Paddle/paddle/fluid/train/imdb_demo/nets.py

# Copyright (c) 2019 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 sys
import time
import numpy as np

import paddle
import paddle.fluid as fluid


def bow_net(data,
            label,
            dict_dim,
            emb_dim=128,
            hid_dim=128,
            hid_dim2=96,
            class_dim=2):
    """
    bow net
    """
    emb = fluid.layers.embedding(
        input=data, size=[dict_dim, emb_dim], is_sparse=True)
    bow = fluid.layers.sequence_pool(input=emb, pool_type='sum')
    bow_tanh = fluid.layers.tanh(bow)
    fc_1 = fluid.layers.fc(input=bow_tanh, size=hid_dim, act="tanh")
    fc_2 = fluid.layers.fc(input=fc_1, size=hid_dim2, act="tanh")
    prediction = fluid.layers.fc(input=[fc_2], size=class_dim, act="softmax")
    cost = fluid.layers.cross_entropy(input=prediction, label=label)
    avg_cost = fluid.layers.mean(x=cost)
    acc = fluid.layers.accuracy(input=prediction, label=label)

    return avg_cost, acc, prediction


def cnn_net(data,
            label,
            dict_dim,
            emb_dim=128,
            hid_dim=128,
            hid_dim2=96,
            class_dim=2,
            win_size=3):
    """
    conv net
    """
    emb = fluid.layers.embedding(
        input=data, size=[dict_dim, emb_dim], is_sparse=True)
    conv_3 = fluid.nets.sequence_conv_pool(
        input=emb,
        num_filters=hid_dim,
        filter_size=win_size,
        act="tanh",
        pool_type="max")

    fc_1 = fluid.layers.fc(input=[conv_3], size=hid_dim2)

    prediction = fluid.layers.fc(input=[fc_1], size=class_dim, act="softmax")
    cost = fluid.layers.cross_entropy(input=prediction, label=label)
    avg_cost = fluid.layers.mean(x=cost)
    acc = fluid.layers.accuracy(input=prediction, label=label)

    return avg_cost, acc, prediction


def lstm_net(data,
             label,
             dict_dim,
             emb_dim=128,
             hid_dim=128,
             hid_dim2=96,
             class_dim=2,
             emb_lr=30.0):
    """
    lstm net
    """
    emb = fluid.layers.embedding(
        input=data,
        size=[dict_dim, emb_dim],
        param_attr=fluid.ParamAttr(learning_rate=emb_lr),
        is_sparse=True)

    fc0 = fluid.layers.fc(input=emb, size=hid_dim * 4)

    lstm_h, c = fluid.layers.dynamic_lstm(
        input=fc0, size=hid_dim * 4, is_reverse=False)

    lstm_max = fluid.layers.sequence_pool(input=lstm_h, pool_type='max')
    lstm_max_tanh = fluid.layers.tanh(lstm_max)

    fc1 = fluid.layers.fc(input=lstm_max_tanh, size=hid_dim2, act='tanh')

    prediction = fluid.layers.fc(input=fc1, size=class_dim, act='softmax')

    cost = fluid.layers.cross_entropy(input=prediction, label=label)
    avg_cost = fluid.layers.mean(x=cost)
    acc = fluid.layers.accuracy(input=prediction, label=label)

    return avg_cost, acc, prediction


def gru_net(data,
            label,
            dict_dim,
            emb_dim=128,
            hid_dim=128,
            hid_dim2=96,
            class_dim=2,
            emb_lr=400.0):
    """
    gru net
    """
    emb = fluid.layers.embedding(
        input=data,
        size=[dict_dim, emb_dim],
        param_attr=fluid.ParamAttr(learning_rate=emb_lr))

    fc0 = fluid.layers.fc(input=emb, size=hid_dim * 3)
    gru_h = fluid.layers.dynamic_gru(input=fc0, size=hid_dim, is_reverse=False)
    gru_max = fluid.layers.sequence_pool(input=gru_h, pool_type='max')
    gru_max_tanh = fluid.layers.tanh(gru_max)
    fc1 = fluid.layers.fc(input=gru_max_tanh, size=hid_dim2, act='tanh')
    prediction = fluid.layers.fc(input=fc1, size=class_dim, act='softmax')

    cost = fluid.layers.cross_entropy(input=prediction, label=label)
    avg_cost = fluid.layers.mean(x=cost)
    acc = fluid.layers.accuracy(input=prediction, label=label)

    return avg_cost, acc, prediction