test_dataset.py 5.0 KB
Newer Older
X
xjqbest 已提交
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144
#   Copyright (c) 2018 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.

from __future__ import print_function
import paddle.fluid as fluid
import numpy as np
import os
import shutil
import unittest


class TestDataset(unittest.TestCase):
    def test_dataset_create(self):
        try:
            dataset = fluid.DatasetFactory().create_dataset("InMemoryDataset")
        except:
            self.assertTrue(False)

        try:
            dataset = fluid.DatasetFactory().create_dataset("QueueDataset")
        except:
            self.assertTrue(False)

        try:
            dataset = fluid.DatasetFactory().create_dataset("MyOwnDataset")
            self.assertTrue(False)
        except:
            self.assertTrue(True)

    def test_dataset_config(self):
        dataset = fluid.core.Dataset("MultiSlotDataset")
        dataset.set_thread_num(12)
        dataset.set_filelist(["a.txt", "b.txt", "c.txt"])
        dataset.set_trainer_num(4)
        dataset.set_hdfs_config("my_fs_name", "my_fs_ugi")

        thread_num = dataset.get_thread_num()
        self.assertEqual(thread_num, 12)

        filelist = dataset.get_filelist()
        self.assertEqual(len(filelist), 3)
        self.assertEqual(filelist[0], "a.txt")
        self.assertEqual(filelist[1], "b.txt")
        self.assertEqual(filelist[2], "c.txt")

        trainer_num = dataset.get_trainer_num()
        self.assertEqual(trainer_num, 4)

        name, ugi = dataset.get_hdfs_config()
        self.assertEqual(name, "my_fs_name")
        self.assertEqual(ugi, "my_fs_ugi")

    def test_in_memory_dataset_run(self):
        with open("test_dataset_a.txt", "w") as f:
            data = "1 1 2 3 3 4 5 5 5 5 1 1\n"
            data += "1 2 2 3 4 4 6 6 6 6 1 2\n"
            data += "1 3 2 3 5 4 7 7 7 7 1 3\n"
            f.write(data)
        with open("test_dataset_b.txt", "w") as f:
            data = "1 4 2 3 3 4 5 5 5 5 1 4\n"
            data += "1 5 2 3 4 4 6 6 6 6 1 5\n"
            data += "1 6 2 3 5 4 7 7 7 7 1 6\n"
            data += "1 7 2 3 6 4 8 8 8 8 1 7\n"
            f.write(data)

        slots = ["slot1","slot2","slot3","slot4"]
        slots_vars = []
        for slot in slots:
            var = fluid.layers.data(name=slot, shape=[1],
                                    dtype="int64", lod_level=1)
            slots_vars.append(var)

        dataset = fluid.DatasetFactory().create_dataset("InMemoryDataset")
        dataset.set_batch_size(32)
        dataset.set_thread(3)
        dataset.set_filelist(["test_dataset_a.txt", "test_dataset_b.txt"])
        dataset.set_pipe_command("cat")
        dataset.set_use_var(slots_vars)
        dataset.load_into_memory()
        dataset.local_shuffle()

        exe = fluid.Executor(fluid.CPUPlace())
        exe.run(fluid.default_startup_program())
        for i in range(2):
            try:
                exe.train_from_dataset(fluid.default_main_program(), dataset)
            except:
                self.assertTrue(False)

        os.remove("./test_dataset_a.txt")
        os.remove("./test_dataset_b.txt")

    def test_queue_dataset_run(self):
        with open("test_dataset_a.txt", "w") as f:
            data = "1 1 2 3 3 4 5 5 5 5 1 1\n"
            data += "1 2 2 3 4 4 6 6 6 6 1 2\n"
            data += "1 3 2 3 5 4 7 7 7 7 1 3\n"
            f.write(data)
        with open("test_dataset_b.txt", "w") as f:
            data = "1 4 2 3 3 4 5 5 5 5 1 4\n"
            data += "1 5 2 3 4 4 6 6 6 6 1 5\n"
            data += "1 6 2 3 5 4 7 7 7 7 1 6\n"
            data += "1 7 2 3 6 4 8 8 8 8 1 7\n"
            f.write(data)

        slots = ["slot1","slot2","slot3","slot4"]
        slots_vars = []
        for slot in slots:
            var = fluid.layers.data(name=slot, shape=[1],
                                    dtype="int64", lod_level=1)
            slots_vars.append(var)

        dataset = fluid.DatasetFactory().create_dataset("QueueDataset")
        dataset.set_batch_size(32)
        dataset.set_thread(3)
        dataset.set_filelist(["test_dataset_a.txt", "test_dataset_b.txt"])
        dataset.set_pipe_command("cat")
        dataset.set_use_var(slots_vars)

        exe = fluid.Executor(fluid.CPUPlace())
        exe.run(fluid.default_startup_program())
        for i in range(2):
            try:
                exe.train_from_dataset(fluid.default_main_program(), dataset)
            except:
                self.assertTrue(False)

        os.remove("./test_dataset_a.txt")
        os.remove("./test_dataset_b.txt")


if __name__ == '__main__':
    unittest.main()