diff --git a/modules/dnn/perf/opencl/perf_convolution.cpp b/modules/dnn/perf/opencl/perf_convolution.cpp deleted file mode 100644 index 28fbf3ae83..0000000000 --- a/modules/dnn/perf/opencl/perf_convolution.cpp +++ /dev/null @@ -1,107 +0,0 @@ -#include "../perf_precomp.hpp" -#include "opencv2/ts/ocl_perf.hpp" -#include - -#ifdef HAVE_OPENCL - -namespace opencv_test { namespace ocl { -using namespace ::perf; - -namespace { -enum {STRIDE_OFF = 1, STRIDE_ON = 2}; -CV_ENUM(StrideSize, STRIDE_OFF, STRIDE_ON); - -enum {GROUP_OFF = 1, GROUP_2 = 2}; -CV_ENUM(GroupSize, GROUP_OFF, GROUP_2); -} // namespace - -//Squared Size -#define SSZ(n) cv::Size(n, n) - -typedef std::pair InpShapeNumOut; -typedef tuple ConvParam; //kernel_size, inp shape, groups, stride -typedef TestBaseWithParam ConvolutionPerfTest; - -static inline MatShape blobShape(int count, int nplanes, int height, int width) -{ - int data[] = {count, nplanes, height, width}; - return MatShape(data, data+4); -} - -OCL_PERF_TEST_P( ConvolutionPerfTest, perf, Combine( - Values(Size(1, 1), Size(3, 3), Size(5, 5), Size(11, 11)), - Values(make_pair(blobShape(1, 4, 224, 224), 64), - make_pair(blobShape(1, 64, 112, 122), 128), - make_pair(blobShape(1, 256, 28, 28), 512)), - GroupSize::all(), - StrideSize::all()) -) -{ - RNG rng(0); - - ConvParam params = GetParam(); - int ksz = get<0>(params).width; - MatShape inpShape = get<1>(params).first; - int outCn = get<1>(params).second; - int groups = get<2>(params); - int stride = (ksz >= 11) ? 4 : (int)get<3>(params); - - int inpCn = inpShape[1]; - int wgtSize[] = { outCn, inpCn/groups, ksz, ksz }; - int biasSize[] = { outCn, 1, 1, 1 }; - const int wtype = CV_32F; - Mat wgtBlob(4, wgtSize, wtype), biasBlob(4, biasSize, wtype); - Mat inpBlob(4, &inpShape[0], wtype); - rng.fill(biasBlob, RNG::UNIFORM, -1, +1); - rng.fill(wgtBlob, RNG::UNIFORM, -1, +1); - rng.fill(inpBlob, RNG::UNIFORM, -1, +1); - - LayerParams lp; - lp.set("num_output", outCn); - lp.set("group", groups); - lp.set("stride", stride); - lp.set("kernel_size", ksz); - lp.blobs.reserve(2); - lp.blobs.push_back(wgtBlob); - lp.blobs.push_back(biasBlob); - - std::vector inpBlobs(1, &inpBlob); - std::vector outBlobs, internalBlobs; - - Ptr layer = cv::dnn::LayerFactory::createLayerInstance("Convolution", lp); - std::vector inputShapes(1, shape(inpBlob)), outShapes, internals; - layer->getMemoryShapes(inputShapes, 0, outShapes, internals); - for (size_t i = 0; i < outShapes.size(); i++) - { - outBlobs.push_back(Mat(outShapes[i], CV_32F)); - } - for (size_t i = 0; i < internals.size(); i++) - { - internalBlobs.push_back(Mat()); - if (total(internals[i])) - internalBlobs.back().create(internals[i], CV_32F); - } - - layer->finalize(inpBlobs, outBlobs); - layer->preferableTarget = DNN_TARGET_OPENCL; - - Mat inpBlob2D = inpBlob.reshape(1, outCn); - Mat wgtBlob2D = wgtBlob.reshape(1, outCn*(inpCn/groups)); - Mat outBlob2D = outBlobs[0].reshape(1, outBlobs[0].size[0]); - declare.in(inpBlob2D, wgtBlob2D, WARMUP_RNG).out(outBlob2D); - - // warmup - layer->forward(inpBlobs, outBlobs, internalBlobs); - - TEST_CYCLE() - { - layer->forward(inpBlobs, outBlobs, internalBlobs); - } - - SANITY_CHECK_NOTHING(); -} - -} -} - -#endif diff --git a/modules/dnn/perf/perf_convolution.cpp b/modules/dnn/perf/perf_convolution.cpp index 16006d75da..5164ac0130 100644 --- a/modules/dnn/perf/perf_convolution.cpp +++ b/modules/dnn/perf/perf_convolution.cpp @@ -1,92 +1,680 @@ +// This file is part of OpenCV project. +// It is subject to the license terms in the LICENSE file found in the top-level directory +// of this distribution and at http://opencv.org/license.html. + #include "perf_precomp.hpp" #include namespace opencv_test { -enum {STRIDE_OFF = 1, STRIDE_ON = 2}; -CV_ENUM(StrideSize, STRIDE_OFF, STRIDE_ON); - -enum {GROUP_OFF = 1, GROUP_2 = 2}; -CV_ENUM(GroupSize, GROUP_OFF, GROUP_2); - -typedef std::pair InpShapeNumOut; -typedef tuple ConvParam; //kernel_size, inp shape, groups, stride -typedef TestBaseWithParam ConvolutionPerfTest; - -static inline MatShape blobShape(int count, int nplanes, int height, int width) +// Flops_Kernel_Input_OutCN_Group_Stride_Pad_Dilation_PadAdjust_PadMode_Bias +struct TestSize_ { + int width, height; + operator Size() const { return Size(width, height); } +}; +struct ConvParam_t { + struct TestSize_ kernel; + struct BlobShape { int dims[4]; } shapeIn; + int outCN; + int groups; + struct TestSize_ stride; + struct TestSize_ dilation; + struct TestSize_ pad; + struct TestSize_ padAdjust; + const char* padMode; + bool hasBias; + double declared_flops; +}; +// Details: #12142 +static const ConvParam_t testConvolutionConfigs[] = { + /* GFLOPS 10.087 x 1 = 10.087 */ {{3, 3}, {{1, 576, 38, 50}}, 512, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 10086963200.}, + /* GFLOPS 1.704 x 5 = 8.518 */ {{3, 3}, {{1, 512, 19, 19}}, 512, 512, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 1703596544.}, + /* GFLOPS 1.704 x 5 = 8.518 */ {{3, 3}, {{1, 512, 19, 19}}, 512, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 1703596544.}, + /* GFLOPS 6.641 x 1 = 6.641 */ {{3, 3}, {{1, 64, 150, 200}}, 192, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 6641280000.}, + /* GFLOPS 1.659 x 3 = 4.977 */ {{3, 3}, {{1, 960, 10, 10}}, 960, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 1658976000.}, + /* GFLOPS 2.156 x 2 = 4.312 */ {{3, 3}, {{1, 576, 19, 19}}, 576, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 2156088384.}, + /* GFLOPS 0.958 x 4 = 3.833 */ {{3, 3}, {{1, 384, 19, 19}}, 384, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 958307712.}, + /* GFLOPS 0.830 x 4 = 3.321 */ {{3, 3}, {{1, 64, 75, 100}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 830160000.}, + /* GFLOPS 1.245 x 2 = 2.490 */ {{3, 3}, {{1, 96, 75, 100}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 1244880000.}, + /* GFLOPS 2.100 x 1 = 2.100 */ {{3, 3}, {{1, 144, 75, 75}}, 144, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 2100330000.}, + /* GFLOPS 1.022 x 2 = 2.044 */ {{3, 3}, {{1, 576, 19, 19}}, 273, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 1021896057.}, + /* GFLOPS 0.958 x 2 = 1.917 */ {{3, 3}, {{1, 192, 38, 38}}, 192, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 958446336.}, + /* GFLOPS 1.888 x 1 = 1.888 */ {{3, 3}, {{1, 1024, 10, 10}}, 1024, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 1887539200.}, + /* GFLOPS 1.888 x 1 = 1.888 */ {{3, 3}, {{1, 1024, 10, 10}}, 1024, 1024, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 1887539200.}, + /* GFLOPS 1.704 x 1 = 1.704 */ {{3, 3}, {{1, 256, 38, 38}}, 256, 256, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 1703781376.}, + /* GFLOPS 1.704 x 1 = 1.704 */ {{3, 3}, {{1, 256, 38, 38}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 1703781376.}, + /* GFLOPS 1.660 x 1 = 1.660 */ {{3, 3}, {{1, 128, 75, 75}}, 128, 128, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 1659600000.}, + /* GFLOPS 1.660 x 1 = 1.660 */ {{3, 3}, {{1, 128, 75, 75}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 1659600000.}, + /* GFLOPS 0.280 x 5 = 1.402 */ {{1, 1}, {{1, 576, 38, 50}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 280409600.}, + /* GFLOPS 0.701 x 2 = 1.401 */ {{3, 3}, {{1, 128, 38, 50}}, 160, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 700720000.}, + /* GFLOPS 0.231 x 6 = 1.388 */ {{3, 3}, {{1, 128, 56, 56}}, 32, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", false, 231311360.}, + /* GFLOPS 0.231 x 6 = 1.388 */ {{3, 3}, {{1, 256, 14, 14}}, 256, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", false, 231261184.}, + /* GFLOPS 0.210 x 6 = 1.262 */ {{1, 1}, {{1, 576, 38, 50}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 210307200.}, + /* GFLOPS 0.420 x 3 = 1.261 */ {{3, 3}, {{1, 96, 38, 50}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 420492800.}, + /* GFLOPS 1.261 x 1 = 1.261 */ {{3, 3}, {{1, 192, 38, 50}}, 192, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 1261113600.}, + /* GFLOPS 1.258 x 1 = 1.258 */ {{3, 3}, {{1, 1280, 10, 10}}, 546, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 1258038600.}, + /* GFLOPS 1.245 x 1 = 1.245 */ {{3, 3}, {{1, 64, 75, 75}}, 192, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 1245240000.}, + /* GFLOPS 0.561 x 2 = 1.121 */ {{3, 3}, {{1, 128, 38, 50}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 560576000.}, + /* GFLOPS 1.051 x 1 = 1.051 */ {{3, 3}, {{1, 160, 38, 50}}, 192, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 1050988800.}, + /* GFLOPS 1.006 x 1 = 1.006 */ {{3, 3}, {{1, 1024, 10, 10}}, 546, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 1006441800.}, + /* GFLOPS 0.246 x 4 = 0.985 */ {{1, 1}, {{1, 256, 75, 100}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 246240000.}, + /* GFLOPS 0.189 x 5 = 0.947 */ {{1, 1}, {{1, 512, 19, 19}}, 512, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 189452800.}, + /* GFLOPS 0.189 x 5 = 0.947 */ {{1, 1}, {{1, 512, 19, 19}}, 512, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 189452800.}, + /* GFLOPS 0.934 x 1 = 0.934 */ {{3, 3}, {{1, 96, 150, 150}}, 96, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 933660000.}, + /* GFLOPS 0.231 x 4 = 0.925 */ {{3, 3}, {{1, 128, 28, 28}}, 128, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", false, 231311360.}, + /* GFLOPS 0.896 x 1 = 0.896 */ {{5, 5}, {{1, 96, 27, 27}}, 256, 2, {1, 1}, {1, 1}, {2, 2}, {0, 0}, "", true, 895981824.}, + /* GFLOPS 0.876 x 1 = 0.876 */ {{3, 3}, {{1, 160, 38, 50}}, 160, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 875824000.}, + /* GFLOPS 0.850 x 1 = 0.850 */ {{7, 7}, {{1, 3, 600, 800}}, 24, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 849600000.}, + /* GFLOPS 0.841 x 1 = 0.841 */ {{3, 3}, {{1, 128, 38, 50}}, 192, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 840864000.