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.

util.py 1.5 kB

123456789101112131415161718192021222324252627282930313233343536
  1. # Copyright 2020 Huawei Technologies Co., Ltd
  2. #
  3. # Licensed under the Apache License, Version 2.0 (the "License");
  4. # you may not use this file except in compliance with the License.
  5. # You may obtain a copy of the License at
  6. #
  7. # http://www.apache.org/licenses/LICENSE-2.0
  8. #
  9. # Unless required by applicable law or agreed to in writing, software
  10. # distributed under the License is distributed on an "AS IS" BASIS,
  11. # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  12. # See the License for the specific language governing permissions and
  13. # limitations under the License.
  14. # ============================================================================
  15. """Util class or function."""
  16. def get_param_groups(network):
  17. """Param groups for optimizer."""
  18. decay_params = []
  19. no_decay_params = []
  20. for x in network.trainable_params():
  21. parameter_name = x.name
  22. if parameter_name.endswith('.bias'):
  23. # all bias not using weight decay
  24. no_decay_params.append(x)
  25. elif parameter_name.endswith('.gamma'):
  26. # bn weight bias not using weight decay, be carefully for now x not include BN
  27. no_decay_params.append(x)
  28. elif parameter_name.endswith('.beta'):
  29. # bn weight bias not using weight decay, be carefully for now x not include BN
  30. no_decay_params.append(x)
  31. else:
  32. decay_params.append(x)
  33. return [{'params': no_decay_params, 'weight_decay': 0.0}, {'params': decay_params}]

MindArmour关注AI的安全和隐私问题。致力于增强模型的安全可信、保护用户的数据隐私。主要包含3个模块:对抗样本鲁棒性模块、Fuzz Testing模块、隐私保护与评估模块。 对抗样本鲁棒性模块 对抗样本鲁棒性模块用于评估模型对于对抗样本的鲁棒性,并提供模型增强方法用于增强模型抗对抗样本攻击的能力,提升模型鲁棒性。对抗样本鲁棒性模块包含了4个子模块:对抗样本的生成、对抗样本的检测、模型防御、攻防评估。