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_loss.py 1.0 kB

123456789101112131415161718192021222324252627
  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. import numpy as np
  10. import megengine.functional as F
  11. from megengine import tensor
  12. # XXX need to test label_smooth
  13. def test_cross_entropy_with_softmax():
  14. data = tensor([1, 100]).astype(np.float32).reshape((1, 2))
  15. label = tensor([1]).astype(np.int32)
  16. loss = F.cross_entropy_with_softmax(data, label)
  17. np.testing.assert_allclose(loss.numpy(), 0.0)
  18. label = tensor([0]).astype(np.int32)
  19. loss = F.cross_entropy_with_softmax(data, label)
  20. np.testing.assert_allclose(loss.numpy(), 100 - 1)
  21. label = np.array([1])
  22. loss = F.cross_entropy_with_softmax(data, label)
  23. np.testing.assert_allclose(loss.numpy(), 0.0)

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