}, + /* GFLOPS 0.415 x 2 = 0.831 */ {{3, 3}, {{1, 32, 150, 150}}, 32, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 415440000.}, + /* GFLOPS 0.351 x 2 = 0.701 */ {{1, 1}, {{1, 576, 38, 50}}, 160, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 350512000.}, + /* GFLOPS 0.701 x 1 = 0.701 */ {{3, 3}, {{1, 128, 75, 100}}, 160, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 700720000.}, + /* GFLOPS 0.694 x 1 = 0.694 */ {{3, 3}, {{1, 64, 56, 56}}, 192, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 694235136.}, + /* GFLOPS 0.694 x 1 = 0.694 */ {{3, 3}, {{1, 64, 56, 56}}, 192, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 694235136.}, + /* GFLOPS 0.231 x 3 = 0.694 */ {{3, 3}, {{1, 64, 56, 56}}, 64, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", false, 231411712.}, + /* GFLOPS 0.058 x 12 = 0.694 */ {{3, 3}, {{1, 128, 28, 28}}, 32, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", false, 57827840.}, + /* GFLOPS 0.231 x 3 = 0.694 */ {{3, 3}, {{1, 512, 7, 7}}, 512, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", false, 231236096.}, + /* GFLOPS 0.160 x 4 = 0.639 */ {{3, 3}, {{1, 64, 38, 38}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 159833472.}, + /* GFLOPS 0.103 x 6 = 0.618 */ {{1, 1}, {{1, 256, 14, 14}}, 1024, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 102961152.}, + /* GFLOPS 0.615 x 1 = 0.615 */ {{1, 1}, {{1, 320, 75, 100}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 615360000.}, + /* GFLOPS 0.597 x 1 = 0.597 */ {{3, 3}, {{1, 576, 19, 19}}, 576, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 597254400.}, + /* GFLOPS 0.185 x 3 = 0.554 */ {{1, 1}, {{1, 192, 75, 100}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 184800000.}, + /* GFLOPS 0.553 x 1 = 0.553 */ {{3, 3}, {{1, 64, 75, 100}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 553440000.}, + /* GFLOPS 0.539 x 1 = 0.539 */ {{3, 3}, {{1, 144, 75, 75}}, 144, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 539178048.}, + /* GFLOPS 0.103 x 5 = 0.514 */ {{1, 1}, {{1, 1024, 14, 14}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 102810624.}, + /* GFLOPS 0.491 x 1 = 0.491 */ {{1, 1}, {{1, 576, 38, 50}}, 224, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 490716800.}, + /* GFLOPS 0.240 x 2 = 0.479 */ {{3, 3}, {{1, 96, 38, 38}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 239680896.}, + /* GFLOPS 0.237 x 2 = 0.474 */ {{7, 7}, {{1, 3, 224, 224}}, 64, 1, {2, 2}, {1, 1}, {3, 3}, {0, 0}, "", true, 236830720.}, + /* GFLOPS 0.472 x 1 = 0.472 */ {{3, 3}, {{1, 512, 19, 19}}, 512, 512, {2, 2}, {1, 1}, {1, 1}, {0, 0}, "", true, 471910400.}, + /* GFLOPS 0.472 x 1 = 0.472 */ {{3, 3}, {{1, 512, 19, 19}}, 512, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 471910400.}, + /* GFLOPS 0.449 x 1 = 0.449 */ {{3, 3}, {{1, 384, 13, 13}}, 384, 2, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 448626048.}, + /* GFLOPS 0.426 x 1 = 0.426 */ {{3, 3}, {{1, 128, 75, 75}}, 128, 128, {2, 2}, {1, 1}, {1, 1}, {0, 0}, "", true, 426037760.}, + /* GFLOPS 0.426 x 1 = 0.426 */ {{3, 3}, {{1, 128, 75, 75}}, 128, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 426037760.}, + /* GFLOPS 0.426 x 1 = 0.426 */ {{3, 3}, {{1, 128, 38, 38}}, 128, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", false, 426037760.}, + /* GFLOPS 0.426 x 1 = 0.426 */ {{3, 3}, {{1, 256, 38, 38}}, 256, 256, {2, 2}, {1, 1}, {1, 1}, {0, 0}, "", true, 425945344.}, + /* GFLOPS 0.426 x 1 = 0.426 */ {{3, 3}, {{1, 256, 38, 38}}, 256, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 425945344.}, + /* GFLOPS 0.426 x 1 = 0.426 */ {{3, 3}, {{1, 256, 19, 19}}, 256, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", false, 425945344.}, + /* GFLOPS 0.421 x 1 = 0.421 */ {{1, 1}, {{1, 576, 38, 50}}, 192, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 420614400.}, + /* GFLOPS 0.415 x 1 = 0.415 */ {{3, 3}, {{1, 32, 150, 150}}, 32, 32, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 415440000.}, + /* GFLOPS 0.415 x 1 = 0.415 */ {{3, 3}, {{1, 64, 150, 150}}, 64, 64, {2, 2}, {1, 1}, {1, 1}, {0, 0}, "", true, 415080000.}, + /* GFLOPS 0.415 x 1 = 0.415 */ {{3, 3}, {{1, 64, 150, 150}}, 64, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 415080000.}, + /* GFLOPS 0.104 x 4 = 0.414 */ {{1, 1}, {{1, 64, 56, 56}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 103563264.}, + /* GFLOPS 0.103 x 4 = 0.413 */ {{1, 1}, {{1, 128, 28, 28}}, 512, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 103161856.}, + /* GFLOPS 0.376 x 1 = 0.376 */ {{1, 1}, {{1, 24, 300, 400}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "VALID", true, 376320000.}, + /* GFLOPS 0.347 x 1 = 0.347 */ {{3, 3}, {{1, 128, 28, 28}}, 192, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 346967040.}, + /* GFLOPS 0.347 x 1 = 0.347 */ {{3, 3}, {{1, 128, 28, 28}}, 192, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 346967040.}, + /* GFLOPS 0.014 x 24 = 0.347 */ {{3, 3}, {{1, 128, 14, 14}}, 32, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", false, 14456960.}, + /* GFLOPS 0.053 x 6 = 0.320 */ {{1, 1}, {{1, 576, 19, 19}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 53277824.}, + /* GFLOPS 0.319 x 1 = 0.319 */ {{3, 3}, {{1, 192, 19, 19}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 319482112.}, + /* GFLOPS 0.315 x 1 = 0.315 */ {{3, 3}, {{1, 96, 75, 100}}, 96, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 315369600.}, + /* GFLOPS 0.103 x 3 = 0.309 */ {{1, 1}, {{1, 512, 7, 7}}, 2048, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 102860800.}, + /* GFLOPS 0.103 x 3 = 0.309 */ {{1, 1}, {{1, 512, 28, 28}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 102860800.}, + /* GFLOPS 0.308 x 1 = 0.308 */ {{1, 1}, {{1, 320, 75, 100}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 307680000.}, + /* GFLOPS 0.299 x 1 = 0.299 */ {{3, 3}, {{1, 256, 13, 13}}, 384, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 299105664.}, + /* GFLOPS 0.299 x 1 = 0.299 */ {{3, 3}, {{1, 384, 13, 13}}, 256, 2, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 299084032.}, + /* GFLOPS 0.017 x 17 = 0.290 */ {{1, 1}, {{1, 32, 32, 64}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 17039360.}, + /* GFLOPS 0.017 x 16 = 0.269 */ {{1, 1}, {{1, 128, 32, 64}}, 32, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 16842752.}, + /* GFLOPS 0.133 x 2 = 0.266 */ {{3, 3}, {{1, 128, 19, 19}}, 160, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 133136800.}, + /* GFLOPS 0.038 x 7 = 0.265 */ {{3, 3}, {{1, 16, 64, 128}}, 16, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 37879808.}, + /* GFLOPS 0.126 x 2 = 0.252 */ {{3, 3}, {{1, 512, 5, 5}}, 546, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 125812050.}, + /* GFLOPS 0.248 x 1 = 0.248 */ {{1, 1}, {{1, 64, 150, 200}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 247680000.}, + /* GFLOPS 0.040 x 6 = 0.240 */ {{1, 1}, {{1, 576, 19, 19}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 39958368.}, + /* GFLOPS 0.080 x 3 = 0.240 */ {{3, 3}, {{1, 96, 19, 19}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 79893632.}, + /* GFLOPS 0.240 x 1 = 0.240 */ {{3, 3}, {{1, 192, 38, 38}}, 192, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 239611584.}, + /* GFLOPS 0.240 x 1 = 0.240 */ {{3, 3}, {{1, 192, 19, 19}}, 192, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 239611584.}, + /* GFLOPS 0.237 x 1 = 0.237 */ {{7, 7}, {{1, 3, 224, 224}}, 64, 1, {2, 2}, {1, 1}, {3, 3}, {0, 0}, "", false, 236830720.}, + /* GFLOPS 0.237 x 1 = 0.237 */ {{7, 7}, {{1, 3, 224, 224}}, 64, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 236830720.}, + /* GFLOPS 0.111 x 2 = 0.221 */ {{3, 3}, {{1, 192, 10, 10}}, 320, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 110624000.}, + /* GFLOPS 0.213 x 1 = 0.213 */ {{3, 3}, {{1, 128, 38, 38}}, 256, 1, {2, 2}, {1, 1}, {1, 1}, {0, 0}, "", false, 213018880.}, + /* GFLOPS 0.213 x 1 = 0.213 */ {{3, 3}, {{1, 128, 19, 19}}, 256, 1, {1, 1}, {2, 2}, {2, 2}, {0, 0}, "", false, 213018880.}, + /* GFLOPS 0.107 x 2 = 0.213 */ {{3, 3}, {{1, 128, 19, 19}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 106509440.}, + /* GFLOPS 0.213 x 1 = 0.213 */ {{3, 3}, {{1, 256, 19, 19}}, 128, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", false, 212972672.}, + /* GFLOPS 0.212 x 1 = 0.212 */ {{7, 7}, {{1, 3, 300, 300}}, 32, 1, {2, 2}, {1, 1}, {3, 3}, {0, 0}, "", true, 212400000.}, + /* GFLOPS 0.211 x 1 = 0.211 */ {{11, 11}, {{1, 3, 227, 227}}, 96, 1, {4, 4}, {1, 1}, {0, 0}, {0, 0}, "", true, 211120800.}, + /* GFLOPS 0.210 x 1 = 0.210 */ {{3, 3}, {{1, 64, 38, 50}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 210307200.}, + /* GFLOPS 0.210 x 1 = 0.210 */ {{1, 1}, {{1, 1024, 10, 10}}, 1024, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 209817600.}, + /* GFLOPS 0.210 x 1 = 0.210 */ {{1, 1}, {{1, 1024, 10, 10}}, 1024, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 209817600.}, + /* GFLOPS 0.104 x 2 = 0.208 */ {{3, 3}, {{1, 32, 75, 75}}, 32, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", false, 103860000.}, + /* GFLOPS 0.206 x 1 = 0.206 */ {{1, 1}, {{1, 256, 56, 56}}, 512, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "", false, 205922304.}, + /* GFLOPS 0.206 x 1 = 0.206 */ {{1, 1}, {{1, 256, 56, 56}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 205922304.}, + /* GFLOPS 0.103 x 2 = 0.206 */ {{1, 1}, {{1, 256, 56, 56}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 102961152.}, + /* GFLOPS 0.206 x 1 = 0.206 */ {{1, 1}, {{1, 512, 28, 28}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 205721600.}, + /* GFLOPS 0.206 x 1 = 0.206 */ {{1, 1}, {{1, 512, 28, 28}}, 1024, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "", false, 205721600.