(squared_features_emb,
1) # None * embedding_size
y_second_order = 0.5 * paddle.sum(
summed_features_emb_square - squared_sum_features_emb,
1,
keepdim=True) # None * 1
return y_first_order, y_second_order