Time compensation is 0
TEST: Skip tests with tags: 'mem_6gb', 'verylong'
CTEST_FULL_OUTPUT
OpenCV version: 4.1.1-dev
OpenCV VCS version: 4.0.1-1379-g83b76b37c
Build type: Release
Compiler: /usr/bin/c++  (ver 7.4.0)
Parallel framework: pthreads
CPU features: NEON FP16
OpenCL is disabled
[==========] Running 270 tests from 3 test cases.
[----------] Global test environment set-up.
[----------] 200 tests from Conv
[ RUN      ] Conv.conv/0, where GetParam() = (GFLOPS=10.087, K=[3 x 3], IN={1, 576, 38, 50}, OCN=512, PM=SAME, BIAS, CUDA/CUDA)
IN=4275 Kb [ 1 576 38 50 ]    OUT=3800 Kb [ 1 512 38 50 ]    Weights(parameters): 10370 Kb    MFLOPS=10087
[ PERFSTAT ]    (samples=27   mean=51.47   median=51.86   min=48.34   stddev=1.51 (2.9%))
[       OK ] Conv.conv/0 (10283 ms)
[ RUN      ] Conv.conv/1, where GetParam() = (GFLOPS=10.087, K=[3 x 3], IN={1, 576, 38, 50}, OCN=512, PM=SAME, BIAS, OCV/CPU)
IN=4275 Kb [ 1 576 38 50 ]    OUT=3800 Kb [ 1 512 38 50 ]    Weights(parameters): 10370 Kb    MFLOPS=10087
[ PERFSTAT ]    (samples=10   mean=581.00   median=580.08   min=576.40   stddev=3.36 (0.6%))
[       OK ] Conv.conv/1 (6433 ms)
[ RUN      ] Conv.conv/2, where GetParam() = (GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, G=512, P=[1 x 1], BIAS, CUDA/CUDA)
IN=722 Kb [ 1 512 19 19 ]    OUT=722 Kb [ 1 512 19 19 ]    Weights(parameters): 20 Kb    MFLOPS=1703.6
[ PERFSTAT ]    (samples=75   mean=38.05   median=37.92   min=37.47   stddev=0.75 (2.0%))
[       OK ] Conv.conv/2 (3104 ms)
[ RUN      ] Conv.conv/3, where GetParam() = (GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, G=512, P=[1 x 1], BIAS, OCV/CPU)
IN=722 Kb [ 1 512 19 19 ]    OUT=722 Kb [ 1 512 19 19 ]    Weights(parameters): 20 Kb    MFLOPS=1703.6
[ PERFSTAT ]    (samples=10   mean=2.51   median=2.49   min=2.46   stddev=0.07 (2.6%))
[       OK ] Conv.conv/3 (42 ms)
[ RUN      ] Conv.conv/4, where GetParam() = (GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, PM=SAME, CUDA/CUDA)
IN=722 Kb [ 1 512 19 19 ]    OUT=722 Kb [ 1 512 19 19 ]    Weights(parameters): 9216 Kb    MFLOPS=1703.6
[ PERFSTAT ]    (samples=10   mean=12.87   median=12.85   min=12.66   stddev=0.15 (1.2%))
[       OK ] Conv.conv/4 (213 ms)
[ RUN      ] Conv.conv/5, where GetParam() = (GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, PM=SAME, OCV/CPU)
IN=722 Kb [ 1 512 19 19 ]    OUT=722 Kb [ 1 512 19 19 ]    Weights(parameters): 9216 Kb    MFLOPS=1703.6
[ PERFSTAT ]    (samples=10   mean=105.69   median=105.59   min=105.49   stddev=0.35 (0.3%))
[       OK ] Conv.conv/5 (1199 ms)
[ RUN      ] Conv.conv/6, where GetParam() = (GFLOPS=6.641, K=[3 x 3], IN={1, 64, 150, 200}, OCN=192, PM=SAME, BIAS, CUDA/CUDA)
IN=7500 Kb [ 1 64 150 200 ]    OUT=22500 Kb [ 1 192 150 200 ]    Weights(parameters): 433 Kb    MFLOPS=6641.28
[ PERFSTAT ]    (samples=10   mean=44.09   median=43.83   min=43.21   stddev=0.86 (2.0%))
[       OK ] Conv.conv/6 (553 ms)
[ RUN      ] Conv.conv/7, where GetParam() = (GFLOPS=6.641, K=[3 x 3], IN={1, 64, 150, 200}, OCN=192, PM=SAME, BIAS, OCV/CPU)
IN=7500 Kb [ 1 64 150 200 ]    OUT=22500 Kb [ 1 192 150 200 ]    Weights(parameters): 433 Kb    MFLOPS=6641.28
[ PERFSTAT ]    (samples=10   mean=372.62   median=372.21   min=371.45   stddev=1.08 (0.3%))
[       OK ] Conv.conv/7 (4142 ms)
[ RUN      ] Conv.conv/8, where GetParam() = (GFLOPS=1.659, K=[3 x 3], IN={1, 960, 10, 10}, OCN=960, PM=SAME, CUDA/CUDA)
IN=375 Kb [ 1 960 10 10 ]    OUT=375 Kb [ 1 960 10 10 ]    Weights(parameters): 32400 Kb    MFLOPS=1658.98
[ PERFSTAT ]    (samples=100   mean=24.17   median=24.48   min=21.35   stddev=0.93 (3.9%))
[       OK ] Conv.conv/8 (2678 ms)
[ RUN      ] Conv.conv/9, where GetParam() = (GFLOPS=1.659, K=[3 x 3], IN={1, 960, 10, 10}, OCN=960, PM=SAME, OCV/CPU)
IN=375 Kb [ 1 960 10 10 ]    OUT=375 Kb [ 1 960 10 10 ]    Weights(parameters): 32400 Kb    MFLOPS=1658.98
[ PERFSTAT ]    (samples=10   mean=116.70   median=116.57   min=114.77   stddev=1.43 (1.2%))
[       OK ] Conv.conv/9 (1358 ms)
[ RUN      ] Conv.conv/10, where GetParam() = (GFLOPS=2.156, K=[3 x 3], IN={1, 576, 19, 19}, OCN=576, PM=SAME, CUDA/CUDA)
IN=813 Kb [ 1 576 19 19 ]    OUT=813 Kb [ 1 576 19 19 ]    Weights(parameters): 11664 Kb    MFLOPS=2156.09
[ PERFSTAT ]    (samples=100   mean=19.97   median=20.29   min=15.99   stddev=1.18 (5.9%))
[       OK ] Conv.conv/10 (2130 ms)
[ RUN      ] Conv.conv/11, where GetParam() = (GFLOPS=2.156, K=[3 x 3], IN={1, 576, 19, 19}, OCN=576, PM=SAME, OCV/CPU)
IN=813 Kb [ 1 576 19 19 ]    OUT=813 Kb [ 1 576 19 19 ]    Weights(parameters): 11664 Kb    MFLOPS=2156.09
[ PERFSTAT ]    (samples=10   mean=130.99   median=131.20   min=130.19   stddev=0.41 (0.3%))
[       OK ] Conv.conv/11 (1483 ms)
[ RUN      ] Conv.conv/12, where GetParam() = (GFLOPS=0.958, K=[3 x 3], IN={1, 384, 19, 19}, OCN=384, PM=SAME, CUDA/CUDA)
IN=542 Kb [ 1 384 19 19 ]    OUT=542 Kb [ 1 384 19 19 ]    Weights(parameters): 5184 Kb    MFLOPS=958.308
[ PERFSTAT ]    (samples=10   mean=7.28   median=7.27   min=7.16   stddev=0.07 (0.9%))
[       OK ] Conv.conv/12 (137 ms)
[ RUN      ] Conv.conv/13, where GetParam() = (GFLOPS=0.958, K=[3 x 3], IN={1, 384, 19, 19}, OCN=384, PM=SAME, OCV/CPU)
IN=542 Kb [ 1 384 19 19 ]    OUT=542 Kb [ 1 384 19 19 ]    Weights(parameters): 5184 Kb    MFLOPS=958.308
[ PERFSTAT ]    (samples=10   mean=56.49   median=56.34   min=56.21   stddev=0.29 (0.5%))
[       OK ] Conv.conv/13 (651 ms)
[ RUN      ] Conv.conv/14, where GetParam() = (GFLOPS=0.830, K=[3 x 3], IN={1, 64, 75, 100}, OCN=96, PM=SAME, BIAS, CUDA/CUDA)
IN=1875 Kb [ 1 64 75 100 ]    OUT=2813 Kb [ 1 96 75 100 ]    Weights(parameters): 217 Kb    MFLOPS=830.16
[ PERFSTAT ]    (samples=10   mean=5.83   median=5.80   min=5.72   stddev=0.13 (2.2%))
[       OK ] Conv.conv/14 (101 ms)
[ RUN      ] Conv.conv/15, where GetParam() = (GFLOPS=0.830, K=[3 x 3], IN={1, 64, 75, 100}, OCN=96, PM=SAME, BIAS, OCV/CPU)
IN=1875 Kb [ 1 64 75 100 ]    OUT=2813 Kb [ 1 96 75 100 ]    Weights(parameters): 217 Kb    MFLOPS=830.16
[ PERFSTAT ]    (samples=10   mean=48.19   median=48.10   min=47.94   stddev=0.37 (0.8%))
[       OK ] Conv.conv/15 (554 ms)
[ RUN      ] Conv.conv/16, where GetParam() = (GFLOPS=1.245, K=[3 x 3], IN={1, 96, 75, 100}, OCN=96, PM=SAME, BIAS, CUDA/CUDA)
IN=2813 Kb [ 1 96 75 100 ]    OUT=2813 Kb [ 1 96 75 100 ]    Weights(parameters): 325 Kb    MFLOPS=1244.88
[ PERFSTAT ]    (samples=100   mean=9.29   median=9.34   min=7.01   stddev=0.96 (10.4%))
[       OK ] Conv.conv/16 (1004 ms)
[ RUN      ] Conv.conv/17, where GetParam() = (GFLOPS=1.245, K=[3 x 3], IN={1, 96, 75, 100}, OCN=96, PM=SAME, BIAS, OCV/CPU)
IN=2813 Kb [ 1 96 75 100 ]    OUT=2813 Kb [ 1 96 75 100 ]    Weights(parameters): 325 Kb    MFLOPS=1244.88
[ PERFSTAT ]    (samples=10   mean=72.01   median=71.62   min=71.35   stddev=1.35 (1.9%))
[       OK ] Conv.conv/17 (819 ms)
[ RUN      ] Conv.conv/18, where GetParam() = (GFLOPS=2.100, K=[3 x 3], IN={1, 144, 75, 75}, OCN=144, PM=SAME, CUDA/CUDA)
IN=3165 Kb [ 1 144 75 75 ]    OUT=3165 Kb [ 1 144 75 75 ]    Weights(parameters): 729 Kb    MFLOPS=2100.33
[ PERFSTAT ]    (samples=100   mean=14.63   median=14.73   min=10.64   stddev=1.54 (10.5%))
[       OK ] Conv.conv/18 (1559 ms)
[ RUN      ] Conv.conv/19, where GetParam() = (GFLOPS=2.100, K=[3 x 3], IN={1, 144, 75, 75}, OCN=144, PM=SAME, OCV/CPU)
IN=3165 Kb [ 1 144 75 75 ]    OUT=3165 Kb [ 1 144 75 75 ]    Weights(parameters): 729 Kb    MFLOPS=2100.33
[ PERFSTAT ]    (samples=10   mean=119.11   median=119.08   min=118.61   stddev=0.27 (0.2%))
[       OK ] Conv.conv/19 (1338 ms)
[ RUN      ] Conv.conv/20, where GetParam() = (GFLOPS=1.022, K=[3 x 3], IN={1, 576, 19, 19}, OCN=273, PM=SAME, BIAS, CUDA/CUDA)
IN=813 Kb [ 1 576 19 19 ]    OUT=385 Kb [ 1 273 19 19 ]    Weights(parameters): 5530 Kb    MFLOPS=1021.9
[ PERFSTAT ]    (samples=10   mean=8.09   median=8.09   min=7.99   stddev=0.07 (0.9%))
[       OK ] Conv.conv/20 (148 ms)
[ RUN      ] Conv.conv/21, where GetParam() = (GFLOPS=1.022, K=[3 x 3], IN={1, 576, 19, 19}, OCN=273, PM=SAME, BIAS, OCV/CPU)
IN=813 Kb [ 1 576 19 19 ]    OUT=385 Kb [ 1 273 19 19 ]    Weights(parameters): 5530 Kb    MFLOPS=1021.9
[ PERFSTAT ]    (samples=10   mean=60.67   median=60.49   min=60.44   stddev=0.56 (0.9%))
[       OK ] Conv.conv/21 (697 ms)
[ RUN      ] Conv.conv/22, where GetParam() = (GFLOPS=0.958, K=[3 x 3], IN={1, 192, 38, 38}, OCN=192, PM=SAME, CUDA/CUDA)
