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.

special.py 1.3 kB

12345678910111213141516171819202122232425262728293031323334353637383940
  1. # -*- coding: utf-8 -*-
  2. # MegEngine is Licensed under the Apache License, Version 2.0 (the "License")
  3. #
  4. # Copyright (c) 2014-2021 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. import numpy as np
  10. from .._imperative_rt import make_const
  11. from .._imperative_rt.core2 import SymbolVar, Tensor
  12. class Const:
  13. def __init__(self, value=None, *, dtype=None, device=None):
  14. self.value = np.asarray(value, dtype=dtype)
  15. self.dtype = dtype
  16. self.device = device
  17. def __call__(self, *reference):
  18. from ...tensor import Tensor
  19. device = self.device
  20. if len(reference) != 0:
  21. reference = reference[0]
  22. assert isinstance(
  23. reference, (SymbolVar, Tensor)
  24. ), "Reference should be Tensor or VarNode"
  25. if device is None:
  26. device = reference.device
  27. if isinstance(reference, SymbolVar):
  28. cls = type(reference)
  29. rst = cls(make_const(reference.graph, self.value, device, self.dtype))
  30. return (rst,)
  31. return (Tensor(self.value, self.dtype, self.device, True),)

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