You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.

dropout.py 1.3 kB

123456789101112131415161718192021222324252627282930313233
  1. # -*- coding: utf-8 -*-
  2. # MegEngine is Licensed under the Apache License, Version 2.0 (the "License")
  3. #
  4. # Copyright (c) 2014-2020 Megvii Inc. All rights reserved.
  5. #
  6. # Unless required by applicable law or agreed to in writing,
  7. # software distributed under the License is distributed on an
  8. # "AS IS" BASIS, WITHOUT ARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  9. from ..functional import dropout
  10. from .module import Module
  11. class Dropout(Module):
  12. r"""Randomly sets input elements to zeros with the probability :math:`drop\_prob` during training.
  13. Commonly used in large networks to prevent overfitting.
  14. Note that we perform dropout only during training, we also rescale(multiply) the output tensor
  15. by :math:`\frac{1}{1 - drop\_prob}`. During inference :class:`~.Dropout` is equal to :class:`~.Identity`.
  16. :param drop_prob: The probability to drop (set to zero) each single element
  17. """
  18. def __init__(self, drop_prob=0.0):
  19. super().__init__()
  20. self.drop_prob = drop_prob
  21. def forward(self, inputs):
  22. if self.training:
  23. return dropout(inputs, self.drop_prob, training=True)
  24. else:
  25. return inputs
  26. def _module_info_string(self) -> str:
  27. return "drop_prob={drop_prob}".format(drop_prob=self.drop_prob)

MegEngine 安装包中集成了使用 GPU 运行代码所需的 CUDA 环境,不用区分 CPU 和 GPU 版。 如果想要运行 GPU 程序,请确保机器本身配有 GPU 硬件设备并安装好驱动。 如果你想体验在云端 GPU 算力平台进行深度学习开发的感觉,欢迎访问 MegStudio 平台