IN=1083 Kb [ 1 192 38 38 ]    OUT=1083 Kb [ 1 192 38 38 ]    Weights(parameters): 1296 Kb    MFLOPS=958.446
[ PERFSTAT ]    (samples=10   mean=5.01   median=4.99   min=4.93   stddev=0.06 (1.2%))
[       OK ] Conv.conv/22 (92 ms)
[ RUN      ] Conv.conv/23, where GetParam() = (GFLOPS=0.958, K=[3 x 3], IN={1, 192, 38, 38}, OCN=192, PM=SAME, OCV/CPU)
IN=1083 Kb [ 1 192 38 38 ]    OUT=1083 Kb [ 1 192 38 38 ]    Weights(parameters): 1296 Kb    MFLOPS=958.446
[ PERFSTAT ]    (samples=10   mean=55.44   median=55.34   min=55.19   stddev=0.28 (0.5%))
[       OK ] Conv.conv/23 (634 ms)
[ RUN      ] Conv.conv/24, where GetParam() = (GFLOPS=1.888, K=[3 x 3], IN={1, 1024, 10, 10}, OCN=1024, PM=SAME, CUDA/CUDA)
IN=400 Kb [ 1 1024 10 10 ]    OUT=400 Kb [ 1 1024 10 10 ]    Weights(parameters): 36864 Kb    MFLOPS=1887.54
[ PERFSTAT ]    (samples=83   mean=27.77   median=27.97   min=24.71   stddev=0.83 (3.0%))
[       OK ] Conv.conv/24 (2571 ms)
[ RUN      ] Conv.conv/25, where GetParam() = (GFLOPS=1.888, K=[3 x 3], IN={1, 1024, 10, 10}, OCN=1024, PM=SAME, OCV/CPU)
IN=400 Kb [ 1 1024 10 10 ]    OUT=400 Kb [ 1 1024 10 10 ]    Weights(parameters): 36864 Kb    MFLOPS=1887.54
[ PERFSTAT ]    (samples=10   mean=129.06   median=130.51   min=126.19   stddev=2.33 (1.8%))
[       OK ] Conv.conv/25 (1514 ms)
[ RUN      ] Conv.conv/26, where GetParam() = (GFLOPS=1.888, K=[3 x 3], IN={1, 1024, 10, 10}, OCN=1024, G=1024, P=[1 x 1], BIAS, CUDA/CUDA)
IN=400 Kb [ 1 1024 10 10 ]    OUT=400 Kb [ 1 1024 10 10 ]    Weights(parameters): 40 Kb    MFLOPS=1887.54
[ PERFSTAT ]    (samples=13   mean=74.26   median=74.25   min=73.81   stddev=0.23 (0.3%))
[       OK ] Conv.conv/26 (1166 ms)
[ RUN      ] Conv.conv/27, where GetParam() = (GFLOPS=1.888, K=[3 x 3], IN={1, 1024, 10, 10}, OCN=1024, G=1024, P=[1 x 1], BIAS, OCV/CPU)
IN=400 Kb [ 1 1024 10 10 ]    OUT=400 Kb [ 1 1024 10 10 ]    Weights(parameters): 40 Kb    MFLOPS=1887.54
[ PERFSTAT ]    (samples=17   mean=1.58   median=1.57   min=1.55   stddev=0.05 (2.9%))
[       OK ] Conv.conv/27 (42 ms)
[ RUN      ] Conv.conv/28, where GetParam() = (GFLOPS=1.704, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, G=256, P=[1 x 1], BIAS, CUDA/CUDA)
IN=1444 Kb [ 1 256 38 38 ]    OUT=1444 Kb [ 1 256 38 38 ]    Weights(parameters): 10 Kb    MFLOPS=1703.78
[ PERFSTAT ]    (samples=10   mean=21.07   median=21.16   min=20.39   stddev=0.36 (1.7%))
[       OK ] Conv.conv/28 (263 ms)
[ RUN      ] Conv.conv/29, where GetParam() = (GFLOPS=1.704, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, G=256, P=[1 x 1], BIAS, OCV/CPU)
IN=1444 Kb [ 1 256 38 38 ]    OUT=1444 Kb [ 1 256 38 38 ]    Weights(parameters): 10 Kb    MFLOPS=1703.78
[ PERFSTAT ]    (samples=10   mean=4.58   median=4.57   min=4.54   stddev=0.04 (0.9%))
[       OK ] Conv.conv/29 (71 ms)
[ RUN      ] Conv.conv/30, where GetParam() = (GFLOPS=1.704, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, PM=SAME, CUDA/CUDA)
IN=1444 Kb [ 1 256 38 38 ]    OUT=1444 Kb [ 1 256 38 38 ]    Weights(parameters): 2304 Kb    MFLOPS=1703.78
[ PERFSTAT ]    (samples=100   mean=9.52   median=9.60   min=8.23   stddev=0.46 (4.8%))
[       OK ] Conv.conv/30 (1021 ms)
[ RUN      ] Conv.conv/31, where GetParam() = (GFLOPS=1.704, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, PM=SAME, OCV/CPU)
IN=1444 Kb [ 1 256 38 38 ]    OUT=1444 Kb [ 1 256 38 38 ]    Weights(parameters): 2304 Kb    MFLOPS=1703.78
[ PERFSTAT ]    (samples=10   mean=97.22   median=97.31   min=96.59   stddev=0.32 (0.3%))
[       OK ] Conv.conv/31 (1096 ms)
[ RUN      ] Conv.conv/32, where GetParam() = (GFLOPS=1.660, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, G=128, P=[1 x 1], BIAS, CUDA/CUDA)
IN=2813 Kb [ 1 128 75 75 ]    OUT=2813 Kb [ 1 128 75 75 ]    Weights(parameters): 5 Kb    MFLOPS=1659.6
[ PERFSTAT ]    (samples=10   mean=34.41   median=34.36   min=33.71   stddev=0.52 (1.5%))
[       OK ] Conv.conv/32 (417 ms)
[ RUN      ] Conv.conv/33, where GetParam() = (GFLOPS=1.660, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, G=128, P=[1 x 1], BIAS, OCV/CPU)
IN=2813 Kb [ 1 128 75 75 ]    OUT=2813 Kb [ 1 128 75 75 ]    Weights(parameters): 5 Kb    MFLOPS=1659.6
[ PERFSTAT ]    (samples=10   mean=8.07   median=8.06   min=7.96   stddev=0.07 (0.9%))
[       OK ] Conv.conv/33 (108 ms)
[ RUN      ] Conv.conv/34, where GetParam() = (GFLOPS=1.660, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, PM=SAME, CUDA/CUDA)
IN=2813 Kb [ 1 128 75 75 ]    OUT=2813 Kb [ 1 128 75 75 ]    Weights(parameters): 576 Kb    MFLOPS=1659.6
[ PERFSTAT ]    (samples=10   mean=8.22   median=8.17   min=8.07   stddev=0.14 (1.7%))
[       OK ] Conv.conv/34 (132 ms)
[ RUN      ] Conv.conv/35, where GetParam() = (GFLOPS=1.660, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, PM=SAME, OCV/CPU)
IN=2813 Kb [ 1 128 75 75 ]    OUT=2813 Kb [ 1 128 75 75 ]    Weights(parameters): 576 Kb    MFLOPS=1659.6
[ PERFSTAT ]    (samples=10   mean=95.03   median=94.84   min=94.44   stddev=0.53 (0.6%))
[       OK ] Conv.conv/35 (1087 ms)
[ RUN      ] Conv.conv/36, where GetParam() = (GFLOPS=0.280, K=[1 x 1], IN={1, 576, 38, 50}, OCN=128, PM=SAME, BIAS, CUDA/CUDA)
IN=4275 Kb [ 1 576 38 50 ]    OUT=950 Kb [ 1 128 38 50 ]    Weights(parameters): 289 Kb    MFLOPS=280.41
[ PERFSTAT ]    (samples=10   mean=2.29   median=2.29   min=2.24   stddev=0.04 (1.8%))
[       OK ] Conv.conv/36 (76 ms)
[ RUN      ] Conv.conv/37, where GetParam() = (GFLOPS=0.280, K=[1 x 1], IN={1, 576, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU)
IN=4275 Kb [ 1 576 38 50 ]    OUT=950 Kb [ 1 128 38 50 ]    Weights(parameters): 289 Kb    MFLOPS=280.41
[ PERFSTAT ]    (samples=13   mean=17.36   median=17.37   min=17.29   stddev=0.04 (0.2%))
[       OK ] Conv.conv/37 (280 ms)
[ RUN      ] Conv.conv/38, where GetParam() = (GFLOPS=0.701, K=[3 x 3], IN={1, 128, 38, 50}, OCN=160, PM=SAME, BIAS, CUDA/CUDA)
IN=950 Kb [ 1 128 38 50 ]    OUT=1188 Kb [ 1 160 38 50 ]    Weights(parameters): 721 Kb    MFLOPS=700.72
[ PERFSTAT ]    (samples=10   mean=4.28   median=4.30   min=4.19   stddev=0.07 (1.7%))
[       OK ] Conv.conv/38 (81 ms)
[ RUN      ] Conv.conv/39, where GetParam() = (GFLOPS=0.701, K=[3 x 3], IN={1, 128, 38, 50}, OCN=160, PM=SAME, BIAS, OCV/CPU)
IN=950 Kb [ 1 128 38 50 ]    OUT=1188 Kb [ 1 160 38 50 ]    Weights(parameters): 721 Kb    MFLOPS=700.72
[ PERFSTAT ]    (samples=10   mean=39.95   median=39.91   min=39.74   stddev=0.15 (0.4%))
[       OK ] Conv.conv/39 (456 ms)
[ RUN      ] Conv.conv/40, where GetParam() = (GFLOPS=0.231, K=[3 x 3], IN={1, 128, 56, 56}, OCN=32, P=[1 x 1], CUDA/CUDA)
IN=1568 Kb [ 1 128 56 56 ]    OUT=392 Kb [ 1 32 56 56 ]    Weights(parameters): 144 Kb    MFLOPS=231.311
[ PERFSTAT ]    (samples=13   mean=1.24   median=1.23   min=1.19   stddev=0.03 (2.4%))
[       OK ] Conv.conv/40 (49 ms)
[ RUN      ] Conv.conv/41, where GetParam() = (GFLOPS=0.231, K=[3 x 3], IN={1, 128, 56, 56}, OCN=32, P=[1 x 1], OCV/CPU)
IN=1568 Kb [ 1 128 56 56 ]    OUT=392 Kb [ 1 32 56 56 ]    Weights(parameters): 144 Kb    MFLOPS=231.311
[ PERFSTAT ]    (samples=10   mean=15.70   median=15.70   min=15.53   stddev=0.11 (0.7%))
[       OK ] Conv.conv/41 (189 ms)
[ RUN      ] Conv.conv/42, where GetParam() = (GFLOPS=0.231, K=[3 x 3], IN={1, 256, 14, 14}, OCN=256, P=[1 x 1], CUDA/CUDA)
IN=196 Kb [ 1 256 14 14 ]    OUT=196 Kb [ 1 256 14 14 ]    Weights(parameters): 2304 Kb    MFLOPS=231.261
[ PERFSTAT ]    (samples=10   mean=1.55   median=1.55   min=1.51   stddev=0.04 (2.4%))
[       OK ] Conv.conv/42 (53 ms)
[ RUN      ] Conv.conv/43, where GetParam() = (GFLOPS=0.231, K=[3 x 3], IN={1, 256, 14, 14}, OCN=256, P=[1 x 1], OCV/CPU)
IN=196 Kb [ 1 256 14 14 ]    OUT=196 Kb [ 1 256 14 14 ]    Weights(parameters): 2304 Kb    MFLOPS=231.261
[ PERFSTAT ]    (samples=10   mean=14.57   median=14.56   min=14.50   stddev=0.06 (0.4%))
[       OK ] Conv.conv/43 (177 ms)
[ RUN      ] Conv.conv/44, where GetParam() = (GFLOPS=0.210, K=[1 x 1], IN={1, 576, 38, 50}, OCN=96, PM=SAME, BIAS, CUDA/CUDA)
IN=4275 Kb [ 1 576 38 50 ]    OUT=713 Kb [ 1 96 38 50 ]    Weights(parameters): 217 Kb    MFLOPS=210.307
[ PERFSTAT ]    (samples=10   mean=2.28   median=2.27   min=2.21   stddev=0.06 (2.7%))
[       OK ] Conv.conv/44 (66 ms)
[ RUN      ] Conv.conv/45, where GetParam() = (GFLOPS=0.210, K=[1 x 1], IN={1, 576, 38, 50}, OCN=96, PM=SAME, BIAS, OCV/CPU)
IN=4275 Kb [ 1 576 38 50 ]    OUT=713 Kb [ 1 96 38 50 ]    Weights(parameters): 217 Kb    MFLOPS=210.307
[ PERFSTAT ]    (samples=10   mean=13.13   median=13.14   min=13.00   stddev=0.07 (0.5%))