}, + /* GFLOPS 0.206 x 1 = 0.206 */ {{1, 1}, {{1, 1024, 14, 14}}, 512, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 205621248.}, + /* GFLOPS 0.206 x 1 = 0.206 */ {{1, 1}, {{1, 1024, 14, 14}}, 2048, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "", false, 205621248.}, + /* GFLOPS 0.103 x 2 = 0.206 */ {{1, 1}, {{1, 2048, 7, 7}}, 512, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 102785536.}, + /* GFLOPS 0.201 x 1 = 0.201 */ {{1, 1}, {{1, 512, 14, 14}}, 1000, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 200900000.}, + /* GFLOPS 0.200 x 1 = 0.200 */ {{3, 3}, {{1, 160, 19, 19}}, 192, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 199687872.}, + /* GFLOPS 0.190 x 1 = 0.190 */ {{1, 1}, {{1, 256, 38, 38}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 189637632.}, + /* GFLOPS 0.190 x 1 = 0.190 */ {{1, 1}, {{1, 256, 38, 38}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 189637632.}, + /* GFLOPS 0.047 x 4 = 0.190 */ {{1, 1}, {{1, 256, 38, 38}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 47409408.}, + /* GFLOPS 0.038 x 5 = 0.189 */ {{3, 3}, {{1, 32, 32, 64}}, 32, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 37814272.}, + /* GFLOPS 0.185 x 1 = 0.185 */ {{1, 1}, {{1, 128, 75, 75}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 185040000.}, + /* GFLOPS 0.185 x 1 = 0.185 */ {{1, 1}, {{1, 128, 75, 75}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 185040000.}, + /* GFLOPS 0.181 x 1 = 0.181 */ {{3, 3}, {{1, 160, 14, 14}}, 320, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 180696320.}, + /* GFLOPS 0.181 x 1 = 0.181 */ {{3, 3}, {{1, 160, 14, 14}}, 320, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 180696320.}, + /* GFLOPS 0.090 x 2 = 0.181 */ {{3, 3}, {{1, 224, 10, 10}}, 224, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 90339200.}, + /* GFLOPS 0.180 x 1 = 0.180 */ {{1, 1}, {{1, 224, 56, 56}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 180232192.}, + /* GFLOPS 0.174 x 1 = 0.174 */ {{3, 3}, {{1, 96, 28, 28}}, 128, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 173508608.}, + /* GFLOPS 0.174 x 1 = 0.174 */ {{3, 3}, {{1, 96, 28, 28}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 173508608.}, + /* GFLOPS 0.166 x 1 = 0.166 */ {{3, 3}, {{1, 160, 19, 19}}, 160, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 166406560.}, + /* GFLOPS 0.080 x 2 = 0.160 */ {{1, 1}, {{1, 576, 19, 19}}, 192, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 79916736.}, + /* GFLOPS 0.160 x 1 = 0.160 */ {{3, 3}, {{1, 128, 19, 19}}, 192, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 159764160.}, + /* GFLOPS 0.159 x 1 = 0.159 */ {{7, 7}, {{1, 3, 300, 300}}, 24, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 159300000.}, + /* GFLOPS 0.155 x 1 = 0.155 */ {{1, 1}, {{1, 192, 56, 56}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 154542080.}, + /* GFLOPS 0.146 x 1 = 0.146 */ {{3, 3}, {{1, 144, 14, 14}}, 288, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 146369664.}, + /* GFLOPS 0.146 x 1 = 0.146 */ {{3, 3}, {{1, 144, 14, 14}}, 288, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 146369664.}, + /* GFLOPS 0.072 x 2 = 0.144 */ {{1, 1}, {{1, 1024, 10, 10}}, 352, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 72124800.}, + /* GFLOPS 0.140 x 1 = 0.140 */ {{1, 1}, {{1, 576, 38, 50}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 140204800.}, + /* GFLOPS 0.017 x 8 = 0.138 */ {{1, 1}, {{1, 16, 64, 128}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 17301504.}, + /* GFLOPS 0.067 x 2 = 0.133 */ {{1, 1}, {{1, 576, 19, 19}}, 160, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 66597280.}, + /* GFLOPS 0.133 x 1 = 0.133 */ {{3, 3}, {{1, 128, 38, 38}}, 160, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 133136800.}, + /* GFLOPS 0.129 x 1 = 0.129 */ {{1, 1}, {{1, 160, 56, 56}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 128851968.}, + /* GFLOPS 0.128 x 1 = 0.128 */ {{3, 3}, {{1, 64, 24, 24}}, 192, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 127512576.}, + /* GFLOPS 0.120 x 1 = 0.120 */ {{5, 5}, {{1, 32, 28, 28}}, 96, 1, {1, 1}, {1, 1}, {2, 2}, {0, 0}, "", true, 120497664.}, + /* GFLOPS 0.120 x 1 = 0.120 */ {{5, 5}, {{1, 32, 28, 28}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 120497664.}, + /* GFLOPS 0.040 x 3 = 0.120 */ {{1, 1}, {{1, 96, 19, 19}}, 576, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 40131648.}, + /* GFLOPS 0.118 x 1 = 0.118 */ {{1, 1}, {{1, 320, 38, 38}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 118477312.}, + /* GFLOPS 0.017 x 7 = 0.118 */ {{1, 1}, {{1, 64, 64, 128}}, 16, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 16908288.}, + /* GFLOPS 0.039 x 3 = 0.118 */ {{1, 1}, {{1, 1024, 10, 10}}, 192, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 39340800.}, + /* GFLOPS 0.118 x 1 = 0.118 */ {{3, 3}, {{1, 256, 19, 19}}, 256, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 117990400.}, + /* GFLOPS 0.058 x 2 = 0.116 */ {{3, 3}, {{1, 16, 56, 56}}, 64, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 58003456.}, + /* GFLOPS 0.058 x 2 = 0.116 */ {{3, 3}, {{1, 32, 28, 28}}, 128, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 57903104.}, + /* GFLOPS 0.058 x 2 = 0.116 */ {{3, 3}, {{1, 64, 14, 14}}, 256, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 57852928.}, + /* GFLOPS 0.116 x 1 = 0.116 */ {{3, 3}, {{1, 128, 14, 14}}, 256, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 115655680.}, + /* GFLOPS 0.116 x 1 = 0.116 */ {{3, 3}, {{1, 128, 14, 14}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 115655680.}, + /* GFLOPS 0.112 x 1 = 0.112 */ {{1, 1}, {{1, 1024, 10, 10}}, 546, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 111875400.}, + /* GFLOPS 0.036 x 3 = 0.107 */ {{1, 1}, {{1, 192, 38, 38}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 35580160.}, + /* GFLOPS 0.107 x 1 = 0.107 */ {{3, 3}, {{1, 32, 75, 75}}, 128, 1, {2, 2}, {1, 1}, {1, 1}, {0, 0}, "", false, 106648064.}, + /* GFLOPS 0.107 x 1 = 0.107 */ {{3, 3}, {{1, 64, 38, 38}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 106555648.}, + /* GFLOPS 0.105 x 1 = 0.105 */ {{1, 1}, {{1, 512, 10, 10}}, 1024, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 104960000.}, + /* GFLOPS 0.105 x 1 = 0.105 */ {{1, 1}, {{1, 512, 10, 10}}, 1024, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 104960000.}, + /* GFLOPS 0.103 x 1 = 0.103 */ {{1, 1}, {{1, 128, 56, 56}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 103161856.}, + /* GFLOPS 0.051 x 2 = 0.103 */ {{1, 1}, {{1, 256, 28, 28}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 51480576.}, + /* GFLOPS 0.051 x 2 = 0.103 */ {{1, 1}, {{1, 256, 28, 28}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 51480576.}, + /* GFLOPS 0.101 x 1 = 0.101 */ {{1, 1}, {{1, 512, 19, 19}}, 273, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 101016825.}, + /* GFLOPS 0.096 x 1 = 0.096 */ {{1, 1}, {{1, 480, 28, 28}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 96438272.}, + /* GFLOPS 0.095 x 1 = 0.095 */ {{1, 1}, {{1, 128, 38, 38}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 95003648.}, + /* GFLOPS 0.095 x 1 = 0.095 */ {{1, 1}, {{1, 128, 38, 38}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 95003648.}, + /* GFLOPS 0.095 x 1 = 0.095 */ {{1, 1}, {{1, 256, 19, 19}}, 512, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 94818816.}, + /* GFLOPS 0.095 x 1 = 0.095 */ {{1, 1}, {{1, 256, 19, 19}}, 512, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 94818816.}, + /* GFLOPS 0.094 x 1 = 0.094 */ {{1, 1}, {{1, 32, 150, 150}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 93600000.}, + /* GFLOPS 0.094 x 1 = 0.094 */ {{1, 1}, {{1, 32, 150, 150}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 93600000.}, + /* GFLOPS 0.093 x 1 = 0.093 */ {{1, 1}, {{1, 512, 38, 50}}, 48, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 93480000.}, + /* GFLOPS 0.093 x 1 = 0.093 */ {{1, 1}, {{1, 576, 19, 19}}, 224, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 93236192.}, + /* GFLOPS 0.093 x 1 = 0.093 */ {{1, 1}, {{1, 64, 75, 75}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 92880000.}, + /* GFLOPS 0.093 x 1 = 0.093 */ {{1, 1}, {{1, 64, 75, 75}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 92880000.}, + /* GFLOPS 0.031 x 3 = 0.092 */ {{1, 1}, {{1, 160, 10, 10}}, 960, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 30816000.}, + /* GFLOPS 0.092 x 1 = 0.092 */ {{1, 1}, {{1, 192, 75, 100}}, 32, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 92400000.}, + /* GFLOPS 0.090 x 1 = 0.090 */ {{1, 1}, {{1, 448, 28, 28}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 90015744.}, + /* GFLOPS 0.045 x 2 = 0.090 */ {{3, 3}, {{1, 576, 19, 19}}, 12, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 44918508.}, + /* GFLOPS 0.089 x 1 = 0.089 */ {{3, 3}, {{1, 112, 14, 14}}, 224, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 88554368.}, + /* GFLOPS 0.089 x 1 = 0.089 */ {{3, 3}, {{1, 112, 14, 14}}, 224, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 88554368.}, + /* GFLOPS 0.021 x 4 = 0.084 */ {{5, 1}, {{1, 32, 32, 64}}, 32, 1, {1, 1}, {1, 1}, {2, 0}, {0, 0}, "", false, 21037056.}, + /* GFLOPS 0.021 x 4 = 0.084 */ {{1, 5}, {{1, 32, 32, 64}}, 32, 1, {1, 1}, {1, 1}, {0, 2}, {0, 0}, "", true, 21037056.}, + /* GFLOPS 0.084 x 1 = 0.084 */ {{1, 1}, {{1, 416, 28, 28}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 83593216.}, + /* GFLOPS 0.082 x 1 = 0.082 */ {{1, 1}, {{1, 320, 10, 10}}, 1280, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 82048000.}, + /* GFLOPS 0.040 x 2 = 0.080 */ {{1, 1}, {{1, 576, 19, 19}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 39958368.}, + /* GFLOPS 0.040 x 2 = 0.079 */ {{1, 1}, {{1, 24, 75, 75}}, 144, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 39690000.