tiny_dnn 1.0.0
A header only, dependency-free deep learning framework in C++11
Loading...
Searching...
No Matches
fully_connected_op_nnpack.h
1/*
2 Copyright (c) 2016, Taiga Nomi, Edgar Riba
3 All rights reserved.
4
5 Redistribution and use in source and binary forms, with or without
6 modification, are permitted provided that the following conditions are met:
7 * Redistributions of source code must retain the above copyright
8 notice, this list of conditions and the following disclaimer.
9 * Redistributions in binary form must reproduce the above copyright
10 notice, this list of conditions and the following disclaimer in the
11 documentation and/or other materials provided with the distribution.
12 * Neither the name of the <organization> nor the
13 names of its contributors may be used to endorse or promote products
14 derived from this software without specific prior written permission.
15
16 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY
17 EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
18 WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
19 DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY
20 DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
21 (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
22 LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
23 ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24 (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
25 SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26*/
27#pragma once
28
29#include "tiny_dnn/core/params/fully_params.h"
30
31namespace tiny_dnn {
32namespace kernels {
33
34inline void
35fully_connected_op_nnpack(const tensor_t& in_data,
36 const vec_t& W,
37 const vec_t& bias,
38 tensor_t& out_data,
39 const fully_params& params,
40 const bool layer_parallelize) {
41#ifdef CNN_USE_NNPACK
42 const float* kernel_ptr = W.data();
43 const float* input_ptr = in_data[0].data();
44 float* output_ptr =out_data[0].data();
45
46 // TODO: embed it into a class
47 const size_t num_mkl_threads = 1;
48 pthreadpool_t threadpool = pthreadpool_create(num_mkl_threads);
49
50 const auto status =
51 nnp_fully_connected_inference(
52 params.in_size_,
53 params.out_size_,
54 input_ptr,
55 kernel_ptr,
56 output_ptr,
57 threadpool);
58
59 if (status != nnp_status_success) {
60 throw nn_error("Could not succeed with nnp_max_pooling_output");
61 }
62
63 // TODO: embed it into a class
64 pthreadpool_destroy(threadpool);
65
66 // TODO: find a proper way to do this
67 output_ptr =out_data[0].data();
68 if (params.has_bias_) {
69 for_i(layer_parallelize, params.out_size_, [&](int i) {
70 // TODO(edgar): revise this
71 // add bias manually (since no bias param in nnp_fully_connected_inference)
72 output_ptr[i] += bias[i];
73 });
74 }
75#else
76 throw nn_error("TinyDNN has not been compiled with NNPACK support.");
77#endif
78}
79
80} // namespace kernels
81} // namespace tiny_dnn