[       OK ] Conv.conv/45 (166 ms)
[ RUN      ] Conv.conv/46, where GetParam() = (GFLOPS=0.420, K=[3 x 3], IN={1, 96, 38, 50}, OCN=128, PM=SAME, BIAS, CUDA/CUDA)
IN=713 Kb [ 1 96 38 50 ]    OUT=950 Kb [ 1 128 38 50 ]    Weights(parameters): 433 Kb    MFLOPS=420.493
[ PERFSTAT ]    (samples=10   mean=2.83   median=2.83   min=2.78   stddev=0.04 (1.2%))
[       OK ] Conv.conv/46 (63 ms)
[ RUN      ] Conv.conv/47, where GetParam() = (GFLOPS=0.420, K=[3 x 3], IN={1, 96, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU)
IN=713 Kb [ 1 96 38 50 ]    OUT=950 Kb [ 1 128 38 50 ]    Weights(parameters): 433 Kb    MFLOPS=420.493
[ PERFSTAT ]    (samples=10   mean=23.83   median=23.82   min=23.71   stddev=0.09 (0.4%))
[       OK ] Conv.conv/47 (278 ms)
[ RUN      ] Conv.conv/48, where GetParam() = (GFLOPS=1.261, K=[3 x 3], IN={1, 192, 38, 50}, OCN=192, PM=SAME, BIAS, CUDA/CUDA)
IN=1425 Kb [ 1 192 38 50 ]    OUT=1425 Kb [ 1 192 38 50 ]    Weights(parameters): 1297 Kb    MFLOPS=1261.11
[ PERFSTAT ]    (samples=100   mean=8.58   median=8.52   min=6.60   stddev=1.00 (11.7%))
[       OK ] Conv.conv/48 (939 ms)
[ RUN      ] Conv.conv/49, where GetParam() = (GFLOPS=1.261, K=[3 x 3], IN={1, 192, 38, 50}, OCN=192, PM=SAME, BIAS, OCV/CPU)
IN=1425 Kb [ 1 192 38 50 ]    OUT=1425 Kb [ 1 192 38 50 ]    Weights(parameters): 1297 Kb    MFLOPS=1261.11
[ PERFSTAT ]    (samples=10   mean=73.68   median=73.59   min=73.14   stddev=0.42 (0.6%))
[       OK ] Conv.conv/49 (836 ms)
[ RUN      ] Conv.conv/50, where GetParam() = (GFLOPS=1.258, K=[3 x 3], IN={1, 1280, 10, 10}, OCN=546, PM=SAME, BIAS, CUDA/CUDA)
IN=500 Kb [ 1 1280 10 10 ]    OUT=214 Kb [ 1 546 10 10 ]    Weights(parameters): 24573 Kb    MFLOPS=1258.04
[ PERFSTAT ]    (samples=100   mean=19.09   median=19.30   min=17.01   stddev=0.65 (3.4%))
[       OK ] Conv.conv/50 (2099 ms)
[ RUN      ] Conv.conv/51, where GetParam() = (GFLOPS=1.258, K=[3 x 3], IN={1, 1280, 10, 10}, OCN=546, PM=SAME, BIAS, OCV/CPU)
IN=500 Kb [ 1 1280 10 10 ]    OUT=214 Kb [ 1 546 10 10 ]    Weights(parameters): 24573 Kb    MFLOPS=1258.04
[ PERFSTAT ]    (samples=10   mean=84.60   median=84.28   min=84.20   stddev=0.99 (1.2%))
[       OK ] Conv.conv/51 (992 ms)
[ RUN      ] Conv.conv/52, where GetParam() = (GFLOPS=1.245, K=[3 x 3], IN={1, 64, 75, 75}, OCN=192, PM=SAME, BIAS, CUDA/CUDA)
IN=1407 Kb [ 1 64 75 75 ]    OUT=4219 Kb [ 1 192 75 75 ]    Weights(parameters): 433 Kb    MFLOPS=1245.24
[ PERFSTAT ]    (samples=100   mean=10.68   median=10.77   min=8.54   stddev=0.72 (6.7%))
[       OK ] Conv.conv/52 (1128 ms)
[ RUN      ] Conv.conv/53, where GetParam() = (GFLOPS=1.245, K=[3 x 3], IN={1, 64, 75, 75}, OCN=192, PM=SAME, BIAS, OCV/CPU)
IN=1407 Kb [ 1 64 75 75 ]    OUT=4219 Kb [ 1 192 75 75 ]    Weights(parameters): 433 Kb    MFLOPS=1245.24
[ PERFSTAT ]    (samples=10   mean=69.39   median=69.31   min=69.07   stddev=0.46 (0.7%))
[       OK ] Conv.conv/53 (787 ms)
[ RUN      ] Conv.conv/54, where GetParam() = (GFLOPS=0.561, K=[3 x 3], IN={1, 128, 38, 50}, OCN=128, PM=SAME, BIAS, CUDA/CUDA)
IN=950 Kb [ 1 128 38 50 ]    OUT=950 Kb [ 1 128 38 50 ]    Weights(parameters): 577 Kb    MFLOPS=560.576
[ PERFSTAT ]    (samples=10   mean=3.45   median=3.46   min=3.41   stddev=0.02 (0.7%))
[       OK ] Conv.conv/54 (71 ms)
[ RUN      ] Conv.conv/55, where GetParam() = (GFLOPS=0.561, K=[3 x 3], IN={1, 128, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU)
IN=950 Kb [ 1 128 38 50 ]    OUT=950 Kb [ 1 128 38 50 ]    Weights(parameters): 577 Kb    MFLOPS=560.576
[ PERFSTAT ]    (samples=10   mean=32.27   median=32.25   min=32.15   stddev=0.10 (0.3%))
[       OK ] Conv.conv/55 (371 ms)
[ RUN      ] Conv.conv/56, where GetParam() = (GFLOPS=1.051, K=[3 x 3], IN={1, 160, 38, 50}, OCN=192, PM=SAME, BIAS, CUDA/CUDA)
IN=1188 Kb [ 1 160 38 50 ]    OUT=1425 Kb [ 1 192 38 50 ]    Weights(parameters): 1081 Kb    MFLOPS=1050.99
[ PERFSTAT ]    (samples=10   mean=5.87   median=5.85   min=5.81   stddev=0.06 (1.0%))
[       OK ] Conv.conv/56 (102 ms)
[ RUN      ] Conv.conv/57, where GetParam() = (GFLOPS=1.051, K=[3 x 3], IN={1, 160, 38, 50}, OCN=192, PM=SAME, BIAS, OCV/CPU)
IN=1188 Kb [ 1 160 38 50 ]    OUT=1425 Kb [ 1 192 38 50 ]    Weights(parameters): 1081 Kb    MFLOPS=1050.99
[ PERFSTAT ]    (samples=10   mean=59.97   median=59.99   min=59.64   stddev=0.16 (0.3%))
[       OK ] Conv.conv/57 (684 ms)
[ RUN      ] Conv.conv/58, where GetParam() = (GFLOPS=1.006, K=[3 x 3], IN={1, 1024, 10, 10}, OCN=546, PM=SAME, BIAS, CUDA/CUDA)
IN=400 Kb [ 1 1024 10 10 ]    OUT=214 Kb [ 1 546 10 10 ]    Weights(parameters): 19659 Kb    MFLOPS=1006.44
[ PERFSTAT ]    (samples=100   mean=15.50   median=15.76   min=12.86   stddev=0.75 (4.8%))
[       OK ] Conv.conv/58 (1713 ms)
[ RUN      ] Conv.conv/59, where GetParam() = (GFLOPS=1.006, K=[3 x 3], IN={1, 1024, 10, 10}, OCN=546, PM=SAME, BIAS, OCV/CPU)
IN=400 Kb [ 1 1024 10 10 ]    OUT=214 Kb [ 1 546 10 10 ]    Weights(parameters): 19659 Kb    MFLOPS=1006.44
[ PERFSTAT ]    (samples=10   mean=68.00   median=67.88   min=67.81   stddev=0.39 (0.6%))
[       OK ] Conv.conv/59 (802 ms)
[ RUN      ] Conv.conv/60, where GetParam() = (GFLOPS=0.246, K=[1 x 1], IN={1, 256, 75, 100}, OCN=64, PM=SAME, BIAS, CUDA/CUDA)
IN=7500 Kb [ 1 256 75 100 ]    OUT=1875 Kb [ 1 64 75 100 ]    Weights(parameters): 65 Kb    MFLOPS=246.24
[ PERFSTAT ]    (samples=76   mean=3.18   median=3.20   min=2.90   stddev=0.09 (3.0%))
[       OK ] Conv.conv/60 (299 ms)
[ RUN      ] Conv.conv/61, where GetParam() = (GFLOPS=0.246, K=[1 x 1], IN={1, 256, 75, 100}, OCN=64, PM=SAME, BIAS, OCV/CPU)
IN=7500 Kb [ 1 256 75 100 ]    OUT=1875 Kb [ 1 64 75 100 ]    Weights(parameters): 65 Kb    MFLOPS=246.24
[ PERFSTAT ]    (samples=10   mean=17.86   median=17.83   min=17.61   stddev=0.15 (0.8%))
[       OK ] Conv.conv/61 (225 ms)
[ RUN      ] Conv.conv/62, where GetParam() = (GFLOPS=0.189, K=[1 x 1], IN={1, 512, 19, 19}, OCN=512, BIAS, CUDA/CUDA)
IN=722 Kb [ 1 512 19 19 ]    OUT=722 Kb [ 1 512 19 19 ]    Weights(parameters): 1026 Kb    MFLOPS=189.453
[ PERFSTAT ]    (samples=10   mean=1.81   median=1.81   min=1.75   stddev=0.04 (2.1%))
[       OK ] Conv.conv/62 (52 ms)
[ RUN      ] Conv.conv/63, where GetParam() = (GFLOPS=0.189, K=[1 x 1], IN={1, 512, 19, 19}, OCN=512, BIAS, OCV/CPU)
IN=722 Kb [ 1 512 19 19 ]    OUT=722 Kb [ 1 512 19 19 ]    Weights(parameters): 1026 Kb    MFLOPS=189.453
[ PERFSTAT ]    (samples=10   mean=11.48   median=11.47   min=11.32   stddev=0.10 (0.9%))
[       OK ] Conv.conv/63 (142 ms)
[ RUN      ] Conv.conv/64, where GetParam() = (GFLOPS=0.189, K=[1 x 1], IN={1, 512, 19, 19}, OCN=512, PM=SAME, CUDA/CUDA)
IN=722 Kb [ 1 512 19 19 ]    OUT=722 Kb [ 1 512 19 19 ]    Weights(parameters): 1024 Kb    MFLOPS=189.453
[ PERFSTAT ]    (samples=10   mean=1.66   median=1.66   min=1.63   stddev=0.02 (1.3%))
[       OK ] Conv.conv/64 (51 ms)
[ RUN      ] Conv.conv/65, where GetParam() = (GFLOPS=0.189, K=[1 x 1], IN={1, 512, 19, 19}, OCN=512, PM=SAME, OCV/CPU)
IN=722 Kb [ 1 512 19 19 ]    OUT=722 Kb [ 1 512 19 19 ]    Weights(parameters): 1024 Kb    MFLOPS=189.453
[ PERFSTAT ]    (samples=10   mean=11.47   median=11.44   min=11.32   stddev=0.16 (1.4%))
[       OK ] Conv.conv/65 (142 ms)
[ RUN      ] Conv.conv/66, where GetParam() = (GFLOPS=0.934, K=[3 x 3], IN={1, 96, 150, 150}, OCN=96, S=[2 x 2], PM=SAME, CUDA/CUDA)
IN=8438 Kb [ 1 96 150 150 ]    OUT=2110 Kb [ 1 96 75 75 ]    Weights(parameters): 324 Kb    MFLOPS=933.66
[ PERFSTAT ]    (samples=100   mean=11.84   median=11.89   min=9.65   stddev=0.72 (6.0%))
[       OK ] Conv.conv/66 (1276 ms)
[ RUN      ] Conv.conv/67, where GetParam() = (GFLOPS=0.934, K=[3 x 3], IN={1, 96, 150, 150}, OCN=96, S=[2 x 2], PM=SAME, OCV/CPU)
IN=8438 Kb [ 1 96 150 150 ]    OUT=2110 Kb [ 1 96 75 75 ]    Weights(parameters): 324 Kb    MFLOPS=933.66
[ PERFSTAT ]    (samples=10   mean=57.33   median=57.30   min=56.84   stddev=0.45 (0.8%))
[       OK ] Conv.conv/67 (668 ms)
[ RUN      ] Conv.conv/68, where GetParam() = (GFLOPS=0.231, K=[3 x 3], IN={1, 128, 28, 28}, OCN=128, P=[1 x 1], CUDA/CUDA)
IN=392 Kb [ 1 128 28 28 ]    OUT=392 Kb [ 1 128 28 28 ]    Weights(parameters): 576 Kb    MFLOPS=231.311
[ PERFSTAT ]    (samples=10   mean=1.47   median=1.47   min=1.42   stddev=0.04 (2.5%))
[       OK ] Conv.conv/68 (48 ms)
[ RUN      ] Conv.conv/69, where GetParam() = (GFLOPS=0.231, K=[3 x 3], IN={1, 128, 28, 28}, OCN=128, P=[1 x 1], OCV/CPU)