}, + /* GFLOPS 0.040 x 2 = 0.079 */ {{3, 3}, {{1, 3, 300, 300}}, 32, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 39600000.}, + /* GFLOPS 0.077 x 1 = 0.077 */ {{1, 1}, {{1, 96, 56, 56}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 77471744.}, + /* GFLOPS 0.077 x 1 = 0.077 */ {{3, 3}, {{1, 192, 10, 10}}, 224, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 77436800.}, + /* GFLOPS 0.077 x 1 = 0.077 */ {{1, 1}, {{1, 384, 28, 28}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 77170688.}, + /* GFLOPS 0.038 x 2 = 0.076 */ {{3, 3}, {{1, 32, 32, 64}}, 32, 1, {1, 1}, {8, 8}, {8, 8}, {0, 0}, "", true, 37814272.}, + /* GFLOPS 0.038 x 2 = 0.076 */ {{3, 3}, {{1, 32, 32, 64}}, 32, 1, {1, 1}, {4, 4}, {4, 4}, {0, 0}, "", true, 37814272.}, + /* GFLOPS 0.038 x 2 = 0.076 */ {{3, 3}, {{1, 32, 32, 64}}, 32, 1, {1, 1}, {2, 2}, {2, 2}, {0, 0}, "", true, 37814272.}, + /* GFLOPS 0.038 x 2 = 0.076 */ {{3, 3}, {{1, 32, 32, 64}}, 32, 1, {1, 1}, {16, 16}, {16, 16}, {0, 0}, "", true, 37814272.}, + /* GFLOPS 0.018 x 4 = 0.072 */ {{1, 1}, {{1, 64, 19, 19}}, 384, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 17882496.}, + /* GFLOPS 0.071 x 1 = 0.071 */ {{1, 1}, {{1, 16, 150, 150}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 71280000.}, + /* GFLOPS 0.071 x 1 = 0.071 */ {{1, 1}, {{1, 352, 28, 28}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 70748160.}, + /* GFLOPS 0.071 x 1 = 0.071 */ {{1, 1}, {{1, 24, 150, 150}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "VALID", true, 70560000.}, + /* GFLOPS 0.070 x 1 = 0.070 */ {{3, 3}, {{1, 96, 14, 14}}, 208, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 70487872.}, + /* GFLOPS 0.069 x 1 = 0.069 */ {{3, 3}, {{1, 96, 14, 14}}, 204, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 69132336.}, + /* GFLOPS 0.066 x 1 = 0.066 */ {{1, 1}, {{1, 1280, 10, 10}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 65561600.}, + /* GFLOPS 0.033 x 2 = 0.065 */ {{3, 3}, {{1, 48, 14, 14}}, 192, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 32551680.}, + /* GFLOPS 0.065 x 1 = 0.065 */ {{3, 3}, {{1, 192, 7, 7}}, 384, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 65046912.}, + /* GFLOPS 0.065 x 1 = 0.065 */ {{3, 3}, {{1, 192, 7, 7}}, 384, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 65046912.}, + /* GFLOPS 0.065 x 1 = 0.065 */ {{3, 3}, {{1, 160, 10, 10}}, 224, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 64534400.}, + /* GFLOPS 0.064 x 1 = 0.064 */ {{1, 1}, {{1, 320, 28, 28}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 64325632.}, + /* GFLOPS 0.032 x 2 = 0.064 */ {{3, 3}, {{1, 96, 12, 12}}, 128, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 31868928.}, + /* GFLOPS 0.061 x 1 = 0.061 */ {{1, 1}, {{1, 960, 10, 10}}, 320, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 61472000.}, + /* GFLOPS 0.031 x 2 = 0.061 */ {{1, 1}, {{1, 960, 10, 10}}, 160, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 30736000.}, + /* GFLOPS 0.060 x 1 = 0.060 */ {{3, 3}, {{1, 96, 38, 38}}, 96, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 59920224.}, + /* GFLOPS 0.059 x 1 = 0.059 */ {{1, 1}, {{1, 320, 38, 38}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 59238656.}, + /* GFLOPS 0.059 x 1 = 0.059 */ {{3, 3}, {{1, 128, 19, 19}}, 256, 1, {2, 2}, {1, 1}, {1, 1}, {0, 0}, "", true, 59008000.}, + /* GFLOPS 0.059 x 1 = 0.059 */ {{3, 3}, {{1, 256, 10, 10}}, 512, 1, {2, 2}, {1, 1}, {1, 1}, {0, 0}, "", true, 58995200.}, + /* GFLOPS 0.059 x 1 = 0.059 */ {{3, 3}, {{1, 256, 10, 10}}, 512, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 58995200.}, + /* GFLOPS 0.059 x 1 = 0.059 */ {{3, 3}, {{1, 256, 10, 10}}, 512, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 58995200.}, + /* GFLOPS 0.058 x 1 = 0.058 */ {{1, 1}, {{1, 288, 28, 28}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 57903104.}, + /* GFLOPS 0.004 x 16 = 0.058 */ {{3, 3}, {{1, 128, 7, 7}}, 32, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", false, 3614240.}, + /* GFLOPS 0.055 x 1 = 0.055 */ {{3, 3}, {{1, 1280, 10, 10}}, 24, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 55298400.}, + /* GFLOPS 0.018 x 3 = 0.054 */ {{1, 1}, {{1, 32, 38, 38}}, 192, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 18021120.}, + /* GFLOPS 0.018 x 3 = 0.053 */ {{1, 1}, {{1, 384, 19, 19}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 17766976.}, + /* GFLOPS 0.053 x 1 = 0.053 */ {{3, 3}, {{1, 128, 38, 38}}, 16, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 53254720.}, + /* GFLOPS 0.053 x 1 = 0.053 */ {{1, 1}, {{1, 528, 14, 14}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 53036032.}, + /* GFLOPS 0.053 x 1 = 0.053 */ {{1, 1}, {{1, 528, 14, 14}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 53036032.}, + /* GFLOPS 0.052 x 1 = 0.052 */ {{1, 1}, {{1, 1024, 10, 10}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 52454400.}, + /* GFLOPS 0.052 x 1 = 0.052 */ {{1, 1}, {{1, 1024, 10, 10}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 52454400.}, + /* GFLOPS 0.052 x 1 = 0.052 */ {{1, 1}, {{1, 1024, 10, 10}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 52454400.}, + /* GFLOPS 0.026 x 2 = 0.052 */ {{1, 1}, {{1, 1024, 10, 10}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 26227200.}, + /* GFLOPS 0.052 x 1 = 0.052 */ {{1, 1}, {{1, 64, 56, 56}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 51781632.}, + /* GFLOPS 0.051 x 1 = 0.051 */ {{1, 1}, {{1, 256, 56, 56}}, 128, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "", false, 51480576.}, + /* GFLOPS 0.051 x 1 = 0.051 */ {{1, 1}, {{1, 256, 28, 28}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 51480576.}, + /* GFLOPS 0.051 x 1 = 0.051 */ {{1, 1}, {{1, 512, 28, 28}}, 256, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "", false, 51430400.}, + /* GFLOPS 0.026 x 2 = 0.051 */ {{1, 1}, {{1, 512, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 25715200.}, + /* GFLOPS 0.026 x 2 = 0.051 */ {{1, 1}, {{1, 512, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 25715200.}, + /* GFLOPS 0.013 x 4 = 0.051 */ {{1, 1}, {{1, 512, 14, 14}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 12857600.}, + /* GFLOPS 0.051 x 1 = 0.051 */ {{1, 1}, {{1, 1024, 14, 14}}, 512, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "", false, 51405312.}, + /* GFLOPS 0.050 x 1 = 0.050 */ {{1, 1}, {{1, 992, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 49799680.}, + /* GFLOPS 0.048 x 1 = 0.048 */ {{1, 1}, {{1, 960, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 48194048.}, + /* GFLOPS 0.047 x 1 = 0.047 */ {{1, 1}, {{1, 256, 19, 19}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 47409408.}, + /* GFLOPS 0.047 x 1 = 0.047 */ {{1, 1}, {{1, 512, 38, 50}}, 24, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 46740000.}, + /* GFLOPS 0.047 x 1 = 0.047 */ {{1, 1}, {{1, 928, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 46588416.}, + /* GFLOPS 0.046 x 1 = 0.046 */ {{1, 1}, {{1, 64, 75, 75}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 46440000.}, + /* GFLOPS 0.023 x 2 = 0.045 */ {{3, 3}, {{1, 256, 3, 3}}, 546, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 22648626.}, + /* GFLOPS 0.045 x 1 = 0.045 */ {{3, 3}, {{1, 160, 7, 7}}, 320, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 45174080.}, + /* GFLOPS 0.045 x 1 = 0.045 */ {{3, 3}, {{1, 160, 7, 7}}, 320, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 45174080.}, + /* GFLOPS 0.045 x 1 = 0.045 */ {{1, 1}, {{1, 224, 28, 28}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 45058048.}, + /* GFLOPS 0.023 x 2 = 0.045 */ {{1, 1}, {{1, 512, 14, 14}}, 112, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 22500800.}, + /* GFLOPS 0.045 x 1 = 0.045 */ {{1, 1}, {{1, 896, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 44982784.}, + /* GFLOPS 0.045 x 1 = 0.045 */ {{3, 3}, {{1, 3, 227, 227}}, 64, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "", true, 44946880.}, + /* GFLOPS 0.044 x 1 = 0.044 */ {{3, 3}, {{1, 128, 19, 19}}, 192, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 44256000.}, + /* GFLOPS 0.044 x 1 = 0.044 */ {{3, 3}, {{1, 1024, 10, 10}}, 24, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 44239200.}, + /* GFLOPS 0.043 x 1 = 0.043 */ {{7, 7}, {{1, 3, 96, 96}}, 64, 1, {2, 2}, {1, 1}, {3, 3}, {0, 0}, "", true, 43499520.}, + /* GFLOPS 0.043 x 1 = 0.043 */ {{1, 1}, {{1, 864, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 43377152.}, + /* GFLOPS 0.042 x 1 = 0.042 */ {{1, 1}, {{1, 832, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 41771520.}, + /* GFLOPS 0.040 x 1 = 0.040 */ {{5, 5}, {{1, 32, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {2, 2}, {0, 0}, "", true, 40165888.}, + /* GFLOPS 0.040 x 1 = 0.040 */ {{5, 5}, {{1, 32, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 40165888.}, + /* GFLOPS 0.040 x 1 = 0.040 */ {{1, 1}, {{1, 800, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 40165888.}, + /* GFLOPS 0.040 x 1 = 0.040 */ {{3, 3}, {{1, 64, 19, 19}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 39958368.}, + /* GFLOPS 0.040 x 1 = 0.040 */ {{3, 3}, {{1, 256, 19, 19}}, 24, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 39932376.}, + /* GFLOPS 0.040 x 1 = 0.040 */ {{3, 3}, {{1, 3, 300, 300}}, 32, 1, {2, 2}, {1, 1}, {1, 1}, {0, 0}, "", true, 39600000.}, + /* GFLOPS 0.039 x 1 = 0.039 */ {{1, 1}, {{1, 144, 75, 75}}, 24, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 39015000.}, + /* GFLOPS 0.039 x 1 = 0.039 */ {{1, 1}, {{1, 192, 28, 28}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 38635520.}, + /* GFLOPS 0.039 x 1 = 0.039 */ {{1, 1}, {{1, 768, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 38560256.}, + /* GFLOPS 0.037 x 1 = 0.037 */ {{1, 1}, {{1, 736, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 36954624.