conv2dtranspose_cudnn_op.cc 2.0 KB
Newer Older
Z
zchen0211 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40
/* Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserve.

   Licensed under the Apache License, Version 2.0 (the "License");
   you may not use this file except in compliance with the License.
   You may obtain a copy of the License at

   http://www.apache.org/licenses/LICENSE-2.0

   Unless required by applicable law or agreed to in writing, software
   distributed under the License is distributed on an "AS IS" BASIS,
   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
   See the License for the specific language governing permissions and
   limitations under the License. */

#include "paddle/operators/conv2dtranspose_op.h"

namespace paddle {
namespace operators {

class CudnnConv2DTransposeOpMaker : public Conv2DTransposeOpMaker {
 public:
  CudnnConv2DTransposeOpMaker(framework::OpProto* proto,
                              framework::OpAttrChecker* op_checker)
      : Conv2DTransposeOpMaker(proto, op_checker) {
    AddAttr<std::vector<int>>("dilations", "dilations of convolution operator.")
        .SetDefault(std::vector<int>{1, 1});
    AddAttr<int>("workspace_size_MB",
                 "workspace size for cudnn, in MB, "
                 "workspace is a section of GPU memory which will be "
                 "allocated/freed each time the operator runs, larger "
                 "workspace size can increase performance but also requires "
                 "better hardward. This size should be carefully setted.")
        .SetDefault(4096);
  }
};

}  // namespace operators
}  // namespace paddle

namespace ops = paddle::operators;
Z
zchen0211 已提交
41 42
REGISTER_OP(conv2d_transpose_cudnn, ops::Conv2DTransposeOp,
            ops::CudnnConv2DTransposeOpMaker, conv2d_transpose_cudnn_grad,
Z
zchen0211 已提交
43 44 45
            ops::Conv2DTransposeOpGrad);

REGISTER_OP_CPU_KERNEL(
Z
zchen0211 已提交
46
    conv2d_transpose_cudnn,
Z
zchen0211 已提交
47 48
    ops::GemmConv2DTransposeKernel<paddle::platform::CPUPlace, float>);
REGISTER_OP_CPU_KERNEL(
Z
zchen0211 已提交
49
    conv2d_transpose_cudnn_grad,
Z
zchen0211 已提交
50
    ops::GemmConv2DTransposeGradKernel<paddle::platform::CPUPlace, float>);