IN=392 Kb [ 1 128 28 28 ]    OUT=392 Kb [ 1 128 28 28 ]    Weights(parameters): 576 Kb    MFLOPS=231.311
[ PERFSTAT ]    (samples=10   mean=13.07   median=13.08   min=12.96   stddev=0.08 (0.6%))
[       OK ] Conv.conv/69 (159 ms)
[ RUN      ] Conv.conv/70, where GetParam() = (GFLOPS=0.896, K=[5 x 5], IN={1, 96, 27, 27}, OCN=256, G=2, P=[2 x 2], BIAS, CUDA/CUDA)
IN=274 Kb [ 1 96 27 27 ]    OUT=729 Kb [ 1 256 27 27 ]    Weights(parameters): 1201 Kb    MFLOPS=895.982
[ PERFSTAT ]    (samples=10   mean=5.21   median=5.20   min=5.16   stddev=0.03 (0.6%))
[       OK ] Conv.conv/70 (93 ms)
[ RUN      ] Conv.conv/71, where GetParam() = (GFLOPS=0.896, K=[5 x 5], IN={1, 96, 27, 27}, OCN=256, G=2, P=[2 x 2], BIAS, OCV/CPU)
IN=274 Kb [ 1 96 27 27 ]    OUT=729 Kb [ 1 256 27 27 ]    Weights(parameters): 1201 Kb    MFLOPS=895.982
[ PERFSTAT ]    (samples=10   mean=29.35   median=29.34   min=29.04   stddev=0.14 (0.5%))
[       OK ] Conv.conv/71 (339 ms)
[ RUN      ] Conv.conv/72, where GetParam() = (GFLOPS=0.876, K=[3 x 3], IN={1, 160, 38, 50}, OCN=160, PM=SAME, BIAS, CUDA/CUDA)
IN=1188 Kb [ 1 160 38 50 ]    OUT=1188 Kb [ 1 160 38 50 ]    Weights(parameters): 901 Kb    MFLOPS=875.824
[ PERFSTAT ]    (samples=10   mean=4.89   median=4.89   min=4.85   stddev=0.03 (0.7%))
[       OK ] Conv.conv/72 (90 ms)
[ RUN      ] Conv.conv/73, where GetParam() = (GFLOPS=0.876, K=[3 x 3], IN={1, 160, 38, 50}, OCN=160, PM=SAME, BIAS, OCV/CPU)
IN=1188 Kb [ 1 160 38 50 ]    OUT=1188 Kb [ 1 160 38 50 ]    Weights(parameters): 901 Kb    MFLOPS=875.824
[ PERFSTAT ]    (samples=10   mean=50.33   median=50.37   min=49.79   stddev=0.27 (0.5%))
[       OK ] Conv.conv/73 (577 ms)
[ RUN      ] Conv.conv/74, where GetParam() = (GFLOPS=0.850, K=[7 x 7], IN={1, 3, 600, 800}, OCN=24, S=[2 x 2], PM=SAME, CUDA/CUDA)
IN=5625 Kb [ 1 3 600 800 ]    OUT=11250 Kb [ 1 24 300 400 ]    Weights(parameters): 14 Kb    MFLOPS=849.6
[ PERFSTAT ]    (samples=100   mean=20.21   median=19.87   min=15.77   stddev=2.54 (12.6%))
[       OK ] Conv.conv/74 (2150 ms)
[ RUN      ] Conv.conv/75, where GetParam() = (GFLOPS=0.850, K=[7 x 7], IN={1, 3, 600, 800}, OCN=24, S=[2 x 2], PM=SAME, OCV/CPU)
IN=5625 Kb [ 1 3 600 800 ]    OUT=11250 Kb [ 1 24 300 400 ]    Weights(parameters): 14 Kb    MFLOPS=849.6
[ PERFSTAT ]    (samples=10   mean=51.04   median=50.97   min=50.85   stddev=0.23 (0.5%))
[       OK ] Conv.conv/75 (592 ms)
[ RUN      ] Conv.conv/76, where GetParam() = (GFLOPS=0.841, K=[3 x 3], IN={1, 128, 38, 50}, OCN=192, PM=SAME, BIAS, CUDA/CUDA)
IN=950 Kb [ 1 128 38 50 ]    OUT=1425 Kb [ 1 192 38 50 ]    Weights(parameters): 865 Kb    MFLOPS=840.864
[ PERFSTAT ]    (samples=10   mean=5.04   median=5.04   min=4.87   stddev=0.07 (1.4%))
[       OK ] Conv.conv/76 (91 ms)
[ RUN      ] Conv.conv/77, where GetParam() = (GFLOPS=0.841, K=[3 x 3], IN={1, 128, 38, 50}, OCN=192, PM=SAME, BIAS, OCV/CPU)
IN=950 Kb [ 1 128 38 50 ]    OUT=1425 Kb [ 1 192 38 50 ]    Weights(parameters): 865 Kb    MFLOPS=840.864
[ PERFSTAT ]    (samples=10   mean=48.40   median=48.33   min=48.11   stddev=0.25 (0.5%))
[       OK ] Conv.conv/77 (555 ms)
[ RUN      ] Conv.conv/78, where GetParam() = (GFLOPS=0.415, K=[3 x 3], IN={1, 32, 150, 150}, OCN=32, PM=SAME, CUDA/CUDA)
IN=2813 Kb [ 1 32 150 150 ]    OUT=2813 Kb [ 1 32 150 150 ]    Weights(parameters): 36 Kb    MFLOPS=415.44
[ PERFSTAT ]    (samples=10   mean=3.58   median=3.59   min=3.49   stddev=0.05 (1.5%))
[       OK ] Conv.conv/78 (76 ms)
[ RUN      ] Conv.conv/79, where GetParam() = (GFLOPS=0.415, K=[3 x 3], IN={1, 32, 150, 150}, OCN=32, PM=SAME, OCV/CPU)
IN=2813 Kb [ 1 32 150 150 ]    OUT=2813 Kb [ 1 32 150 150 ]    Weights(parameters): 36 Kb    MFLOPS=415.44
[ PERFSTAT ]    (samples=10   mean=25.76   median=25.79   min=25.59   stddev=0.13 (0.5%))
[       OK ] Conv.conv/79 (302 ms)
[ RUN      ] Conv.conv/80, where GetParam() = (GFLOPS=0.351, K=[1 x 1], IN={1, 576, 38, 50}, OCN=160, PM=SAME, BIAS, CUDA/CUDA)
IN=4275 Kb [ 1 576 38 50 ]    OUT=1188 Kb [ 1 160 38 50 ]    Weights(parameters): 361 Kb    MFLOPS=350.512
[ PERFSTAT ]    (samples=10   mean=3.47   median=3.47   min=3.40   stddev=0.04 (1.3%))
[       OK ] Conv.conv/80 (81 ms)
[ RUN      ] Conv.conv/81, where GetParam() = (GFLOPS=0.351, K=[1 x 1], IN={1, 576, 38, 50}, OCN=160, PM=SAME, BIAS, OCV/CPU)
IN=4275 Kb [ 1 576 38 50 ]    OUT=1188 Kb [ 1 160 38 50 ]    Weights(parameters): 361 Kb    MFLOPS=350.512
[ PERFSTAT ]    (samples=10   mean=21.62   median=21.62   min=21.48   stddev=0.11 (0.5%))
[       OK ] Conv.conv/81 (260 ms)
[ RUN      ] Conv.conv/82, where GetParam() = (GFLOPS=0.701, K=[3 x 3], IN={1, 128, 75, 100}, OCN=160, S=[2 x 2], PM=SAME, BIAS, CUDA/CUDA)
IN=3750 Kb [ 1 128 75 100 ]    OUT=1188 Kb [ 1 160 38 50 ]    Weights(parameters): 721 Kb    MFLOPS=700.72
[ PERFSTAT ]    (samples=10   mean=7.07   median=7.07   min=6.81   stddev=0.20 (2.8%))
[       OK ] Conv.conv/82 (125 ms)
[ RUN      ] Conv.conv/83, where GetParam() = (GFLOPS=0.701, K=[3 x 3], IN={1, 128, 75, 100}, OCN=160, S=[2 x 2], PM=SAME, BIAS, OCV/CPU)
IN=3750 Kb [ 1 128 75 100 ]    OUT=1188 Kb [ 1 160 38 50 ]    Weights(parameters): 721 Kb    MFLOPS=700.72
[ PERFSTAT ]    (samples=10   mean=42.05   median=42.03   min=41.88   stddev=0.18 (0.4%))
[       OK ] Conv.conv/83 (485 ms)
[ RUN      ] Conv.conv/84, where GetParam() = (GFLOPS=0.694, K=[3 x 3], IN={1, 64, 56, 56}, OCN=192, P=[1 x 1], BIAS, CUDA/CUDA)
IN=784 Kb [ 1 64 56 56 ]    OUT=2352 Kb [ 1 192 56 56 ]    Weights(parameters): 433 Kb    MFLOPS=694.235
[ PERFSTAT ]    (samples=10   mean=4.82   median=4.79   min=4.66   stddev=0.14 (2.9%))
[       OK ] Conv.conv/84 (86 ms)
[ RUN      ] Conv.conv/85, where GetParam() = (GFLOPS=0.694, K=[3 x 3], IN={1, 64, 56, 56}, OCN=192, P=[1 x 1], BIAS, OCV/CPU)
IN=784 Kb [ 1 64 56 56 ]    OUT=2352 Kb [ 1 192 56 56 ]    Weights(parameters): 433 Kb    MFLOPS=694.235
[ PERFSTAT ]    (samples=10   mean=38.86   median=38.87   min=38.71   stddev=0.10 (0.3%))
[       OK ] Conv.conv/85 (443 ms)
[ RUN      ] Conv.conv/86, where GetParam() = (GFLOPS=0.694, K=[3 x 3], IN={1, 64, 56, 56}, OCN=192, PM=SAME, BIAS, CUDA/CUDA)
IN=784 Kb [ 1 64 56 56 ]    OUT=2352 Kb [ 1 192 56 56 ]    Weights(parameters): 433 Kb    MFLOPS=694.235
[ PERFSTAT ]    (samples=10   mean=4.76   median=4.73   min=4.67   stddev=0.10 (2.1%))
[       OK ] Conv.conv/86 (87 ms)
[ RUN      ] Conv.conv/87, where GetParam() = (GFLOPS=0.694, K=[3 x 3], IN={1, 64, 56, 56}, OCN=192, PM=SAME, BIAS, OCV/CPU)
IN=784 Kb [ 1 64 56 56 ]    OUT=2352 Kb [ 1 192 56 56 ]    Weights(parameters): 433 Kb    MFLOPS=694.235
[ PERFSTAT ]    (samples=10   mean=39.15   median=39.16   min=38.97   stddev=0.13 (0.3%))
[       OK ] Conv.conv/87 (446 ms)
[ RUN      ] Conv.conv/88, where GetParam() = (GFLOPS=0.231, K=[3 x 3], IN={1, 64, 56, 56}, OCN=64, P=[1 x 1], CUDA/CUDA)
IN=784 Kb [ 1 64 56 56 ]    OUT=784 Kb [ 1 64 56 56 ]    Weights(parameters): 144 Kb    MFLOPS=231.412
[ PERFSTAT ]    (samples=10   mean=1.63   median=1.61   min=1.59   stddev=0.03 (1.7%))
[       OK ] Conv.conv/88 (48 ms)
[ RUN      ] Conv.conv/89, where GetParam() = (GFLOPS=0.231, K=[3 x 3], IN={1, 64, 56, 56}, OCN=64, P=[1 x 1], OCV/CPU)
IN=784 Kb [ 1 64 56 56 ]    OUT=784 Kb [ 1 64 56 56 ]    Weights(parameters): 144 Kb    MFLOPS=231.412
[ PERFSTAT ]    (samples=10   mean=14.12   median=14.13   min=13.93   stddev=0.09 (0.7%))
[       OK ] Conv.conv/89 (170 ms)
[ RUN      ] Conv.conv/90, where GetParam() = (GFLOPS=0.058, K=[3 x 3], IN={1, 128, 28, 28}, OCN=32, P=[1 x 1], CUDA/CUDA)
IN=392 Kb [ 1 128 28 28 ]    OUT=98 Kb [ 1 32 28 28 ]    Weights(parameters): 144 Kb    MFLOPS=57.8278
[ PERFSTAT ]    (samples=100   mean=0.46   median=0.47   min=0.43   stddev=0.02 (3.7%))
[       OK ] Conv.conv/90 (75 ms)
[ RUN      ] Conv.conv/91, where GetParam() = (GFLOPS=0.058, K=[3 x 3], IN={1, 128, 28, 28}, OCN=32, P=[1 x 1], OCV/CPU)
IN=392 Kb [ 1 128 28 28 ]    OUT=98 Kb [ 1 32 28 28 ]    Weights(parameters): 144 Kb    MFLOPS=57.8278
[ PERFSTAT ]    (samples=10   mean=3.79   median=3.77   min=3.75   stddev=0.05 (1.2%))
[       OK ] Conv.conv/91 (56 ms)
[ RUN      ] Conv.conv/92, where GetParam() = (GFLOPS=0.231, K=[3 x 3], IN={1, 512, 7, 7}, OCN=512, P=[1 x 1], CUDA/CUDA)
IN=98 Kb [ 1 512 7 7 ]    OUT=98 Kb [ 1 512 7 7 ]    Weights(parameters): 9216 Kb    MFLOPS=231.236
[ PERFSTAT ]    (samples=10   mean=3.71   median=3.71   min=3.57   stddev=0.08 (2.2%))
[       OK ] Conv.conv/92 (112 ms)