}, + /* GFLOPS 0.036 x 1 = 0.036 */ {{1, 1}, {{1, 480, 14, 14}}, 192, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 36164352.}, + /* GFLOPS 0.036 x 1 = 0.036 */ {{1, 1}, {{1, 480, 14, 14}}, 192, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 36164352.}, + /* GFLOPS 0.018 x 2 = 0.036 */ {{1, 1}, {{1, 192, 38, 38}}, 32, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 17790080.}, + /* GFLOPS 0.035 x 1 = 0.035 */ {{1, 1}, {{1, 704, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 35348992.}, + /* GFLOPS 0.034 x 1 = 0.034 */ {{1, 1}, {{1, 672, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 33743360.}, + /* GFLOPS 0.034 x 1 = 0.034 */ {{1, 1}, {{1, 128, 32, 64}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 33685504.}, + /* GFLOPS 0.034 x 1 = 0.034 */ {{2, 2}, {{1, 64, 64, 128}}, 32, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "", false, 33619968.}, + /* GFLOPS 0.033 x 1 = 0.033 */ {{1, 1}, {{1, 528, 14, 14}}, 160, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 33147520.}, + /* GFLOPS 0.033 x 1 = 0.033 */ {{1, 1}, {{1, 528, 14, 14}}, 160, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 33147520.}, + /* GFLOPS 0.033 x 1 = 0.033 */ {{1, 1}, {{1, 1024, 10, 10}}, 160, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 32784000.}, + /* GFLOPS 0.032 x 1 = 0.032 */ {{1, 1}, {{1, 160, 28, 28}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 32212992.}, + /* GFLOPS 0.032 x 1 = 0.032 */ {{1, 1}, {{1, 512, 14, 14}}, 160, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 32144000.}, + /* GFLOPS 0.032 x 1 = 0.032 */ {{1, 1}, {{1, 640, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 32137728.}, + /* GFLOPS 0.032 x 1 = 0.032 */ {{1, 1}, {{1, 508, 14, 14}}, 160, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 31893120.}, + /* GFLOPS 0.031 x 1 = 0.031 */ {{1, 1}, {{1, 832, 7, 7}}, 384, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 31328640.}, + /* GFLOPS 0.031 x 1 = 0.031 */ {{1, 1}, {{1, 832, 7, 7}}, 384, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 31328640.}, + /* GFLOPS 0.031 x 1 = 0.031 */ {{1, 1}, {{1, 608, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 30532096.}, + /* GFLOPS 0.015 x 2 = 0.030 */ {{5, 5}, {{1, 24, 14, 14}}, 64, 1, {1, 1}, {1, 1}, {2, 2}, {0, 0}, "", true, 15065344.}, + /* GFLOPS 0.015 x 2 = 0.030 */ {{5, 5}, {{1, 24, 14, 14}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 15065344.}, + /* GFLOPS 0.015 x 2 = 0.030 */ {{5, 5}, {{1, 48, 7, 7}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 15059072.}, + /* GFLOPS 0.029 x 1 = 0.029 */ {{3, 3}, {{1, 256, 10, 10}}, 256, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 29497600.}, + /* GFLOPS 0.029 x 1 = 0.029 */ {{1, 1}, {{1, 192, 28, 28}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 28976640.}, + /* GFLOPS 0.029 x 1 = 0.029 */ {{1, 1}, {{1, 192, 28, 28}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 28976640.}, + /* GFLOPS 0.029 x 1 = 0.029 */ {{1, 1}, {{1, 512, 14, 14}}, 144, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 28929600.}, + /* GFLOPS 0.029 x 1 = 0.029 */ {{1, 1}, {{1, 512, 14, 14}}, 144, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 28929600.}, + /* GFLOPS 0.029 x 1 = 0.029 */ {{1, 1}, {{1, 576, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 28926464.}, + /* GFLOPS 0.027 x 1 = 0.027 */ {{1, 1}, {{1, 544, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 27320832.}, + /* GFLOPS 0.027 x 1 = 0.027 */ {{1, 1}, {{1, 384, 19, 19}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 26650464.}, + /* GFLOPS 0.027 x 1 = 0.027 */ {{1, 1}, {{1, 576, 19, 19}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 26638912.}, + /* GFLOPS 0.027 x 1 = 0.027 */ {{3, 3}, {{1, 128, 38, 38}}, 8, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 26627360.}, + /* GFLOPS 0.027 x 1 = 0.027 */ {{1, 1}, {{1, 528, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 26518016.}, + /* GFLOPS 0.027 x 1 = 0.027 */ {{1, 1}, {{1, 528, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 26518016.}, + /* GFLOPS 0.026 x 1 = 0.026 */ {{1, 1}, {{1, 96, 75, 75}}, 24, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 26055000.}, + /* GFLOPS 0.026 x 1 = 0.026 */ {{1, 1}, {{1, 64, 56, 56}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "VALID", true, 25890816.}, + /* GFLOPS 0.026 x 1 = 0.026 */ {{1, 1}, {{1, 64, 56, 56}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 25890816.}, + /* GFLOPS 0.026 x 1 = 0.026 */ {{1, 1}, {{1, 64, 56, 56}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 25890816.}, + /* GFLOPS 0.026 x 1 = 0.026 */ {{1, 1}, {{1, 1024, 10, 10}}, 126, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 25817400.}, + /* GFLOPS 0.026 x 1 = 0.026 */ {{1, 1}, {{1, 128, 28, 28}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 25790464.}, + /* GFLOPS 0.026 x 1 = 0.026 */ {{1, 1}, {{1, 256, 28, 28}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 25740288.}, + /* GFLOPS 0.026 x 1 = 0.026 */ {{1, 1}, {{1, 256, 28, 28}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 25740288.}, + /* GFLOPS 0.013 x 2 = 0.026 */ {{1, 1}, {{1, 256, 28, 28}}, 32, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 12870144.}, + /* GFLOPS 0.026 x 1 = 0.026 */ {{1, 1}, {{1, 512, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 25715200.}, + /* GFLOPS 0.013 x 2 = 0.026 */ {{1, 1}, {{1, 512, 14, 14}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 12857600.}, + /* GFLOPS 0.024 x 1 = 0.024 */ {{1, 1}, {{1, 480, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 24109568.}, + /* GFLOPS 0.024 x 1 = 0.024 */ {{1, 1}, {{1, 128, 38, 38}}, 256, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "", false, 23750912.}, + /* GFLOPS 0.024 x 1 = 0.024 */ {{1, 1}, {{1, 256, 19, 19}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 23704704.}, + /* GFLOPS 0.023 x 1 = 0.023 */ {{3, 3}, {{1, 3, 256, 512}}, 13, 1, {2, 2}, {1, 1}, {1, 1}, {0, 0}, "", true, 23429120.}, + /* GFLOPS 0.023 x 1 = 0.023 */ {{1, 1}, {{1, 32, 150, 150}}, 16, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 23400000.}, + /* GFLOPS 0.023 x 1 = 0.023 */ {{1, 1}, {{1, 512, 19, 19}}, 63, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 23311575.}, + /* GFLOPS 0.023 x 1 = 0.023 */ {{1, 1}, {{1, 448, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 22503936.}, + /* GFLOPS 0.023 x 1 = 0.023 */ {{1, 1}, {{1, 512, 14, 14}}, 112, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 22500800.}, + /* GFLOPS 0.022 x 1 = 0.022 */ {{1, 1}, {{1, 508, 14, 14}}, 112, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 22325184.}, + /* GFLOPS 0.021 x 1 = 0.021 */ {{3, 3}, {{1, 128, 12, 12}}, 256, 1, {2, 2}, {1, 1}, {1, 1}, {0, 0}, "", true, 21242880.}, + /* GFLOPS 0.021 x 1 = 0.021 */ {{1, 1}, {{1, 416, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 20898304.}, + /* GFLOPS 0.021 x 1 = 0.021 */ {{1, 1}, {{1, 832, 7, 7}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 20885760.}, + /* GFLOPS 0.021 x 1 = 0.021 */ {{1, 1}, {{1, 832, 7, 7}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 20885760.}, + /* GFLOPS 0.010 x 2 = 0.021 */ {{1, 1}, {{1, 832, 7, 7}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 10442880.}, + /* GFLOPS 0.010 x 2 = 0.021 */ {{1, 1}, {{1, 832, 7, 7}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 10442880.}, + /* GFLOPS 0.010 x 2 = 0.020 */ {{3, 3}, {{1, 256, 2, 2}}, 546, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 10066056.}, + /* GFLOPS 0.020 x 1 = 0.020 */ {{5, 5}, {{1, 16, 28, 28}}, 32, 1, {1, 1}, {1, 1}, {2, 2}, {0, 0}, "", true, 20095488.}, + /* GFLOPS 0.020 x 1 = 0.020 */ {{5, 5}, {{1, 16, 28, 28}}, 32, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 20095488.}, + /* GFLOPS 0.020 x 1 = 0.020 */ {{5, 5}, {{1, 32, 14, 14}}, 64, 1, {1, 1}, {1, 1}, {2, 2}, {0, 0}, "", true, 20082944.}, + /* GFLOPS 0.020 x 1 = 0.020 */ {{5, 5}, {{1, 32, 14, 14}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 20082944.}, + /* GFLOPS 0.020 x 1 = 0.020 */ {{3, 3}, {{1, 256, 19, 19}}, 12, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 19966188.}, + /* GFLOPS 0.019 x 1 = 0.019 */ {{1, 1}, {{1, 192, 28, 28}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 19317760.}, + /* GFLOPS 0.019 x 1 = 0.019 */ {{1, 1}, {{1, 192, 28, 28}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 19317760.}, + /* GFLOPS 0.019 x 1 = 0.019 */ {{1, 1}, {{1, 384, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 19292672.}, + /* GFLOPS 0.018 x 1 = 0.018 */ {{1, 1}, {{1, 576, 10, 10}}, 160, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 18448000.}, + /* GFLOPS 0.018 x 1 = 0.018 */ {{1, 1}, {{1, 480, 14, 14}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 18082176.}, + /* GFLOPS 0.018 x 1 = 0.018 */ {{1, 1}, {{1, 480, 14, 14}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 18082176.}, + /* GFLOPS 0.018 x 1 = 0.018 */ {{1, 1}, {{1, 192, 38, 38}}, 32, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 17790080.}, + /* GFLOPS 0.018 x 1 = 0.018 */ {{1, 1}, {{1, 352, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 17687040.}, + /* GFLOPS 0.017 x 1 = 0.017 */ {{2, 2}, {{1, 16, 128, 256}}, 16, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "", false, 16908288.}, + /* GFLOPS 0.016 x 1 = 0.016 */ {{1, 1}, {{1, 320, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 16081408.}, + /* GFLOPS 0.016 x 1 = 0.016 */ {{1, 1}, {{1, 832, 7, 7}}, 192, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 15664320.}, + /* GFLOPS 0.016 x 1 = 0.016 */ {{1, 1}, {{1, 832, 7, 7}}, 192, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 15664320.}, + /* GFLOPS 0.015 x 1 = 0.015 */ {{5, 5}, {{1, 48, 7, 7}}, 128, 1, {1, 1}, {1, 1}, {2, 2}, {0, 0}, "", true, 15059072.}, + /* GFLOPS 0.015 x 1 = 0.015 */ {{5, 5}, {{1, 32, 12, 12}}, 64, 1, {1, 1}, {1, 1}, {2, 2}, {0, 0}, "", true, 14754816.