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.

test_activation.py 784 B

1234567891011121314151617181920212223
  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. import megengine as mge
  11. from megengine.module import LeakyReLU
  12. def test_leaky_relu():
  13. data = np.array([-8, -12, 6, 10]).astype(np.float32)
  14. negative_slope = 0.1
  15. leaky_relu = LeakyReLU(negative_slope)
  16. output = leaky_relu(mge.tensor(data))
  17. np_output = np.maximum(0, data) + negative_slope * np.minimum(0, data)
  18. np.testing.assert_equal(output.numpy(), np_output)

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