[ RUN      ] Conv.conv/93, where GetParam() = (GFLOPS=0.231, K=[3 x 3], IN={1, 512, 7, 7}, OCN=512, P=[1 x 1], OCV/CPU)
IN=98 Kb [ 1 512 7 7 ]    OUT=98 Kb [ 1 512 7 7 ]    Weights(parameters): 9216 Kb    MFLOPS=231.236
[ PERFSTAT ]    (samples=10   mean=16.81   median=16.76   min=16.73   stddev=0.13 (0.8%))
[       OK ] Conv.conv/93 (214 ms)
[ RUN      ] Conv.conv/94, where GetParam() = (GFLOPS=0.160, K=[3 x 3], IN={1, 64, 38, 38}, OCN=96, PM=SAME, BIAS, CUDA/CUDA)
IN=361 Kb [ 1 64 38 38 ]    OUT=542 Kb [ 1 96 38 38 ]    Weights(parameters): 217 Kb    MFLOPS=159.833
[ PERFSTAT ]    (samples=10   mean=1.36   median=1.35   min=1.33   stddev=0.03 (2.1%))
[       OK ] Conv.conv/94 (43 ms)
[ RUN      ] Conv.conv/95, where GetParam() = (GFLOPS=0.160, K=[3 x 3], IN={1, 64, 38, 38}, OCN=96, PM=SAME, BIAS, OCV/CPU)
IN=361 Kb [ 1 64 38 38 ]    OUT=542 Kb [ 1 96 38 38 ]    Weights(parameters): 217 Kb    MFLOPS=159.833
[ PERFSTAT ]    (samples=10   mean=9.24   median=9.21   min=9.13   stddev=0.08 (0.9%))
[       OK ] Conv.conv/95 (116 ms)
[ RUN      ] Conv.conv/96, where GetParam() = (GFLOPS=0.103, K=[1 x 1], IN={1, 256, 14, 14}, OCN=1024, CUDA/CUDA)
IN=196 Kb [ 1 256 14 14 ]    OUT=784 Kb [ 1 1024 14 14 ]    Weights(parameters): 1024 Kb    MFLOPS=102.961
[ PERFSTAT ]    (samples=10   mean=1.33   median=1.33   min=1.28   stddev=0.04 (3.0%))
[       OK ] Conv.conv/96 (46 ms)
[ RUN      ] Conv.conv/97, where GetParam() = (GFLOPS=0.103, K=[1 x 1], IN={1, 256, 14, 14}, OCN=1024, OCV/CPU)
IN=196 Kb [ 1 256 14 14 ]    OUT=784 Kb [ 1 1024 14 14 ]    Weights(parameters): 1024 Kb    MFLOPS=102.961
[ PERFSTAT ]    (samples=10   mean=6.80   median=6.78   min=6.71   stddev=0.09 (1.3%))
[       OK ] Conv.conv/97 (91 ms)
[ RUN      ] Conv.conv/98, where GetParam() = (GFLOPS=0.615, K=[1 x 1], IN={1, 320, 75, 100}, OCN=128, PM=SAME, BIAS, CUDA/CUDA)
IN=9375 Kb [ 1 320 75 100 ]    OUT=3750 Kb [ 1 128 75 100 ]    Weights(parameters): 161 Kb    MFLOPS=615.36
[ PERFSTAT ]    (samples=13   mean=6.15   median=6.14   min=5.90   stddev=0.18 (2.9%))
[       OK ] Conv.conv/98 (145 ms)
[ RUN      ] Conv.conv/99, where GetParam() = (GFLOPS=0.615, K=[1 x 1], IN={1, 320, 75, 100}, OCN=128, PM=SAME, BIAS, OCV/CPU)
IN=9375 Kb [ 1 320 75 100 ]    OUT=3750 Kb [ 1 128 75 100 ]    Weights(parameters): 161 Kb    MFLOPS=615.36
[ PERFSTAT ]    (samples=10   mean=42.14   median=42.07   min=41.76   stddev=0.24 (0.6%))
[       OK ] Conv.conv/99 (496 ms)
[ RUN      ] Conv.conv/100, where GetParam() = (GFLOPS=0.597, K=[3 x 3], IN={1, 576, 19, 19}, OCN=576, S=[2 x 2], PM=SAME, CUDA/CUDA)
IN=813 Kb [ 1 576 19 19 ]    OUT=225 Kb [ 1 576 10 10 ]    Weights(parameters): 11664 Kb    MFLOPS=597.254
[ PERFSTAT ]    (samples=13   mean=7.25   median=7.22   min=6.96   stddev=0.19 (2.6%))
[       OK ] Conv.conv/100 (172 ms)
[ RUN      ] Conv.conv/101, where GetParam() = (GFLOPS=0.597, K=[3 x 3], IN={1, 576, 19, 19}, OCN=576, S=[2 x 2], PM=SAME, OCV/CPU)
IN=813 Kb [ 1 576 19 19 ]    OUT=225 Kb [ 1 576 10 10 ]    Weights(parameters): 11664 Kb    MFLOPS=597.254
[ PERFSTAT ]    (samples=10   mean=40.02   median=40.03   min=39.66   stddev=0.14 (0.3%))
[       OK ] Conv.conv/101 (476 ms)
[ RUN      ] Conv.conv/102, where GetParam() = (GFLOPS=0.185, K=[1 x 1], IN={1, 192, 75, 100}, OCN=64, PM=SAME, BIAS, CUDA/CUDA)
IN=5625 Kb [ 1 192 75 100 ]    OUT=1875 Kb [ 1 64 75 100 ]    Weights(parameters): 49 Kb    MFLOPS=184.8
[ PERFSTAT ]    (samples=10   mean=2.55   median=2.55   min=2.50   stddev=0.04 (1.7%))
[       OK ] Conv.conv/102 (73 ms)
[ RUN      ] Conv.conv/103, where GetParam() = (GFLOPS=0.185, K=[1 x 1], IN={1, 192, 75, 100}, OCN=64, PM=SAME, BIAS, OCV/CPU)
IN=5625 Kb [ 1 192 75 100 ]    OUT=1875 Kb [ 1 64 75 100 ]    Weights(parameters): 49 Kb    MFLOPS=184.8
[ PERFSTAT ]    (samples=10   mean=13.21   median=13.23   min=13.06   stddev=0.07 (0.6%))
[       OK ] Conv.conv/103 (170 ms)
[ RUN      ] Conv.conv/104, where GetParam() = (GFLOPS=0.553, K=[3 x 3], IN={1, 64, 75, 100}, OCN=64, PM=SAME, BIAS, CUDA/CUDA)
IN=1875 Kb [ 1 64 75 100 ]    OUT=1875 Kb [ 1 64 75 100 ]    Weights(parameters): 145 Kb    MFLOPS=553.44
[ PERFSTAT ]    (samples=10   mean=3.89   median=3.87   min=3.83   stddev=0.05 (1.2%))
[       OK ] Conv.conv/104 (77 ms)
[ RUN      ] Conv.conv/105, where GetParam() = (GFLOPS=0.553, K=[3 x 3], IN={1, 64, 75, 100}, OCN=64, PM=SAME, BIAS, OCV/CPU)
IN=1875 Kb [ 1 64 75 100 ]    OUT=1875 Kb [ 1 64 75 100 ]    Weights(parameters): 145 Kb    MFLOPS=553.44
[ PERFSTAT ]    (samples=10   mean=33.71   median=33.70   min=33.30   stddev=0.22 (0.7%))
[       OK ] Conv.conv/105 (388 ms)
[ RUN      ] Conv.conv/106, where GetParam() = (GFLOPS=0.539, K=[3 x 3], IN={1, 144, 75, 75}, OCN=144, S=[2 x 2], PM=SAME, CUDA/CUDA)
IN=3165 Kb [ 1 144 75 75 ]    OUT=813 Kb [ 1 144 38 38 ]    Weights(parameters): 729 Kb    MFLOPS=539.178
[ PERFSTAT ]    (samples=10   mean=4.97   median=4.95   min=4.86   stddev=0.09 (1.9%))
[       OK ] Conv.conv/106 (96 ms)
[ RUN      ] Conv.conv/107, where GetParam() = (GFLOPS=0.539, K=[3 x 3], IN={1, 144, 75, 75}, OCN=144, S=[2 x 2], PM=SAME, OCV/CPU)
IN=3165 Kb [ 1 144 75 75 ]    OUT=813 Kb [ 1 144 38 38 ]    Weights(parameters): 729 Kb    MFLOPS=539.178
[ PERFSTAT ]    (samples=13   mean=32.36   median=32.32   min=32.11   stddev=0.18 (0.6%))
[       OK ] Conv.conv/107 (477 ms)
[ RUN      ] Conv.conv/108, where GetParam() = (GFLOPS=0.103, K=[1 x 1], IN={1, 1024, 14, 14}, OCN=256, CUDA/CUDA)
IN=784 Kb [ 1 1024 14 14 ]    OUT=196 Kb [ 1 256 14 14 ]    Weights(parameters): 1024 Kb    MFLOPS=102.811
[ PERFSTAT ]    (samples=16   mean=0.93   median=0.92   min=0.89   stddev=0.03 (2.9%))
[       OK ] Conv.conv/108 (48 ms)
[ RUN      ] Conv.conv/109, where GetParam() = (GFLOPS=0.103, K=[1 x 1], IN={1, 1024, 14, 14}, OCN=256, OCV/CPU)
IN=784 Kb [ 1 1024 14 14 ]    OUT=196 Kb [ 1 256 14 14 ]    Weights(parameters): 1024 Kb    MFLOPS=102.811
[ PERFSTAT ]    (samples=13   mean=6.62   median=6.59   min=6.48   stddev=0.15 (2.3%))
[       OK ] Conv.conv/109 (115 ms)
[ RUN      ] Conv.conv/110, where GetParam() = (GFLOPS=0.491, K=[1 x 1], IN={1, 576, 38, 50}, OCN=224, PM=SAME, BIAS, CUDA/CUDA)
IN=4275 Kb [ 1 576 38 50 ]    OUT=1663 Kb [ 1 224 38 50 ]    Weights(parameters): 505 Kb    MFLOPS=490.717
[ PERFSTAT ]    (samples=10   mean=4.21   median=4.20   min=4.17   stddev=0.03 (0.8%))
[       OK ] Conv.conv/110 (90 ms)
[ RUN      ] Conv.conv/111, where GetParam() = (GFLOPS=0.491, K=[1 x 1], IN={1, 576, 38, 50}, OCN=224, PM=SAME, BIAS, OCV/CPU)
IN=4275 Kb [ 1 576 38 50 ]    OUT=1663 Kb [ 1 224 38 50 ]    Weights(parameters): 505 Kb    MFLOPS=490.717
[ PERFSTAT ]    (samples=10   mean=30.69   median=30.69   min=30.58   stddev=0.08 (0.3%))
[       OK ] Conv.conv/111 (360 ms)
[ RUN      ] Conv.conv/112, where GetParam() = (GFLOPS=0.240, K=[3 x 3], IN={1, 96, 38, 38}, OCN=96, PM=SAME, BIAS, CUDA/CUDA)
IN=542 Kb [ 1 96 38 38 ]    OUT=542 Kb [ 1 96 38 38 ]    Weights(parameters): 325 Kb    MFLOPS=239.681
[ PERFSTAT ]    (samples=10   mean=1.71   median=1.71   min=1.68   stddev=0.02 (1.3%))
[       OK ] Conv.conv/112 (48 ms)
[ RUN      ] Conv.conv/113, where GetParam() = (GFLOPS=0.240, K=[3 x 3], IN={1, 96, 38, 38}, OCN=96, PM=SAME, BIAS, OCV/CPU)
IN=542 Kb [ 1 96 38 38 ]    OUT=542 Kb [ 1 96 38 38 ]    Weights(parameters): 325 Kb    MFLOPS=239.681
[ PERFSTAT ]    (samples=10   mean=13.63   median=13.60   min=13.49   stddev=0.13 (1.0%))
[       OK ] Conv.conv/113 (165 ms)
[ RUN      ] Conv.conv/114, where GetParam() = (GFLOPS=0.237, K=[7 x 7], IN={1, 3, 224, 224}, OCN=64, S=[2 x 2], P=[3 x 3], BIAS, CUDA/CUDA)
IN=588 Kb [ 1 3 224 224 ]    OUT=3136 Kb [ 1 64 112 112 ]    Weights(parameters): 37 Kb    MFLOPS=236.831
[ PERFSTAT ]    (samples=10   mean=3.73   median=3.75   min=3.63   stddev=0.06 (1.6%))
[       OK ] Conv.conv/114 (70 ms)
[ RUN      ] Conv.conv/115, where GetParam() = (GFLOPS=0.237, K=[7 x 7], IN={1, 3, 224, 224}, OCN=64, S=[2 x 2], P=[3 x 3], BIAS, OCV/CPU)
IN=588 Kb [ 1 3 224 224 ]    OUT=3136 Kb [ 1 64 112 112 ]    Weights(parameters): 37 Kb    MFLOPS=236.831
[ PERFSTAT ]    (samples=10   mean=11.76   median=11.74   min=11.69   stddev=0.07 (0.6%))
[       OK ] Conv.conv/115 (144 ms)
[ RUN      ] Conv.conv/116, where GetParam() = (GFLOPS=0.472, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, G=512, S=[2 x 2], P=[1 x 1], BIAS, CUDA/CUDA)
IN=722 Kb [ 1 512 19 19 ]    OUT=200 Kb [ 1 512 10 10 ]    Weights(parameters): 20 Kb    MFLOPS=471.91