}, + /* GFLOPS 0.014 x 1 = 0.014 */ {{1, 1}, {{1, 288, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 14475776.}, + /* GFLOPS 0.014 x 1 = 0.014 */ {{1, 1}, {{1, 512, 5, 5}}, 546, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 13991250.}, + /* GFLOPS 0.013 x 1 = 0.013 */ {{1, 1}, {{1, 144, 38, 38}}, 32, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 13354112.}, + /* GFLOPS 0.007 x 2 = 0.013 */ {{1, 1}, {{1, 16, 56, 56}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 6623232.}, + /* GFLOPS 0.013 x 1 = 0.013 */ {{1, 1}, {{1, 832, 7, 7}}, 160, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 13053600.}, + /* GFLOPS 0.013 x 1 = 0.013 */ {{1, 1}, {{1, 832, 7, 7}}, 160, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 13053600.}, + /* GFLOPS 0.007 x 2 = 0.013 */ {{1, 1}, {{1, 32, 28, 28}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 6522880.}, + /* GFLOPS 0.006 x 2 = 0.013 */ {{1, 1}, {{1, 64, 14, 14}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 6472704.}, + /* GFLOPS 0.013 x 1 = 0.013 */ {{1, 1}, {{1, 128, 56, 56}}, 16, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 12895232.}, + /* GFLOPS 0.013 x 1 = 0.013 */ {{1, 1}, {{1, 256, 28, 28}}, 32, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 12870144.}, + /* GFLOPS 0.013 x 1 = 0.013 */ {{1, 1}, {{1, 256, 14, 14}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 12870144.}, + /* GFLOPS 0.013 x 1 = 0.013 */ {{1, 1}, {{1, 508, 14, 14}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 12757248.}, + /* GFLOPS 0.012 x 1 = 0.012 */ {{1, 1}, {{1, 992, 7, 7}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 12449920.}, + /* GFLOPS 0.012 x 1 = 0.012 */ {{1, 1}, {{1, 480, 14, 14}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 12054784.}, + /* GFLOPS 0.012 x 1 = 0.012 */ {{1, 1}, {{1, 480, 14, 14}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 12054784.}, + /* GFLOPS 0.012 x 1 = 0.012 */ {{1, 1}, {{1, 960, 7, 7}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 12048512.}, + /* GFLOPS 0.012 x 1 = 0.012 */ {{1, 1}, {{1, 32, 75, 75}}, 128, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "", false, 12014080.}, + /* GFLOPS 0.012 x 1 = 0.012 */ {{3, 3}, {{1, 96, 6, 6}}, 192, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 11950848.}, + /* GFLOPS 0.006 x 2 = 0.012 */ {{3, 3}, {{1, 96, 3, 3}}, 384, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 5975424.}, + /* GFLOPS 0.012 x 1 = 0.012 */ {{1, 1}, {{1, 320, 12, 12}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 11814912.}, + /* GFLOPS 0.012 x 1 = 0.012 */ {{1, 1}, {{1, 640, 6, 6}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 11805696.}, + /* GFLOPS 0.012 x 1 = 0.012 */ {{1, 1}, {{1, 928, 7, 7}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 11647104.}, + /* GFLOPS 0.011 x 1 = 0.011 */ {{1, 1}, {{1, 896, 7, 7}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 11245696.}, + /* GFLOPS 0.011 x 1 = 0.011 */ {{3, 3}, {{1, 256, 10, 10}}, 24, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 11061600.}, + /* GFLOPS 0.006 x 2 = 0.011 */ {{3, 3}, {{1, 512, 5, 5}}, 24, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 5530200.}, + /* GFLOPS 0.011 x 1 = 0.011 */ {{1, 1}, {{1, 864, 7, 7}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 10844288.}, + /* GFLOPS 0.010 x 1 = 0.010 */ {{1, 1}, {{1, 832, 7, 7}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 10442880.}, + /* GFLOPS 0.010 x 1 = 0.010 */ {{5, 5}, {{1, 32, 7, 7}}, 128, 1, {1, 1}, {1, 1}, {2, 2}, {0, 0}, "", true, 10041472.}, + /* GFLOPS 0.010 x 1 = 0.010 */ {{1, 1}, {{1, 800, 7, 7}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 10041472.}, + /* GFLOPS 0.010 x 1 = 0.010 */ {{1, 1}, {{1, 192, 28, 28}}, 32, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 9658880.}, + /* GFLOPS 0.010 x 1 = 0.010 */ {{1, 1}, {{1, 192, 28, 28}}, 32, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 9658880.}, + /* GFLOPS 0.010 x 1 = 0.010 */ {{1, 1}, {{1, 384, 14, 14}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 9646336.}, + /* GFLOPS 0.005 x 2 = 0.010 */ {{1, 1}, {{1, 512, 14, 14}}, 24, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 4821600.}, + /* GFLOPS 0.010 x 1 = 0.010 */ {{1, 1}, {{1, 768, 7, 7}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 9640064.}, + /* GFLOPS 0.010 x 1 = 0.010 */ {{3, 3}, {{1, 4, 128, 256}}, 4, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 9568256.}, + /* GFLOPS 0.005 x 2 = 0.009 */ {{1, 1}, {{1, 4, 128, 256}}, 16, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 4718592.}, + /* GFLOPS 0.009 x 1 = 0.009 */ {{1, 1}, {{1, 736, 7, 7}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 9238656.}, + /* GFLOPS 0.009 x 1 = 0.009 */ {{1, 1}, {{1, 192, 19, 19}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 8895040.}, + /* GFLOPS 0.009 x 1 = 0.009 */ {{1, 1}, {{1, 704, 7, 7}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 8837248.}, + /* GFLOPS 0.008 x 1 = 0.008 */ {{1, 1}, {{1, 672, 7, 7}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 8435840.}, + /* GFLOPS 0.008 x 1 = 0.008 */ {{1, 1}, {{1, 128, 32, 64}}, 16, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 8421376.}, + /* GFLOPS 0.008 x 1 = 0.008 */ {{1, 1}, {{1, 640, 7, 7}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 8034432.}, + /* GFLOPS 0.004 x 2 = 0.008 */ {{1, 1}, {{1, 832, 7, 7}}, 48, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 3916080.}, + /* GFLOPS 0.008 x 1 = 0.008 */ {{1, 1}, {{1, 608, 7, 7}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 7633024.}, + /* GFLOPS 0.008 x 1 = 0.008 */ {{5, 5}, {{1, 16, 14, 14}}, 48, 1, {1, 1}, {1, 1}, {2, 2}, {0, 0}, "", true, 7535808.}, + /* GFLOPS 0.008 x 1 = 0.008 */ {{5, 5}, {{1, 16, 14, 14}}, 48, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 7535808.}, + /* GFLOPS 0.004 x 2 = 0.007 */ {{3, 3}, {{1, 64, 5, 5}}, 128, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 3689600.}, + /* GFLOPS 0.007 x 1 = 0.007 */ {{1, 1}, {{1, 640, 6, 6}}, 160, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 7378560.}, + /* GFLOPS 0.004 x 2 = 0.007 */ {{1, 1}, {{1, 48, 14, 14}}, 192, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 3650304.}, + /* GFLOPS 0.007 x 1 = 0.007 */ {{1, 1}, {{1, 384, 14, 14}}, 48, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 7234752.}, + /* GFLOPS 0.007 x 1 = 0.007 */ {{1, 1}, {{1, 576, 7, 7}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 7231616.}, + /* GFLOPS 0.007 x 1 = 0.007 */ {{1, 1}, {{1, 256, 12, 12}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 7091712.}, + /* GFLOPS 0.007 x 1 = 0.007 */ {{1, 1}, {{1, 544, 7, 7}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 6830208.}, + /* GFLOPS 0.007 x 1 = 0.007 */ {{3, 3}, {{1, 160, 6, 6}}, 256, 1, {2, 2}, {1, 1}, {1, 1}, {0, 0}, "", true, 6637824.}, + /* GFLOPS 0.007 x 1 = 0.007 */ {{1, 1}, {{1, 528, 14, 14}}, 32, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 6629504.}, + /* GFLOPS 0.007 x 1 = 0.007 */ {{1, 1}, {{1, 528, 14, 14}}, 32, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 6629504.}, + /* GFLOPS 0.007 x 1 = 0.007 */ {{1, 1}, {{1, 256, 5, 5}}, 512, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 6566400.}, + /* GFLOPS 0.003 x 2 = 0.007 */ {{1, 1}, {{1, 512, 5, 5}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 3280000.}, + /* GFLOPS 0.006 x 1 = 0.006 */ {{1, 1}, {{1, 64, 56, 56}}, 16, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 6472704.}, + /* GFLOPS 0.006 x 1 = 0.006 */ {{1, 1}, {{1, 128, 28, 28}}, 32, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 6447616.}, + /* GFLOPS 0.006 x 1 = 0.006 */ {{1, 1}, {{1, 512, 7, 7}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 6428800.}, + /* GFLOPS 0.006 x 1 = 0.006 */ {{1, 1}, {{1, 512, 14, 14}}, 32, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 6428800.}, + /* GFLOPS 0.006 x 1 = 0.006 */ {{1, 1}, {{1, 512, 14, 14}}, 32, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 6428800.}, + /* GFLOPS 0.006 x 1 = 0.006 */ {{3, 3}, {{1, 256, 10, 10}}, 12, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 5530800.}, + /* GFLOPS 0.005 x 1 = 0.005 */ {{1, 1}, {{1, 192, 12, 12}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 5322240.}, + /* GFLOPS 0.005 x 1 = 0.005 */ {{3, 3}, {{1, 128, 5, 5}}, 256, 1, {2, 2}, {1, 1}, {1, 1}, {0, 0}, "", true, 5310720.}, + /* GFLOPS 0.005 x 1 = 0.005 */ {{3, 3}, {{1, 128, 5, 5}}, 256, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 5310720.}, + /* GFLOPS 0.005 x 1 = 0.005 */ {{3, 3}, {{1, 128, 5, 5}}, 256, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 5310720.}, + /* GFLOPS 0.005 x 1 = 0.005 */ {{1, 1}, {{1, 1024, 10, 10}}, 24, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 4917600.}, + /* GFLOPS 0.005 x 1 = 0.005 */ {{1, 1}, {{1, 1024, 10, 10}}, 24, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 4917600.}, + /* GFLOPS 0.005 x 1 = 0.005 */ {{1, 1}, {{1, 192, 28, 28}}, 16, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 4829440.}, + /* GFLOPS 0.005 x 1 = 0.005 */ {{1, 1}, {{1, 192, 28, 28}}, 16, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 4829440.}, + /* GFLOPS 0.005 x 1 = 0.005 */ {{1, 1}, {{1, 256, 14, 14}}, 48, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 4826304.}, + /* GFLOPS 0.005 x 1 = 0.005 */ {{1, 1}, {{1, 512, 14, 14}}, 24, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 4821600.}, + /* GFLOPS 0.005 x 1 = 0.005 */ {{1, 1}, {{1, 508, 14, 14}}, 24, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 4783968.}, + /* GFLOPS 0.005 x 1 = 0.005 */ {{1, 1}, {{1, 64, 24, 24}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 4755456.}, + /* GFLOPS 0.005 x 1 = 0.005 */ {{1, 1}, {{1, 256, 12, 12}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 4727808.