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
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
|
#ifndef CAFFE_CUDNN_DECONV_LAYER_HPP_
#define CAFFE_CUDNN_DECONV_LAYER_HPP_
#include <vector>
#include "caffe/blob.hpp"
#include "caffe/layer.hpp"
#include "caffe/proto/caffe.pb.h"
#include "caffe/layers/deconv_layer.hpp"
namespace caffe {
#ifdef USE_CUDNN
/*
* @brief cuDNN implementation of DeConvolutionLayer.
* Fallback to DeConvolutionLayer for CPU mode.
*
* cuDNN accelerates deconvolution through forward kernels for filtering and
* bias plus backward kernels for the gradient w.r.t. the filters, biases, and
* inputs. Caffe + cuDNN further speeds up the computation through forward
* parallelism across groups and backward parallelism across gradients.
*/
template <typename Dtype>
class CuDNNDeconvolutionLayer : public DeconvolutionLayer<Dtype> {
public:
explicit CuDNNDeconvolutionLayer(const LayerParameter& param)
: DeconvolutionLayer<Dtype>(param), handles_setup_(false) {}
virtual void LayerSetUp(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top);
virtual void Reshape(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top);
virtual ~CuDNNDeconvolutionLayer();
protected:
virtual void Forward_gpu(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top);
virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,
const vector<bool>& propagate_down,
const vector<Blob<Dtype>*>& bottom);
bool handles_setup_;
cudnnHandle_t* handle_;
cudaStream_t* stream_;
// algorithms for forward and backwards convolutions
cudnnConvolutionFwdAlgo_t *fwd_algo_;
cudnnConvolutionBwdFilterAlgo_t *bwd_filter_algo_;
cudnnConvolutionBwdDataAlgo_t *bwd_data_algo_;
vector<cudnnTensorDescriptor_t> bottom_descs_, top_descs_;
cudnnTensorDescriptor_t bias_desc_;
cudnnFilterDescriptor_t filter_desc_;
vector<cudnnConvolutionDescriptor_t> conv_descs_;
int bottom_offset_, top_offset_, bias_offset_;
size_t *workspace_fwd_sizes_;
size_t *workspace_bwd_data_sizes_;
size_t *workspace_bwd_filter_sizes_;
size_t workspaceSizeInBytes; // size of underlying storage
void *workspaceData; // underlying storage
void **workspace; // aliases into workspaceData
};
#endif
} // namespace caffe
#endif // CAFFE_CUDNN_DECONV_LAYER_HPP_
|
