model.py 5.2 KB
Newer Older
Z
zhangwenhui03 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17
# 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 math
import paddle.fluid as fluid

18 19
from paddlerec.core.utils import envs
from paddlerec.core.model import Model as ModelBase
Z
zhangwenhui03 已提交
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138
import paddle.fluid.layers.tensor as tensor
import paddle.fluid.layers.io as io
import paddle.fluid.layers.control_flow as cf



class BowEncoder(object):
    """ bow-encoder """

    def __init__(self):
        self.param_name = ""

    def forward(self, emb):
        return fluid.layers.sequence_pool(input=emb, pool_type='sum')


class GrnnEncoder(object):
    """ grnn-encoder """

    def __init__(self, param_name="grnn", hidden_size=128):
        self.param_name = param_name
        self.hidden_size = hidden_size

    def forward(self, emb):
        fc0 = fluid.layers.fc(input=emb,
                              size=self.hidden_size * 3,
                              param_attr=self.param_name + "_fc.w",
                              bias_attr=False)

        gru_h = fluid.layers.dynamic_gru(
            input=fc0,
            size=self.hidden_size,
            is_reverse=False,
            param_attr=self.param_name + ".param",
            bias_attr=self.param_name + ".bias")
        return fluid.layers.sequence_pool(input=gru_h, pool_type='max')

class PairwiseHingeLoss(object):
    def __init__(self, margin=0.8):
        self.margin = margin

    def forward(self, pos, neg):
        loss_part1 = fluid.layers.elementwise_sub(
            tensor.fill_constant_batch_size_like(
                input=pos, shape=[-1, 1], value=self.margin, dtype='float32'),
            pos)
        loss_part2 = fluid.layers.elementwise_add(loss_part1, neg)
        loss_part3 = fluid.layers.elementwise_max(
            tensor.fill_constant_batch_size_like(
                input=loss_part2, shape=[-1, 1], value=0.0, dtype='float32'),
            loss_part2)
        return loss_part3

class Model(ModelBase):
    def __init__(self, config):
        ModelBase.__init__(self, config)

    def get_correct(self, x, y):
        less = tensor.cast(cf.less_than(x, y), dtype='float32')
        correct = fluid.layers.reduce_sum(less)
        return correct

    def train(self):
        
        vocab_size = envs.get_global_env("hyper_parameters.vocab_size", None, self._namespace)
        emb_dim = envs.get_global_env("hyper_parameters.emb_dim", None, self._namespace)
        hidden_size = envs.get_global_env("hyper_parameters.hidden_size", None, self._namespace)
        emb_shape = [vocab_size, emb_dim]

        self.user_encoder = GrnnEncoder()
        self.item_encoder = BowEncoder()
        self.pairwise_hinge_loss = PairwiseHingeLoss()

        user_data = fluid.data(
            name="user", shape=[None, 1], dtype="int64", lod_level=1)
        pos_item_data = fluid.data(
            name="p_item", shape=[None, 1], dtype="int64", lod_level=1)
        neg_item_data = fluid.data(
            name="n_item", shape=[None, 1], dtype="int64", lod_level=1)
        self._data_var.extend([user_data, pos_item_data, neg_item_data])

        user_emb = fluid.embedding(
            input=user_data, size=emb_shape, param_attr="emb.item")
        pos_item_emb = fluid.embedding(
            input=pos_item_data, size=emb_shape, param_attr="emb.item")
        neg_item_emb = fluid.embedding(
            input=neg_item_data, size=emb_shape, param_attr="emb.item")
        user_enc = self.user_encoder.forward(user_emb)
        pos_item_enc = self.item_encoder.forward(pos_item_emb)
        neg_item_enc = self.item_encoder.forward(neg_item_emb)
        user_hid = fluid.layers.fc(input=user_enc,
                                   size=hidden_size,
                                   param_attr='user.w',
                                   bias_attr="user.b")
        pos_item_hid = fluid.layers.fc(input=pos_item_enc,
                                       size=hidden_size,
                                       param_attr='item.w',
                                       bias_attr="item.b")
        neg_item_hid = fluid.layers.fc(input=neg_item_enc,
                                       size=hidden_size,
                                       param_attr='item.w',
                                       bias_attr="item.b")
        cos_pos = fluid.layers.cos_sim(user_hid, pos_item_hid)
        cos_neg = fluid.layers.cos_sim(user_hid, neg_item_hid)
        hinge_loss = self.pairwise_hinge_loss.forward(cos_pos, cos_neg)
        avg_cost = fluid.layers.mean(hinge_loss)
        correct = self.get_correct(cos_neg, cos_pos)
        
        self._cost = avg_cost
        self._metrics["correct"] = correct
        self._metrics["hinge_loss"] = hinge_loss


    def train_net(self):
        self.train()


    def infer_net(self):
        pass