}, + /* GFLOPS 0.005 x 1 = 0.005 */ {{1, 1}, {{1, 1024, 3, 3}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 4720896.}, + /* GFLOPS 0.004 x 1 = 0.004 */ {{1, 1}, {{1, 512, 19, 19}}, 12, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 4440300.}, + /* GFLOPS 0.004 x 1 = 0.004 */ {{1, 1}, {{1, 512, 19, 19}}, 12, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 4440300.}, + /* GFLOPS 0.004 x 1 = 0.004 */ {{1, 1}, {{1, 640, 6, 6}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 4427136.}, + /* GFLOPS 0.004 x 1 = 0.004 */ {{1, 1}, {{1, 16, 128, 256}}, 4, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 4325376.}, + /* GFLOPS 0.004 x 1 = 0.004 */ {{1, 1}, {{1, 64, 64, 128}}, 4, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", false, 4227072.}, + /* GFLOPS 0.004 x 1 = 0.004 */ {{1, 1}, {{1, 832, 7, 7}}, 48, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 3916080.}, + /* GFLOPS 0.004 x 1 = 0.004 */ {{5, 5}, {{1, 16, 12, 12}}, 32, 1, {1, 1}, {1, 1}, {2, 2}, {0, 0}, "", true, 3691008.}, + /* GFLOPS 0.004 x 1 = 0.004 */ {{3, 3}, {{1, 64, 10, 10}}, 128, 1, {2, 2}, {1, 1}, {1, 1}, {0, 0}, "", true, 3689600.}, + /* GFLOPS 0.004 x 1 = 0.004 */ {{5, 5}, {{1, 32, 6, 6}}, 64, 1, {1, 1}, {1, 1}, {2, 2}, {0, 0}, "", true, 3688704.}, + /* GFLOPS 0.004 x 1 = 0.004 */ {{5, 5}, {{1, 32, 12, 12}}, 64, 1, {2, 2}, {1, 1}, {2, 2}, {0, 0}, "", true, 3688704.}, + /* GFLOPS 0.004 x 1 = 0.004 */ {{5, 5}, {{1, 64, 6, 6}}, 128, 1, {2, 2}, {1, 1}, {2, 2}, {0, 0}, "", true, 3687552.}, + /* GFLOPS 0.004 x 1 = 0.004 */ {{1, 1}, {{1, 192, 12, 12}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 3548160.}, + /* GFLOPS 0.003 x 1 = 0.003 */ {{1, 1}, {{1, 736, 3, 3}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 3393792.}, + /* GFLOPS 0.003 x 1 = 0.003 */ {{1, 1}, {{1, 256, 10, 10}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 3283200.}, + /* GFLOPS 0.003 x 1 = 0.003 */ {{1, 1}, {{1, 512, 5, 5}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 3280000.}, + /* GFLOPS 0.003 x 1 = 0.003 */ {{1, 1}, {{1, 512, 5, 5}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 3280000.}, + /* GFLOPS 0.003 x 1 = 0.003 */ {{1, 1}, {{1, 512, 5, 5}}, 126, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 3228750.}, + /* GFLOPS 0.003 x 1 = 0.003 */ {{1, 1}, {{1, 480, 14, 14}}, 16, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 3013696.}, + /* GFLOPS 0.003 x 1 = 0.003 */ {{1, 1}, {{1, 480, 14, 14}}, 16, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 3013696.}, + /* GFLOPS 0.003 x 1 = 0.003 */ {{1, 1}, {{1, 320, 12, 12}}, 32, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 2953728.}, + /* GFLOPS 0.003 x 1 = 0.003 */ {{1, 1}, {{1, 640, 6, 6}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 2951424.}, + /* GFLOPS 0.003 x 1 = 0.003 */ {{3, 3}, {{1, 128, 5, 5}}, 128, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 2655360.}, + /* GFLOPS 0.003 x 1 = 0.003 */ {{1, 1}, {{1, 832, 7, 7}}, 32, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 2610720.}, + /* GFLOPS 0.003 x 1 = 0.003 */ {{1, 1}, {{1, 256, 3, 3}}, 546, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 2520882.}, + /* GFLOPS 0.001 x 2 = 0.003 */ {{3, 3}, {{1, 128, 1, 1}}, 546, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 1258530.}, + /* GFLOPS 0.002 x 1 = 0.002 */ {{1, 1}, {{1, 256, 12, 12}}, 32, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 2363904.}, + /* GFLOPS 0.002 x 1 = 0.002 */ {{3, 3}, {{1, 128, 3, 3}}, 256, 1, {2, 2}, {1, 1}, {1, 1}, {0, 0}, "", true, 2360320.}, + /* GFLOPS 0.002 x 1 = 0.002 */ {{3, 3}, {{1, 128, 3, 3}}, 256, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 2360320.}, + /* GFLOPS 0.002 x 1 = 0.002 */ {{3, 3}, {{1, 128, 3, 3}}, 256, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 2360320.}, + /* GFLOPS 0.002 x 1 = 0.002 */ {{1, 1}, {{1, 528, 4, 4}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 2164736.}, + /* GFLOPS 0.002 x 1 = 0.002 */ {{1, 1}, {{1, 508, 4, 4}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 2082816.}, + /* GFLOPS 0.002 x 1 = 0.002 */ {{1, 1}, {{1, 1024, 1, 1}}, 1000, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 2049000.}, + /* GFLOPS 0.001 x 2 = 0.002 */ {{3, 3}, {{1, 256, 3, 3}}, 24, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 995544.}, + /* GFLOPS 0.001 x 2 = 0.002 */ {{3, 3}, {{1, 128, 5, 5}}, 16, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 922000.}, + /* GFLOPS 0.002 x 1 = 0.002 */ {{1, 1}, {{1, 1024, 3, 3}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 1770336.}, + /* GFLOPS 0.001 x 1 = 0.001 */ {{1, 1}, {{1, 640, 6, 6}}, 32, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 1475712.}, + /* GFLOPS 0.001 x 1 = 0.001 */ {{3, 3}, {{1, 128, 5, 5}}, 24, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 1383000.}, + /* GFLOPS 0.001 x 1 = 0.001 */ {{1, 1}, {{1, 736, 3, 3}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 1272672.}, + /* GFLOPS 0.001 x 2 = 0.001 */ {{1, 1}, {{1, 256, 3, 3}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 590976.}, + /* GFLOPS 0.001 x 1 = 0.001 */ {{3, 3}, {{1, 128, 3, 3}}, 128, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 1180160.}, + /* GFLOPS 0.001 x 1 = 0.001 */ {{1, 1}, {{1, 256, 2, 2}}, 546, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 1120392.}, + /* GFLOPS 0.000 x 2 = 0.001 */ {{3, 3}, {{1, 128, 5, 5}}, 8, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 461000.}, + /* GFLOPS 0.001 x 1 = 0.001 */ {{1, 1}, {{1, 192, 12, 12}}, 16, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 887040.}, + /* GFLOPS 0.000 x 2 = 0.001 */ {{3, 3}, {{1, 256, 2, 2}}, 24, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 442464.}, + /* GFLOPS 0.000 x 2 = 0.001 */ {{1, 1}, {{1, 128, 5, 5}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 411200.}, + /* GFLOPS 0.001 x 1 = 0.001 */ {{3, 3}, {{1, 128, 5, 5}}, 12, 1, {1, 1}, {1, 1}, {1, 1}, {0, 0}, "", true, 691500.}, + /* GFLOPS 0.001 x 1 = 0.001 */ {{1, 1}, {{1, 640, 2, 2}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 655872.}, + /* GFLOPS 0.001 x 1 = 0.001 */ {{1, 1}, {{1, 512, 5, 5}}, 24, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 615000.}, + /* GFLOPS 0.001 x 1 = 0.001 */ {{1, 1}, {{1, 512, 5, 5}}, 24, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 615000.}, + /* GFLOPS 0.001 x 1 = 0.001 */ {{1, 1}, {{1, 128, 3, 3}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 592128.}, + /* GFLOPS 0.001 x 1 = 0.001 */ {{1, 1}, {{1, 256, 3, 3}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 590976.}, + /* GFLOPS 0.001 x 1 = 0.001 */ {{1, 1}, {{1, 256, 3, 3}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 590976.}, + /* GFLOPS 0.001 x 1 = 0.001 */ {{1, 1}, {{1, 256, 3, 3}}, 126, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 581742.}, + /* GFLOPS 0.001 x 1 = 0.001 */ {{1, 1}, {{1, 256, 4, 4}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 525312.}, + /* GFLOPS 0.000 x 1 = 0.000 */ {{1, 1}, {{1, 192, 5, 5}}, 32, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 308000.}, + /* GFLOPS 0.000 x 1 = 0.000 */ {{1, 1}, {{1, 128, 2, 2}}, 256, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 263168.}, + /* GFLOPS 0.000 x 2 = 0.000 */ {{1, 1}, {{1, 256, 2, 2}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 131328.}, + /* GFLOPS 0.000 x 1 = 0.000 */ {{1, 1}, {{1, 256, 2, 2}}, 126, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 258552.}, + /* GFLOPS 0.000 x 1 = 0.000 */ {{1, 1}, {{1, 1024, 1, 1}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 196704.}, + /* GFLOPS 0.000 x 1 = 0.000 */ {{3, 3}, {{1, 64, 2, 2}}, 128, 1, {2, 2}, {1, 1}, {1, 1}, {0, 0}, "", true, 147584.}, + /* GFLOPS 0.000 x 1 = 0.000 */ {{3, 3}, {{1, 64, 2, 2}}, 128, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 147584.}, + /* GFLOPS 0.000 x 1 = 0.000 */ {{3, 3}, {{1, 64, 2, 2}}, 128, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 147584.}, + /* GFLOPS 0.000 x 1 = 0.000 */ {{1, 1}, {{1, 736, 1, 1}}, 96, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 141408.}, + /* GFLOPS 0.000 x 1 = 0.000 */ {{1, 1}, {{1, 128, 1, 1}}, 546, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 140322.}, + /* GFLOPS 0.000 x 1 = 0.000 */ {{1, 1}, {{1, 256, 2, 2}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 131328.}, + /* GFLOPS 0.000 x 1 = 0.000 */ {{1, 1}, {{1, 256, 2, 2}}, 64, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 131328.}, + /* GFLOPS 0.000 x 1 = 0.000 */ {{1, 1}, {{1, 256, 3, 3}}, 24, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 110808.}, + /* GFLOPS 0.000 x 1 = 0.000 */ {{1, 1}, {{1, 256, 3, 3}}, 24, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 110808.}, + /* GFLOPS 0.000 x 2 = 0.000 */ {{3, 3}, {{1, 128, 1, 1}}, 24, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 55320.}, + /* GFLOPS 0.000 x 1 = 0.000 */ {{3, 3}, {{1, 64, 2, 2}}, 64, 1, {2, 2}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 73792.}, + /* GFLOPS 0.000 x 1 = 0.000 */ {{1, 1}, {{1, 256, 2, 2}}, 24, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 49248.}, + /* GFLOPS 0.000 x 1 = 0.000 */ {{1, 1}, {{1, 256, 2, 2}}, 24, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 49248.}, + /* GFLOPS 0.000 x 1 = 0.000 */ {{1, 1}, {{1, 128, 1, 1}}, 126, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 32382.}, + /* GFLOPS 0.000 x 1 = 0.000 */ {{1, 1}, {{1, 64, 1, 1}}, 128, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", false, 16512.}, + /* GFLOPS 0.000 x 1 = 0.000 */ {{1, 1}, {{1, 128, 1, 1}}, 24, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "", true, 6168.}, + /* GFLOPS 0.000 x 1 = 0.000 */ {{1, 1}, {{1, 128, 1, 1}}, 24, 1, {1, 1}, {1, 1}, {0, 0}, {0, 0}, "SAME", true, 6168.