[ PERFSTAT ]    (samples=10   mean=62.86   median=62.81   min=62.70   stddev=0.16 (0.3%))
[       OK ] Conv.conv/116 (722 ms)
[ RUN      ] Conv.conv/117, where GetParam() = (GFLOPS=0.472, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, G=512, S=[2 x 2], P=[1 x 1], BIAS, OCV/CPU)
IN=722 Kb [ 1 512 19 19 ]    OUT=200 Kb [ 1 512 10 10 ]    Weights(parameters): 20 Kb    MFLOPS=471.91
[ PERFSTAT ]    (samples=52   mean=0.82   median=0.80   min=0.79   stddev=0.02 (3.0%))
[       OK ] Conv.conv/117 (58 ms)
[ RUN      ] Conv.conv/118, where GetParam() = (GFLOPS=0.472, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, S=[2 x 2], PM=SAME, CUDA/CUDA)
IN=722 Kb [ 1 512 19 19 ]    OUT=200 Kb [ 1 512 10 10 ]    Weights(parameters): 9216 Kb    MFLOPS=471.91
[ PERFSTAT ]    (samples=10   mean=5.74   median=5.73   min=5.66   stddev=0.05 (0.9%))
[       OK ] Conv.conv/118 (119 ms)
[ RUN      ] Conv.conv/119, where GetParam() = (GFLOPS=0.472, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, S=[2 x 2], PM=SAME, OCV/CPU)
IN=722 Kb [ 1 512 19 19 ]    OUT=200 Kb [ 1 512 10 10 ]    Weights(parameters): 9216 Kb    MFLOPS=471.91
[ PERFSTAT ]    (samples=10   mean=32.83   median=32.85   min=32.74   stddev=0.05 (0.2%))
[       OK ] Conv.conv/119 (392 ms)
[ RUN      ] Conv.conv/120, where GetParam() = (GFLOPS=0.449, K=[3 x 3], IN={1, 384, 13, 13}, OCN=384, G=2, P=[1 x 1], BIAS, CUDA/CUDA)
IN=254 Kb [ 1 384 13 13 ]    OUT=254 Kb [ 1 384 13 13 ]    Weights(parameters): 2594 Kb    MFLOPS=448.626
[ PERFSTAT ]    (samples=10   mean=1.84   median=1.83   min=1.79   stddev=0.04 (2.0%))
[       OK ] Conv.conv/120 (60 ms)
[ RUN      ] Conv.conv/121, where GetParam() = (GFLOPS=0.449, K=[3 x 3], IN={1, 384, 13, 13}, OCN=384, G=2, P=[1 x 1], BIAS, OCV/CPU)
IN=254 Kb [ 1 384 13 13 ]    OUT=254 Kb [ 1 384 13 13 ]    Weights(parameters): 2594 Kb    MFLOPS=448.626
[ PERFSTAT ]    (samples=10   mean=13.26   median=13.26   min=13.16   stddev=0.06 (0.4%))
[       OK ] Conv.conv/121 (163 ms)
[ RUN      ] Conv.conv/122, where GetParam() = (GFLOPS=0.426, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, G=128, S=[2 x 2], P=[1 x 1], BIAS, CUDA/CUDA)
IN=2813 Kb [ 1 128 75 75 ]    OUT=722 Kb [ 1 128 38 38 ]    Weights(parameters): 5 Kb    MFLOPS=426.038
[ PERFSTAT ]    (samples=10   mean=8.42   median=8.41   min=8.32   stddev=0.07 (0.9%))
[       OK ] Conv.conv/122 (129 ms)
[ RUN      ] Conv.conv/123, where GetParam() = (GFLOPS=0.426, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, G=128, S=[2 x 2], P=[1 x 1], BIAS, OCV/CPU)
IN=2813 Kb [ 1 128 75 75 ]    OUT=722 Kb [ 1 128 38 38 ]    Weights(parameters): 5 Kb    MFLOPS=426.038
[ PERFSTAT ]    (samples=10   mean=3.44   median=3.41   min=3.33   stddev=0.10 (3.0%))
[       OK ] Conv.conv/123 (56 ms)
[ RUN      ] Conv.conv/124, where GetParam() = (GFLOPS=0.426, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, S=[2 x 2], PM=SAME, CUDA/CUDA)
IN=2813 Kb [ 1 128 75 75 ]    OUT=722 Kb [ 1 128 38 38 ]    Weights(parameters): 576 Kb    MFLOPS=426.038
[ PERFSTAT ]    (samples=10   mean=2.93   median=2.92   min=2.85   stddev=0.06 (2.0%))
[       OK ] Conv.conv/124 (70 ms)
[ RUN      ] Conv.conv/125, where GetParam() = (GFLOPS=0.426, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, S=[2 x 2], PM=SAME, OCV/CPU)
IN=2813 Kb [ 1 128 75 75 ]    OUT=722 Kb [ 1 128 38 38 ]    Weights(parameters): 576 Kb    MFLOPS=426.038
[ PERFSTAT ]    (samples=10   mean=26.19   median=26.21   min=26.09   stddev=0.06 (0.2%))
[       OK ] Conv.conv/125 (307 ms)
[ RUN      ] Conv.conv/126, where GetParam() = (GFLOPS=0.426, K=[3 x 3], IN={1, 128, 38, 38}, OCN=128, P=[1 x 1], CUDA/CUDA)
IN=722 Kb [ 1 128 38 38 ]    OUT=722 Kb [ 1 128 38 38 ]    Weights(parameters): 576 Kb    MFLOPS=426.038
[ PERFSTAT ]    (samples=10   mean=2.60   median=2.60   min=2.55   stddev=0.03 (1.2%))
[       OK ] Conv.conv/126 (61 ms)
[ RUN      ] Conv.conv/127, where GetParam() = (GFLOPS=0.426, K=[3 x 3], IN={1, 128, 38, 38}, OCN=128, P=[1 x 1], OCV/CPU)
IN=722 Kb [ 1 128 38 38 ]    OUT=722 Kb [ 1 128 38 38 ]    Weights(parameters): 576 Kb    MFLOPS=426.038
[ PERFSTAT ]    (samples=10   mean=24.65   median=24.63   min=24.55   stddev=0.11 (0.4%))
[       OK ] Conv.conv/127 (287 ms)
[ RUN      ] Conv.conv/128, where GetParam() = (GFLOPS=0.426, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, G=256, S=[2 x 2], P=[1 x 1], BIAS, CUDA/CUDA)
IN=1444 Kb [ 1 256 38 38 ]    OUT=361 Kb [ 1 256 19 19 ]    Weights(parameters): 10 Kb    MFLOPS=425.945
[ PERFSTAT ]    (samples=10   mean=31.74   median=31.71   min=31.52   stddev=0.16 (0.5%))
[       OK ] Conv.conv/128 (381 ms)
[ RUN      ] Conv.conv/129, where GetParam() = (GFLOPS=0.426, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, G=256, S=[2 x 2], P=[1 x 1], BIAS, OCV/CPU)
IN=1444 Kb [ 1 256 38 38 ]    OUT=361 Kb [ 1 256 19 19 ]    Weights(parameters): 10 Kb    MFLOPS=425.945
[ PERFSTAT ]    (samples=100   mean=1.36   median=1.35   min=1.30   stddev=0.04 (3.1%))
[       OK ] Conv.conv/129 (157 ms)
[ RUN      ] Conv.conv/130, where GetParam() = (GFLOPS=0.426, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, S=[2 x 2], PM=SAME, CUDA/CUDA)
IN=1444 Kb [ 1 256 38 38 ]    OUT=361 Kb [ 1 256 19 19 ]    Weights(parameters): 2304 Kb    MFLOPS=425.945
[ PERFSTAT ]    (samples=10   mean=5.06   median=5.05   min=4.98   stddev=0.05 (1.0%))
[       OK ] Conv.conv/130 (99 ms)
[ RUN      ] Conv.conv/131, where GetParam() = (GFLOPS=0.426, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, S=[2 x 2], PM=SAME, OCV/CPU)
IN=1444 Kb [ 1 256 38 38 ]    OUT=361 Kb [ 1 256 19 19 ]    Weights(parameters): 2304 Kb    MFLOPS=425.945
[ PERFSTAT ]    (samples=10   mean=25.94   median=25.92   min=25.87   stddev=0.08 (0.3%))
[       OK ] Conv.conv/131 (305 ms)
[ RUN      ] Conv.conv/132, where GetParam() = (GFLOPS=0.426, K=[3 x 3], IN={1, 256, 19, 19}, OCN=256, P=[1 x 1], CUDA/CUDA)
IN=361 Kb [ 1 256 19 19 ]    OUT=361 Kb [ 1 256 19 19 ]    Weights(parameters): 2304 Kb    MFLOPS=425.945
[ PERFSTAT ]    (samples=10   mean=3.47   median=3.46   min=3.44   stddev=0.03 (0.8%))
[       OK ] Conv.conv/132 (77 ms)
[ RUN      ] Conv.conv/133, where GetParam() = (GFLOPS=0.426, K=[3 x 3], IN={1, 256, 19, 19}, OCN=256, P=[1 x 1], OCV/CPU)
IN=361 Kb [ 1 256 19 19 ]    OUT=361 Kb [ 1 256 19 19 ]    Weights(parameters): 2304 Kb    MFLOPS=425.945
[ PERFSTAT ]    (samples=10   mean=25.09   median=25.08   min=24.99   stddev=0.06 (0.3%))
[       OK ] Conv.conv/133 (295 ms)
[ RUN      ] Conv.conv/134, where GetParam() = (GFLOPS=0.421, K=[1 x 1], IN={1, 576, 38, 50}, OCN=192, PM=SAME, BIAS, CUDA/CUDA)
IN=4275 Kb [ 1 576 38 50 ]    OUT=1425 Kb [ 1 192 38 50 ]    Weights(parameters): 433 Kb    MFLOPS=420.614
[ PERFSTAT ]    (samples=10   mean=3.71   median=3.70   min=3.58   stddev=0.10 (2.8%))
[       OK ] Conv.conv/134 (84 ms)
[ RUN      ] Conv.conv/135, where GetParam() = (GFLOPS=0.421, K=[1 x 1], IN={1, 576, 38, 50}, OCN=192, PM=SAME, BIAS, OCV/CPU)
IN=4275 Kb [ 1 576 38 50 ]    OUT=1425 Kb [ 1 192 38 50 ]    Weights(parameters): 433 Kb    MFLOPS=420.614
[ PERFSTAT ]    (samples=10   mean=25.96   median=25.98   min=25.70   stddev=0.13 (0.5%))
[       OK ] Conv.conv/135 (308 ms)
[ RUN      ] Conv.conv/136, where GetParam() = (GFLOPS=0.415, K=[3 x 3], IN={1, 32, 150, 150}, OCN=32, G=32, P=[1 x 1], BIAS, CUDA/CUDA)
IN=2813 Kb [ 1 32 150 150 ]    OUT=2813 Kb [ 1 32 150 150 ]    Weights(parameters): 2 Kb    MFLOPS=415.44
[ PERFSTAT ]    (samples=10   mean=33.06   median=33.19   min=32.31   stddev=0.53 (1.6%))
[       OK ] Conv.conv/136 (403 ms)
[ RUN      ] Conv.conv/137, where GetParam() = (GFLOPS=0.415, K=[3 x 3], IN={1, 32, 150, 150}, OCN=32, G=32, P=[1 x 1], BIAS, OCV/CPU)
IN=2813 Kb [ 1 32 150 150 ]    OUT=2813 Kb [ 1 32 150 150 ]    Weights(parameters): 2 Kb    MFLOPS=415.44
[ PERFSTAT ]    (samples=10   mean=7.96   median=7.97   min=7.78   stddev=0.09 (1.1%))
[       OK ] Conv.conv/137 (107 ms)
[ RUN      ] Conv.conv/138, where GetParam() = (GFLOPS=0.415, K=[3 x 3], IN={1, 64, 150, 150}, OCN=64, G=64, S=[2 x 2], P=[1 x 1], BIAS, CUDA/CUDA)
IN=5625 Kb [ 1 64 150 150 ]    OUT=1407 Kb [ 1 64 75 75 ]    Weights(parameters): 3 Kb    MFLOPS=415.08
[ PERFSTAT ]    (samples=10   mean=7.81   median=7.80   min=7.75   stddev=0.06 (0.8%))
[       OK ] Conv.conv/138 (133 ms)
[ RUN      ] Conv.conv/139, where GetParam() = (GFLOPS=0.415, K=[3 x 3], IN={1, 64, 150, 150}, OCN=64, G=64, S=[2 x 2], P=[1 x 1], BIAS, OCV/CPU)
