[ti-machine-learning/ti-machine-learning.git] / debian / ti-timl / usr / src / timl / src / common / cnn / timlCNNInputForwardPropagation.c
1 /******************************************************************************/\r
2 /*!\r
3 * \file timlCNNForwardPropagation.c\r
4 */\r
5 /* Copyright (C) 2015 Texas Instruments Incorporated - http://www.ti.com/\r
6 *\r
7 * Redistribution and use in source and binary forms, with or without\r
8 * modification, are permitted provided that the following conditions\r
9 * are met:\r
10 *\r
11 * Redistributions of source code must retain the above copyright\r
12 * notice, this list of conditions and the following disclaimer.\r
13 *\r
14 * Redistributions in binary form must reproduce the above copyright\r
15 * notice, this list of conditions and the following disclaimer in the\r
16 * documentation and/or other materials provided with the\r
17 * distribution.\r
18 *\r
19 * Neither the name of Texas Instruments Incorporated nor the names of\r
20 * its contributors may be used to endorse or promote products derived\r
21 * from this software without specific prior written permission.\r
22 *\r
23 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS\r
24 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT\r
25 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR\r
26 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT\r
27 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,\r
28 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT\r
29 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,\r
30 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY\r
31 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT\r
32 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE\r
33 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.\r
34 *\r
35 ******************************************************************************/\r
36 \r
37 \r
38 /*******************************************************************************\r
39 *\r
40 * INCLUDES\r
41 *\r
42 ******************************************************************************/\r
43 \r
44 #include "../api/timl.h"\r
45 \r
46 \r
47 /******************************************************************************/\r
48 /*!\r
49 * \ingroup cnn\r
50 * \brief Forward propagate data to the the input layer\r
51 * \param[in] layer Layer ptr\r
52 * \param[in] data Data ptr\r
53 * \param[in] dim Data dimension\r
54 * \return Error code\r
55 */\r
56 /******************************************************************************/\r
57 \r
58 int timlCNNInputForwardPropagation(timlCNNLayer *layer, float *data, int dim)\r
59 {\r
60 \r
61 int rowOffset;\r
62 int colOffset;\r
63 int deviceId;\r
64 int threadId;\r
65 \r
66 // pass through, assuming feature map has already been loaded\r
67 if (data == NULL) {\r
68 return 0;\r
69 }\r
70 \r
71 deviceId = layer->cnn->deviceId;\r
72 threadId = layer->cnn->threadId;\r
73 \r
74 // testing mode\r
75 if (layer->phase == Util_Test) {\r
76 if (layer->inputParams.testingCropType == Util_CenterCrop) {\r
77 rowOffset = (layer->inputParams.row - layer->row)/2;\r
78 colOffset = (layer->inputParams.col - layer->col)/2;\r
79 }\r
80 else { // randomCrop\r
81 rowOffset = timlUtilRandDiscreteUniformRNG(0, layer->inputParams.row - layer->row);\r
82 colOffset = timlUtilRandDiscreteUniformRNG(0, layer->inputParams.col - layer->col);\r
83 }\r
84 timlUtilTransform(layer->featureMap, layer->inputParams.inputData, data, layer->channel, layer->row, layer->col, rowOffset, colOffset, layer->inputParams.row, layer->inputParams.col, layer->inputParams.scale, layer->inputParams.mean, layer->inputParams.testingMirrorType, deviceId, threadId);\r
85 }\r
86 else { // training mode\r
87 if (layer->inputParams.trainingCropType == Util_CenterCrop) {\r
88 rowOffset = (layer->inputParams.row - layer->row)/2;\r
89 colOffset = (layer->inputParams.col - layer->col)/2;\r
90 }\r
91 else { // randomCrop\r
92 rowOffset = timlUtilRandDiscreteUniformRNG(0, layer->inputParams.row - layer->row);\r
93 colOffset = timlUtilRandDiscreteUniformRNG(0, layer->inputParams.col - layer->col);\r
94 }\r
95 timlUtilTransform(layer->featureMap, layer->inputParams.inputData, data, layer->channel, layer->row, layer->col, rowOffset, colOffset, layer->inputParams.row, layer->inputParams.col, layer->inputParams.scale, layer->inputParams.mean, layer->inputParams.testingMirrorType, deviceId, threadId);\r
96 }\r
97 \r
98 return 0;\r
99 }\r