} +}; +struct ConvParamID { - int data[] = {count, nplanes, height, width}; - return MatShape(data, data+4); + enum { + CONV_0 = 0, + CONV_100 = 100, + CONV_LAST = sizeof(testConvolutionConfigs) / sizeof(testConvolutionConfigs[0]) + }; + int val_; \ + ConvParamID(int val = 0) : val_(val) {} + operator int() const { return val_; } + static ::testing::internal::ParamGenerator all() + { +#if 0 + enum { NUM = (int)CONV_LAST }; +#else + enum { NUM = (int)CONV_100 }; +#endif + ConvParamID v_[NUM]; for (int i = 0; i < NUM; ++i) { v_[i] = ConvParamID(i); } // reduce generated code size + return ::testing::ValuesIn(v_, v_ + NUM); + } +}; \ +static inline void PrintTo(const ConvParamID& v, std::ostream* os) +{ + CV_Assert((int)v >= 0); CV_Assert((int)v < ConvParamID::CONV_LAST); + const ConvParam_t& p = testConvolutionConfigs[(int)v]; + + *os << "GFLOPS=" << cv::format("%.3f", p.declared_flops * 1e-9) + << ", K=" << (Size)p.kernel + << ", IN={" << p.shapeIn.dims[0] << ", " << p.shapeIn.dims[1] << ", " << p.shapeIn.dims[2] << ", " << p.shapeIn.dims[3] << "}" + << ", OCN=" << p.outCN; + if (p.groups > 1) + *os << ", G=" << p.groups; + if (((Size)p.stride).area() != 1) + *os << ", S=" << ((Size)p.stride); + if (((Size)p.dilation).area() != 1) + *os << ", D=" << ((Size)p.dilation); + if (((Size)p.pad).area() != 0) + *os << ", P=" << ((Size)p.pad); + if (((Size)p.padAdjust).area() != 0) + *os << ", PAdj=" << ((Size)p.padAdjust); + if (!((std::string)p.padMode).empty()) + *os << ", PM=" << ((std::string)p.padMode); + if (p.hasBias) + *os << ", BIAS"; } -PERF_TEST_P( ConvolutionPerfTest, perf, Combine( - Values(Size(1, 1), Size(3, 3), Size(5, 5), Size(11, 11)), - Values(make_pair(blobShape(1, 4, 224, 224), 64), - make_pair(blobShape(1, 64, 112, 122), 128), - make_pair(blobShape(1, 256, 28, 28), 512)), - GroupSize::all(), - StrideSize::all()) -) + + +typedef tuple > ConvTestParam_t; +typedef TestBaseWithParam Conv; + +PERF_TEST_P_(Conv, conv) { - RNG rng(0); + int test_id = (int)get<0>(GetParam()); + ASSERT_GE(test_id, 0); ASSERT_LT(test_id, ConvParamID::CONV_LAST); + const ConvParam_t& params = testConvolutionConfigs[test_id]; + double declared_flops = params.declared_flops; + Size kernel = params.kernel; + MatShape inputShape = MatShape(params.shapeIn.dims, params.shapeIn.dims + 4); + int outChannels = params.outCN; + int groups = params.groups; + Size stride = params.stride; + Size dilation = params.dilation; + Size pad = params.pad; + Size padAdjust = params.padAdjust; + std::string padMode(params.padMode); + bool hasBias = params.hasBias; + Backend backendId = get<0>(get<1>(GetParam())); + Target targetId = get<1>(get<1>(GetParam())); - ConvParam params = GetParam(); - int ksz = get<0>(params).width; - MatShape inpShape = get<1>(params).first; - int outCn = get<1>(params).second; - int groups = get<2>(params); - int stride = (ksz >= 11) ? 4 : (int)get<3>(params); + int inChannels = inputShape[1]; + Size inSize(inputShape[3], inputShape[2]); - int inpCn = inpShape[1]; - int wgtSize[] = { outCn, inpCn/groups, ksz, ksz }; - int biasSize[] = { outCn, 1, 1, 1 }; - const int wtype = CV_32F; - Mat wgtBlob(4, wgtSize, wtype), biasBlob(4, biasSize, wtype); - Mat inpBlob(4, &inpShape[0], wtype); - rng.fill(biasBlob, RNG::UNIFORM, -1, +1); - rng.fill(wgtBlob, RNG::UNIFORM, -1, +1); - rng.fill(inpBlob, RNG::UNIFORM, -1, +1); + int sz[] = {outChannels, inChannels / groups, kernel.height, kernel.width}; + Mat weights(4, &sz[0], CV_32F); + randu(weights, -1.0f, 1.0f); LayerParams lp; - lp.set("num_output", outCn); + lp.set("kernel_w", kernel.width); + lp.set("kernel_h", kernel.height); + lp.set("pad_w", pad.width); + lp.set("pad_h", pad.height); + if (padAdjust.width > 0 || padAdjust.height > 0) + { + lp.set("adj_w", padAdjust.width); + lp.set("adj_h", padAdjust.height); + } + if (!padMode.empty()) + lp.set("pad_mode", padMode); + lp.set("stride_w", stride.width); + lp.set("stride_h", stride.height); + lp.set("dilation_w", dilation.width); + lp.set("dilation_h", dilation.height); + lp.set("num_output", outChannels); lp.set("group", groups); - lp.set("stride", stride); - lp.set("kernel_size", ksz); - lp.blobs.reserve(2); - lp.blobs.push_back(wgtBlob); - lp.blobs.push_back(biasBlob); - - std::vector inpBlobs(1, &inpBlob); - std::vector outBlobs, internalBlobs; - - Ptr layer = cv::dnn::LayerFactory::createLayerInstance("Convolution", lp); - std::vector inputShapes(1, shape(inpBlob)), outShapes, internals; - layer->getMemoryShapes(inputShapes, 0, outShapes, internals); - for (size_t i = 0; i < outShapes.size(); i++) + lp.set("bias_term", hasBias); + lp.type = "Convolution"; + lp.name = "testLayer"; + lp.blobs.push_back(weights); + if (hasBias) { - outBlobs.push_back(Mat(outShapes[i], CV_32F)); + Mat bias(1, outChannels, CV_32F); + randu(bias, -1.0f, 1.0f); + lp.blobs.push_back(bias); } - for (size_t i = 0; i < internals.size(); i++) + int inpSz[] = {1, inChannels, inSize.height, inSize.width}; + Mat input(4, &inpSz[0], CV_32F); + randu(input, -1.0f, 1.0f); + + Net net; + net.addLayerToPrev(lp.name, lp.type, lp); + + net.setInput(input); + net.setPreferableBackend(backendId); + net.setPreferableTarget(targetId); + + // warmup + Mat output = net.forward(); + + MatShape netInputShape = shape(input); + size_t weightsMemory = 0, blobsMemory = 0; + net.getMemoryConsumption(netInputShape, weightsMemory, blobsMemory); + int64 flops = net.getFLOPS(netInputShape); + CV_Assert(flops > 0); + + std::cout + << "IN=" << divUp(input.total() * input.elemSize(), 1u<<10) << " Kb " << netInputShape + << " OUT=" << divUp(output.total() * output.elemSize(), 1u<<10) << " Kb " << shape(output) + << " Weights(parameters): " << divUp(weightsMemory, 1u<<10) << " Kb" + << " MFLOPS=" << flops * 1e-6 << std::endl; + + TEST_CYCLE() { - internalBlobs.push_back(Mat()); - if (total(internals[i])) - internalBlobs.back().create(internals[i], CV_32F); + Mat res = net.forward(); } - layer->finalize(inpBlobs, outBlobs); - - Mat inpBlob2D = inpBlob.reshape(1, outCn); - Mat wgtBlob2D = wgtBlob.reshape(1, outCn*(inpCn/groups)); - Mat outBlob2D = outBlobs[0].reshape(1, outBlobs[0].size[0]); - declare.in(inpBlob2D, wgtBlob2D, WARMUP_RNG).out(outBlob2D); - - layer->forward(inpBlobs, outBlobs, internalBlobs); /// warmup - - PERF_SAMPLE_BEGIN() - layer->forward(inpBlobs, outBlobs, internalBlobs); - PERF_SAMPLE_END() - + EXPECT_NEAR(flops, declared_flops, declared_flops * 1e-6); SANITY_CHECK_NOTHING(); } +static const tuple testBackendsAndTargets[] = { + tuple(DNN_BACKEND_OPENCV, DNN_TARGET_CPU), + tuple(DNN_BACKEND_OPENCV, DNN_TARGET_OPENCL), + tuple(DNN_BACKEND_OPENCV, DNN_TARGET_OPENCL_FP16) +}; + +INSTANTIATE_TEST_CASE_P(/**/, Conv, Combine( + ConvParamID::all(), + testing::ValuesIn(testBackendsAndTargets) +)); + } // namespace diff --git a/modules/dnn/perf/perf_precomp.hpp b/modules/dnn/perf/perf_precomp.hpp index 5e58a312fb..81816ca7ec 100644 --- a/modules/dnn/perf/perf_precomp.hpp +++ b/modules/dnn/perf/perf_precomp.hpp @@ -4,6 +4,8 @@ #include #include +#include "../test/test_common.hpp" + namespace opencv_test { using namespace perf; using namespace cv::dnn; diff --git a/modules/dnn/test/test_common.hpp b/modules/dnn/test/test_common.hpp index ec43f3e046..b752f4f5ec 100644 --- a/modules/dnn/test/test_common.hpp +++ b/modules/dnn/test/test_common.hpp @@ -42,6 +42,43 @@ #ifndef __OPENCV_TEST_COMMON_HPP__ #define __OPENCV_TEST_COMMON_HPP__ +namespace cv { namespace dnn { +CV__DNN_EXPERIMENTAL_NS_BEGIN +static inline void PrintTo(const cv::dnn::Backend& v, std::ostream* os) +{ + switch (v) { + case DNN_BACKEND_DEFAULT: *os << "DEFAULT"; return; + case DNN_BACKEND_HALIDE: *os << "HALIDE"; return; + case DNN_BACKEND_INFERENCE_ENGINE: *os << "DLIE"; return; + case DNN_BACKEND_OPENCV: *os << "OCV"; return; + } // don't use "default:" to emit compiler warnings + *os << "DNN_BACKEND_UNKNOWN(" << v << ")"; +} + +static inline void PrintTo(const cv::dnn::Target& v, std::ostream* os) +{ + switch (v) { + case DNN_TARGET_CPU: *os << "CPU"; return; + case DNN_TARGET_OPENCL: *os << "OCL"; return; + case DNN_TARGET_OPENCL_FP16: *os << "OCL_FP16"; return; + case DNN_TARGET_MYRIAD: *os << "MYRIAD"; return; + } // don't use "default:" to emit compiler warnings + *os << "DNN_TARGET_UNKNOWN(" << v << ")"; +} + +using opencv_test::tuple; +using opencv_test::get; +static inline void PrintTo(const tuple v, std::ostream* os) +{ + PrintTo(get<0>(v), os); + *os << "/"; + PrintTo(get<1>(v), os); +} + +CV__DNN_EXPERIMENTAL_NS_END +}} // namespace + + static inline const std::string &getOpenCVExtraDir() { return cvtest::TS::ptr()->get_data_path(); diff --git a/modules/dnn/test/test_precomp.hpp b/modules/dnn/test/test_precomp.hpp index a0a46ab271..0cd8b582e6 100644 --- a/modules/dnn/test/test_precomp.hpp +++ b/modules/dnn/test/test_precomp.hpp @@ -49,35 +49,6 @@ #include "opencv2/dnn.hpp" #include "test_common.hpp" -namespace cv { -namespace dnn { -CV__DNN_EXPERIMENTAL_NS_BEGIN - -static inline void PrintTo(const cv::dnn::Backend& v, std::ostream* os) -{ - switch (v) { - case DNN_BACKEND_DEFAULT: *os << "DNN_BACKEND_DEFAULT"; return; - case DNN_BACKEND_HALIDE: *os << "DNN_BACKEND_HALIDE"; return; - case DNN_BACKEND_INFERENCE_ENGINE: *os << "DNN_BACKEND_INFERENCE_ENGINE"; return; - case DNN_BACKEND_OPENCV: *os << "DNN_BACKEND_OPENCV"; return; - } // don't use "default:" to emit compiler warnings - *os << "DNN_BACKEND_UNKNOWN(" << v << ")"; -} - -static inline void PrintTo(const cv::dnn::Target& v, std::ostream* os) -{ - switch (v) { - case DNN_TARGET_CPU: *os << "DNN_TARGET_CPU"; return; - case DNN_TARGET_OPENCL: *os << "DNN_TARGET_OPENCL"; return; - case DNN_TARGET_OPENCL_FP16: *os << "DNN_TARGET_OPENCL_FP16"; return; - case DNN_TARGET_MYRIAD: *os << "DNN_TARGET_MYRIAD"; return; - } // don't use "default:" to emit compiler warnings - *os << "DNN_TARGET_UNKNOWN(" << v << ")"; -} - -CV__DNN_EXPERIMENTAL_NS_END -}} // namespace - namespace opencv_test { using namespace cv::dnn;