IN=5625 Kb [ 1 64 150 150 ]    OUT=1407 Kb [ 1 64 75 75 ]    Weights(parameters): 3 Kb    MFLOPS=415.08
[ PERFSTAT ]    (samples=10   mean=7.14   median=7.14   min=7.06   stddev=0.07 (0.9%))
[       OK ] Conv.conv/139 (103 ms)
[ RUN      ] Conv.conv/140, where GetParam() = (GFLOPS=0.415, K=[3 x 3], IN={1, 64, 150, 150}, OCN=64, S=[2 x 2], PM=SAME, CUDA/CUDA)
IN=5625 Kb [ 1 64 150 150 ]    OUT=1407 Kb [ 1 64 75 75 ]    Weights(parameters): 144 Kb    MFLOPS=415.08
[ PERFSTAT ]    (samples=10   mean=4.75   median=4.74   min=4.67   stddev=0.05 (1.1%))
[       OK ] Conv.conv/140 (104 ms)
[ RUN      ] Conv.conv/141, where GetParam() = (GFLOPS=0.415, K=[3 x 3], IN={1, 64, 150, 150}, OCN=64, S=[2 x 2], PM=SAME, OCV/CPU)
IN=5625 Kb [ 1 64 150 150 ]    OUT=1407 Kb [ 1 64 75 75 ]    Weights(parameters): 144 Kb    MFLOPS=415.08
[ PERFSTAT ]    (samples=10   mean=27.61   median=27.63   min=27.36   stddev=0.14 (0.5%))
[       OK ] Conv.conv/141 (328 ms)
[ RUN      ] Conv.conv/142, where GetParam() = (GFLOPS=0.104, K=[1 x 1], IN={1, 64, 56, 56}, OCN=256, CUDA/CUDA)
IN=784 Kb [ 1 64 56 56 ]    OUT=3136 Kb [ 1 256 56 56 ]    Weights(parameters): 64 Kb    MFLOPS=103.563
[ PERFSTAT ]    (samples=10   mean=2.64   median=2.65   min=2.60   stddev=0.03 (1.1%))
[       OK ] Conv.conv/142 (60 ms)
[ RUN      ] Conv.conv/143, where GetParam() = (GFLOPS=0.104, K=[1 x 1], IN={1, 64, 56, 56}, OCN=256, OCV/CPU)
IN=784 Kb [ 1 64 56 56 ]    OUT=3136 Kb [ 1 256 56 56 ]    Weights(parameters): 64 Kb    MFLOPS=103.563
[ PERFSTAT ]    (samples=10   mean=5.27   median=5.23   min=5.20   stddev=0.08 (1.6%))
[       OK ] Conv.conv/143 (73 ms)
[ RUN      ] Conv.conv/144, where GetParam() = (GFLOPS=0.103, K=[1 x 1], IN={1, 128, 28, 28}, OCN=512, CUDA/CUDA)
IN=392 Kb [ 1 128 28 28 ]    OUT=1568 Kb [ 1 512 28 28 ]    Weights(parameters): 256 Kb    MFLOPS=103.162
[ PERFSTAT ]    (samples=10   mean=1.73   median=1.73   min=1.69   stddev=0.02 (1.3%))
[       OK ] Conv.conv/144 (49 ms)
[ RUN      ] Conv.conv/145, where GetParam() = (GFLOPS=0.103, K=[1 x 1], IN={1, 128, 28, 28}, OCN=512, OCV/CPU)
IN=392 Kb [ 1 128 28 28 ]    OUT=1568 Kb [ 1 512 28 28 ]    Weights(parameters): 256 Kb    MFLOPS=103.162
[ PERFSTAT ]    (samples=10   mean=5.82   median=5.80   min=5.70   stddev=0.08 (1.4%))
[       OK ] Conv.conv/145 (79 ms)
[ RUN      ] Conv.conv/146, where GetParam() = (GFLOPS=0.376, K=[1 x 1], IN={1, 24, 300, 400}, OCN=64, PM=VALID, BIAS, CUDA/CUDA)
IN=11250 Kb [ 1 24 300 400 ]    OUT=30000 Kb [ 1 64 300 400 ]    Weights(parameters): 7 Kb    MFLOPS=376.32
[ PERFSTAT ]    (samples=10   mean=22.58   median=22.59   min=22.54   stddev=0.03 (0.2%))
[       OK ] Conv.conv/146 (336 ms)
[ RUN      ] Conv.conv/147, where GetParam() = (GFLOPS=0.376, K=[1 x 1], IN={1, 24, 300, 400}, OCN=64, PM=VALID, BIAS, OCV/CPU)
IN=11250 Kb [ 1 24 300 400 ]    OUT=30000 Kb [ 1 64 300 400 ]    Weights(parameters): 7 Kb    MFLOPS=376.32
[ PERFSTAT ]    (samples=10   mean=25.45   median=25.48   min=25.24   stddev=0.14 (0.6%))
[       OK ] Conv.conv/147 (316 ms)
[ RUN      ] Conv.conv/148, where GetParam() = (GFLOPS=0.347, K=[3 x 3], IN={1, 128, 28, 28}, OCN=192, P=[1 x 1], BIAS, CUDA/CUDA)
IN=392 Kb [ 1 128 28 28 ]    OUT=588 Kb [ 1 192 28 28 ]    Weights(parameters): 865 Kb    MFLOPS=346.967
[ PERFSTAT ]    (samples=10   mean=2.20   median=2.20   min=2.17   stddev=0.03 (1.2%))
[       OK ] Conv.conv/148 (57 ms)
[ RUN      ] Conv.conv/149, where GetParam() = (GFLOPS=0.347, K=[3 x 3], IN={1, 128, 28, 28}, OCN=192, P=[1 x 1], BIAS, OCV/CPU)
IN=392 Kb [ 1 128 28 28 ]    OUT=588 Kb [ 1 192 28 28 ]    Weights(parameters): 865 Kb    MFLOPS=346.967
[ PERFSTAT ]    (samples=10   mean=19.68   median=19.67   min=19.61   stddev=0.07 (0.3%))
[       OK ] Conv.conv/149 (232 ms)
[ RUN      ] Conv.conv/150, where GetParam() = (GFLOPS=0.347, K=[3 x 3], IN={1, 128, 28, 28}, OCN=192, PM=SAME, BIAS, CUDA/CUDA)
IN=392 Kb [ 1 128 28 28 ]    OUT=588 Kb [ 1 192 28 28 ]    Weights(parameters): 865 Kb    MFLOPS=346.967
[ PERFSTAT ]    (samples=10   mean=2.19   median=2.19   min=2.16   stddev=0.02 (1.0%))
[       OK ] Conv.conv/150 (57 ms)
[ RUN      ] Conv.conv/151, where GetParam() = (GFLOPS=0.347, K=[3 x 3], IN={1, 128, 28, 28}, OCN=192, PM=SAME, BIAS, OCV/CPU)
IN=392 Kb [ 1 128 28 28 ]    OUT=588 Kb [ 1 192 28 28 ]    Weights(parameters): 865 Kb    MFLOPS=346.967
[ PERFSTAT ]    (samples=10   mean=19.66   median=19.63   min=19.54   stddev=0.11 (0.5%))
[       OK ] Conv.conv/151 (232 ms)
[ RUN      ] Conv.conv/152, where GetParam() = (GFLOPS=0.014, K=[3 x 3], IN={1, 128, 14, 14}, OCN=32, P=[1 x 1], CUDA/CUDA)
IN=98 Kb [ 1 128 14 14 ]    OUT=25 Kb [ 1 32 14 14 ]    Weights(parameters): 144 Kb    MFLOPS=14.457
[ PERFSTAT ]    (samples=50   mean=0.24   median=0.24   min=0.23   stddev=0.01 (2.7%))
[       OK ] Conv.conv/152 (40 ms)
[ RUN      ] Conv.conv/153, where GetParam() = (GFLOPS=0.014, K=[3 x 3], IN={1, 128, 14, 14}, OCN=32, P=[1 x 1], OCV/CPU)
IN=98 Kb [ 1 128 14 14 ]    OUT=25 Kb [ 1 32 14 14 ]    Weights(parameters): 144 Kb    MFLOPS=14.457
[ PERFSTAT ]    (samples=13   mean=1.08   median=1.07   min=1.05   stddev=0.03 (2.5%))
[       OK ] Conv.conv/153 (29 ms)
[ RUN      ] Conv.conv/154, where GetParam() = (GFLOPS=0.053, K=[1 x 1], IN={1, 576, 19, 19}, OCN=128, PM=SAME, BIAS, CUDA/CUDA)
IN=813 Kb [ 1 576 19 19 ]    OUT=181 Kb [ 1 128 19 19 ]    Weights(parameters): 289 Kb    MFLOPS=53.2778
[ PERFSTAT ]    (samples=38   mean=0.59   median=0.59   min=0.57   stddev=0.01 (2.5%))
[       OK ] Conv.conv/154 (54 ms)
[ RUN      ] Conv.conv/155, where GetParam() = (GFLOPS=0.053, K=[1 x 1], IN={1, 576, 19, 19}, OCN=128, PM=SAME, BIAS, OCV/CPU)
IN=813 Kb [ 1 576 19 19 ]    OUT=181 Kb [ 1 128 19 19 ]    Weights(parameters): 289 Kb    MFLOPS=53.2778
[ PERFSTAT ]    (samples=13   mean=3.03   median=2.99   min=2.96   stddev=0.08 (2.6%))
[       OK ] Conv.conv/155 (59 ms)
[ RUN      ] Conv.conv/156, where GetParam() = (GFLOPS=0.319, K=[3 x 3], IN={1, 192, 19, 19}, OCN=256, PM=SAME, BIAS, CUDA/CUDA)
IN=271 Kb [ 1 192 19 19 ]    OUT=361 Kb [ 1 256 19 19 ]    Weights(parameters): 1729 Kb    MFLOPS=319.482
[ PERFSTAT ]    (samples=10   mean=2.85   median=2.87   min=2.80   stddev=0.03 (1.1%))
[       OK ] Conv.conv/156 (66 ms)
[ RUN      ] Conv.conv/157, where GetParam() = (GFLOPS=0.319, K=[3 x 3], IN={1, 192, 19, 19}, OCN=256, PM=SAME, BIAS, OCV/CPU)
IN=271 Kb [ 1 192 19 19 ]    OUT=361 Kb [ 1 256 19 19 ]    Weights(parameters): 1729 Kb    MFLOPS=319.482
[ PERFSTAT ]    (samples=10   mean=18.73   median=18.72   min=18.65   stddev=0.06 (0.3%))
[       OK ] Conv.conv/157 (223 ms)
[ RUN      ] Conv.conv/158, where GetParam() = (GFLOPS=0.315, K=[3 x 3], IN={1, 96, 75, 100}, OCN=96, S=[2 x 2], PM=SAME, BIAS, CUDA/CUDA)
IN=2813 Kb [ 1 96 75 100 ]    OUT=713 Kb [ 1 96 38 50 ]    Weights(parameters): 325 Kb    MFLOPS=315.37
[ PERFSTAT ]    (samples=10   mean=3.61   median=3.59   min=3.53   stddev=0.09 (2.5%))
[       OK ] Conv.conv/158 (81 ms)
[ RUN      ] Conv.conv/159, where GetParam() = (GFLOPS=0.315, K=[3 x 3], IN={1, 96, 75, 100}, OCN=96, S=[2 x 2], PM=SAME, BIAS, OCV/CPU)
IN=2813 Kb [ 1 96 75 100 ]    OUT=713 Kb [ 1 96 38 50 ]    Weights(parameters): 325 Kb    MFLOPS=315.37
[ PERFSTAT ]    (samples=25   mean=19.47   median=19.43   min=19.27   stddev=0.21 (1.1%))
[       OK ] Conv.conv/159 (559 ms)
[ RUN      ] Conv.conv/160, where GetParam() = (GFLOPS=0.103, K=[1 x 1], IN={1, 512, 7, 7}, OCN=2048, CUDA/CUDA)
IN=98 Kb [ 1 512 7 7 ]    OUT=392 Kb [ 1 2048 7 7 ]    Weights(parameters): 4096 Kb    MFLOPS=102.861
[ PERFSTAT ]    (samples=10   mean=1.78   median=1.77   min=1.74   stddev=0.04 (2.1%))
[       OK ] Conv.conv/160 (57 ms)
[ RUN      ] Conv.conv/161, where GetParam() = (GFLOPS=0.103, K=[1 x 1], IN={1, 512, 7, 7}, OCN=2048, OCV/CPU)
IN=98 Kb [ 1 512 7 7 ]    OUT=392 Kb [ 1 2048 7 7 ]    Weights(parameters): 4096 Kb    MFLOPS=102.861
[ PERFSTAT ]    (samples=10   mean=10.88   median=10.82   min=10.70   stddev=0.20 (1.9%))
[       OK ] Conv.conv/161 (140 ms)
[ RUN      ] Conv.conv/162, where GetParam() = (GFLOPS=0.103, K=[1 x 1], IN={1, 512, 28, 28}, OCN=128, CUDA/CUDA)
IN=1568 Kb [ 1 512 28 28 ]    OUT=392 Kb [ 1 128 28 28 ]    Weights(parameters): 256 Kb    MFLOPS=102.861
[ PERFSTAT ]    (samples=10   mean=1.55   median=1.53   min=1.52   stddev=0.03 (1.8%))
[       OK ] Conv.conv/162 (48 ms)
[ RUN      ] Conv.conv/163, where GetParam() = (GFLOPS=0.103, K=[1 x 1], IN={1, 512, 28, 28}, OCN=128, OCV/CPU)
