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.

globalavgpool.h 2.1 kB

3 years ago
12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849
  1. /**
  2. * Copyright 2019 Huawei Technologies Co., Ltd
  3. *
  4. * Licensed under the Apache License, Version 2.0 (the "License");
  5. * you may not use this file except in compliance with the License.
  6. * You may obtain a copy of the License at
  7. *
  8. * http://www.apache.org/licenses/LICENSE-2.0
  9. *
  10. * Unless required by applicable law or agreed to in writing, software
  11. * distributed under the License is distributed on an "AS IS" BASIS,
  12. * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  13. * See the License for the specific language governing permissions and
  14. * limitations under the License.
  15. */
  16. /*!
  17. * \file globalavgpool.h
  18. * \brief
  19. */
  20. #ifndef OPS_BUILT_IN_OP_PROTO_INC_GLOBALAVERAGEPOOL_H_
  21. #define OPS_BUILT_IN_OP_PROTO_INC_GLOBALAVERAGEPOOL_H_
  22. #include "graph/operator_reg.h"
  23. namespace ge {
  24. /**
  25. *@brief GlobalAveragePool consumes an input tensor X and applies average pooling across the values in the same channel.
  26. This is equivalent to AveragePool with kernel size equal to the spatial dimension of input tensor \n
  27. *@par Inputs:
  28. *@li x: Input data tensor from the previous operator; dimensions for image case are (N x C x H x W),
  29. where N is the batch size, C is the number of channels, and H and W are the height and the width of the data.
  30. For non image case, the dimensions are in the form of (N x C x D1 x D2 ... Dn), where N is the batch size.
  31. *@par Outputs:
  32. *y: Output data tensor from pooling across the input tensor. The output tensor has the same rank as the input.
  33. The first two dimensions of output shape are the same as the input (N x C), while the other dimensions are all 1
  34. *@par Restrictions:
  35. *Warning: This operator can be integrated only by configuring INSERT_OP_FILE of aclgrphBuildModel. Please do not use it directly.
  36. */
  37. REG_OP(GlobalAveragePool)
  38. .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT, DT_DOUBLE}))
  39. .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT, DT_DOUBLE}))
  40. .OP_END_FACTORY_REG(GlobalAveragePool)
  41. } // namespace ge
  42. #endif // OPS_BUILT_IN_OP_PROTO_INC_GLOBALAVGPOOL_H_

图引擎模块(GE)是MindSpore的一个子模块,其代码由C++实现,位于前端模块ME和底层硬件之间,起到承接作用。图引擎模块以ME下发的图作为输入,然后进行一系列的深度图优化操作,最后输出一张可以在底层硬件上高效运行的图。GE针对昇腾AI处理器的硬件结构特点,做了特定的优化工作,以此来充分发挥出昇腾AI处理器的强大算力。在进行模型训练/推理时,GE会被自动调用而用户并不感知。GE主要由GE API和GE Core两部分组成,详细的架构图如下所示