IN=1568 Kb [ 1 512 28 28 ]    OUT=392 Kb [ 1 128 28 28 ]    Weights(parameters): 256 Kb    MFLOPS=102.861
[ PERFSTAT ]    (samples=10   mean=5.71   median=5.71   min=5.61   stddev=0.09 (1.5%))
[       OK ] Conv.conv/163 (80 ms)
[ RUN      ] Conv.conv/164, where GetParam() = (GFLOPS=0.308, K=[1 x 1], IN={1, 320, 75, 100}, OCN=64, PM=SAME, BIAS, CUDA/CUDA)
IN=9375 Kb [ 1 320 75 100 ]    OUT=1875 Kb [ 1 64 75 100 ]    Weights(parameters): 81 Kb    MFLOPS=307.68
[ PERFSTAT ]    (samples=100   mean=3.76   median=3.77   min=3.28   stddev=0.17 (4.4%))
[       OK ] Conv.conv/164 (442 ms)
[ RUN      ] Conv.conv/165, where GetParam() = (GFLOPS=0.308, K=[1 x 1], IN={1, 320, 75, 100}, OCN=64, PM=SAME, BIAS, OCV/CPU)
IN=9375 Kb [ 1 320 75 100 ]    OUT=1875 Kb [ 1 64 75 100 ]    Weights(parameters): 81 Kb    MFLOPS=307.68
[ PERFSTAT ]    (samples=10   mean=22.43   median=22.43   min=22.31   stddev=0.09 (0.4%))
[       OK ] Conv.conv/165 (279 ms)
[ RUN      ] Conv.conv/166, where GetParam() = (GFLOPS=0.299, K=[3 x 3], IN={1, 256, 13, 13}, OCN=384, P=[1 x 1], BIAS, CUDA/CUDA)
IN=169 Kb [ 1 256 13 13 ]    OUT=254 Kb [ 1 384 13 13 ]    Weights(parameters): 3458 Kb    MFLOPS=299.106
[ PERFSTAT ]    (samples=10   mean=2.29   median=2.29   min=2.26   stddev=0.02 (1.0%))
[       OK ] Conv.conv/166 (69 ms)
[ RUN      ] Conv.conv/167, where GetParam() = (GFLOPS=0.299, K=[3 x 3], IN={1, 256, 13, 13}, OCN=384, P=[1 x 1], BIAS, OCV/CPU)
IN=169 Kb [ 1 256 13 13 ]    OUT=254 Kb [ 1 384 13 13 ]    Weights(parameters): 3458 Kb    MFLOPS=299.106
[ PERFSTAT ]    (samples=10   mean=18.68   median=18.67   min=18.65   stddev=0.03 (0.2%))
[       OK ] Conv.conv/167 (225 ms)
[ RUN      ] Conv.conv/168, where GetParam() = (GFLOPS=0.299, K=[3 x 3], IN={1, 384, 13, 13}, OCN=256, G=2, P=[1 x 1], BIAS, CUDA/CUDA)
IN=254 Kb [ 1 384 13 13 ]    OUT=169 Kb [ 1 256 13 13 ]    Weights(parameters): 1729 Kb    MFLOPS=299.084
[ PERFSTAT ]    (samples=10   mean=1.25   median=1.25   min=1.22   stddev=0.03 (2.2%))
[       OK ] Conv.conv/168 (49 ms)
[ RUN      ] Conv.conv/169, where GetParam() = (GFLOPS=0.299, K=[3 x 3], IN={1, 384, 13, 13}, OCN=256, G=2, P=[1 x 1], BIAS, OCV/CPU)
IN=254 Kb [ 1 384 13 13 ]    OUT=169 Kb [ 1 256 13 13 ]    Weights(parameters): 1729 Kb    MFLOPS=299.084
[ PERFSTAT ]    (samples=10   mean=8.84   median=8.83   min=8.78   stddev=0.06 (0.6%))
[       OK ] Conv.conv/169 (114 ms)
[ RUN      ] Conv.conv/170, where GetParam() = (GFLOPS=0.017, K=[1 x 1], IN={1, 32, 32, 64}, OCN=128, CUDA/CUDA)
IN=256 Kb [ 1 32 32 64 ]    OUT=1024 Kb [ 1 128 32 64 ]    Weights(parameters): 16 Kb    MFLOPS=17.0394
[ PERFSTAT ]    (samples=13   mean=0.91   median=0.90   min=0.88   stddev=0.03 (2.9%))
[       OK ] Conv.conv/170 (41 ms)
[ RUN      ] Conv.conv/171, where GetParam() = (GFLOPS=0.017, K=[1 x 1], IN={1, 32, 32, 64}, OCN=128, OCV/CPU)
IN=256 Kb [ 1 32 32 64 ]    OUT=1024 Kb [ 1 128 32 64 ]    Weights(parameters): 16 Kb    MFLOPS=17.0394
[ PERFSTAT ]    (samples=13   mean=1.12   median=1.12   min=1.09   stddev=0.02 (1.6%))
[       OK ] Conv.conv/171 (30 ms)
[ RUN      ] Conv.conv/172, where GetParam() = (GFLOPS=0.017, K=[1 x 1], IN={1, 128, 32, 64}, OCN=32, CUDA/CUDA)
IN=1024 Kb [ 1 128 32 64 ]    OUT=256 Kb [ 1 32 32 64 ]    Weights(parameters): 16 Kb    MFLOPS=16.8428
[ PERFSTAT ]    (samples=38   mean=0.44   median=0.45   min=0.42   stddev=0.01 (2.8%))
[       OK ] Conv.conv/172 (48 ms)
[ RUN      ] Conv.conv/173, where GetParam() = (GFLOPS=0.017, K=[1 x 1], IN={1, 128, 32, 64}, OCN=32, OCV/CPU)
IN=1024 Kb [ 1 128 32 64 ]    OUT=256 Kb [ 1 32 32 64 ]    Weights(parameters): 16 Kb    MFLOPS=16.8428
[ PERFSTAT ]    (samples=100   mean=1.54   median=1.55   min=1.39   stddev=0.06 (4.1%))
[       OK ] Conv.conv/173 (175 ms)
[ RUN      ] Conv.conv/174, where GetParam() = (GFLOPS=0.133, K=[3 x 3], IN={1, 128, 19, 19}, OCN=160, PM=SAME, BIAS, CUDA/CUDA)
IN=181 Kb [ 1 128 19 19 ]    OUT=226 Kb [ 1 160 19 19 ]    Weights(parameters): 721 Kb    MFLOPS=133.137
[ PERFSTAT ]    (samples=10   mean=1.37   median=1.37   min=1.33   stddev=0.04 (2.7%))
[       OK ] Conv.conv/174 (46 ms)
[ RUN      ] Conv.conv/175, where GetParam() = (GFLOPS=0.133, K=[3 x 3], IN={1, 128, 19, 19}, OCN=160, PM=SAME, BIAS, OCV/CPU)
IN=181 Kb [ 1 128 19 19 ]    OUT=226 Kb [ 1 160 19 19 ]    Weights(parameters): 721 Kb    MFLOPS=133.137
[ PERFSTAT ]    (samples=38   mean=7.70   median=7.68   min=7.60   stddev=0.07 (0.9%))
[       OK ] Conv.conv/175 (332 ms)
[ RUN      ] Conv.conv/176, where GetParam() = (GFLOPS=0.038, K=[3 x 3], IN={1, 16, 64, 128}, OCN=16, P=[1 x 1], BIAS, CUDA/CUDA)
IN=512 Kb [ 1 16 64 128 ]    OUT=512 Kb [ 1 16 64 128 ]    Weights(parameters): 10 Kb    MFLOPS=37.8798
[ PERFSTAT ]    (samples=11   mean=1.06   median=1.06   min=1.04   stddev=0.03 (3.0%))
[       OK ] Conv.conv/176 (41 ms)
[ RUN      ] Conv.conv/177, where GetParam() = (GFLOPS=0.038, K=[3 x 3], IN={1, 16, 64, 128}, OCN=16, P=[1 x 1], BIAS, OCV/CPU)
IN=512 Kb [ 1 16 64 128 ]    OUT=512 Kb [ 1 16 64 128 ]    Weights(parameters): 10 Kb    MFLOPS=37.8798
[ PERFSTAT ]    (samples=10   mean=2.74   median=2.74   min=2.68   stddev=0.05 (1.9%))
[       OK ] Conv.conv/177 (45 ms)
[ RUN      ] Conv.conv/178, where GetParam() = (GFLOPS=0.126, K=[3 x 3], IN={1, 512, 5, 5}, OCN=546, PM=SAME, BIAS, CUDA/CUDA)
IN=50 Kb [ 1 512 5 5 ]    OUT=54 Kb [ 1 546 5 5 ]    Weights(parameters): 9831 Kb    MFLOPS=125.812
[ PERFSTAT ]    (samples=10   mean=4.07   median=4.07   min=4.02   stddev=0.03 (0.8%))
[       OK ] Conv.conv/178 (118 ms)
[ RUN      ] Conv.conv/179, where GetParam() = (GFLOPS=0.126, K=[3 x 3], IN={1, 512, 5, 5}, OCN=546, PM=SAME, BIAS, OCV/CPU)
IN=50 Kb [ 1 512 5 5 ]    OUT=54 Kb [ 1 546 5 5 ]    Weights(parameters): 9831 Kb    MFLOPS=125.812
[ PERFSTAT ]    (samples=10   mean=9.05   median=8.99   min=8.89   stddev=0.18 (2.0%))
[       OK ] Conv.conv/179 (130 ms)
[ RUN      ] Conv.conv/180, where GetParam() = (GFLOPS=0.248, K=[1 x 1], IN={1, 64, 150, 200}, OCN=64, PM=SAME, BIAS, CUDA/CUDA)
IN=7500 Kb [ 1 64 150 200 ]    OUT=7500 Kb [ 1 64 150 200 ]    Weights(parameters): 17 Kb    MFLOPS=247.68
[ PERFSTAT ]    (samples=100   mean=6.99   median=6.83   min=6.48   stddev=0.48 (6.9%))
[       OK ] Conv.conv/180 (782 ms)
[ RUN      ] Conv.conv/181, where GetParam() = (GFLOPS=0.248, K=[1 x 1], IN={1, 64, 150, 200}, OCN=64, PM=SAME, BIAS, OCV/CPU)
IN=7500 Kb [ 1 64 150 200 ]    OUT=7500 Kb [ 1 64 150 200 ]    Weights(parameters): 17 Kb    MFLOPS=247.68
[ PERFSTAT ]    (samples=13   mean=13.53   median=13.55   min=13.39   stddev=0.07 (0.5%))
[       OK ] Conv.conv/181 (219 ms)
[ RUN      ] Conv.conv/182, where GetParam() = (GFLOPS=0.040, K=[1 x 1], IN={1, 576, 19, 19}, OCN=96, PM=SAME, BIAS, CUDA/CUDA)
IN=813 Kb [ 1 576 19 19 ]    OUT=136 Kb [ 1 96 19 19 ]    Weights(parameters): 217 Kb    MFLOPS=39.9584
[ PERFSTAT ]    (samples=16   mean=0.55   median=0.55   min=0.54   stddev=0.02 (3.0%))
[       OK ] Conv.conv/182 (40 ms)
[ RUN      ] Conv.conv/183, where GetParam() = (GFLOPS=0.040, K=[1 x 1], IN={1, 576, 19, 19}, OCN=96, PM=SAME, BIAS, OCV/CPU)
IN=813 Kb [ 1 576 19 19 ]    OUT=136 Kb [ 1 96 19 19 ]    Weights(parameters): 217 Kb    MFLOPS=39.9584
[ PERFSTAT ]    (samples=10   mean=2.31   median=2.28   min=2.24   stddev=0.07 (2.8%))
[       OK ] Conv.conv/183 (41 ms)
[ RUN      ] Conv.conv/184, where GetParam() = (GFLOPS=0.080, K=[3 x 3], IN={1, 96, 19, 19}, OCN=128, PM=SAME, BIAS, CUDA/CUDA)
IN=136 Kb [ 1 96 19 19 ]    OUT=181 Kb [ 1 128 19 19 ]    Weights(parameters): 433 Kb    MFLOPS=79.8936
[ PERFSTAT ]    (samples=10   mean=0.92   median=0.91   min=0.90   stddev=0.02 (2.0%))
[       OK ] Conv.conv/184 (40 ms)
[ RUN      ] Conv.conv/185, where GetParam() = (GFLOPS=0.080, K=[3 x 3], IN={1, 96, 19, 19}, OCN=128, PM=SAME, BIAS, OCV/CPU)
IN=136 Kb [ 1 96 19 19 ]    OUT=181 Kb [ 1 128 19 19 ]    Weights(parameters): 433 Kb    MFLOPS=79.8936
[ PERFSTAT ]    (samples=10   mean=4.55   median=4.53   min=4.49   stddev=0.05 (1.2%))
[       OK ] Conv.conv/185 (64 ms)
[ RUN      ] Conv.conv/186, where GetParam() = (GFLOPS=0.240, K=[3 x 3], IN={1, 192, 38, 38}, OCN=192, S=[2 x 2], PM=SAME, CUDA/CUDA)
IN=1083 Kb [ 1 192 38 38 ]    OUT=271 Kb [ 1 192 19 19 ]    Weights(parameters): 1296 Kb    MFLOPS=239.612
[ PERFSTAT ]    (samples=10   mean=2.21   median=2.21   min=2.16   stddev=0.03 (1.3%))
[       OK ] Conv.conv/186 (63 ms)
[ RUN      ] Conv.conv/187, where GetParam() = (GFLOPS=0.240, K=[3 x 3], IN={1, 192, 38, 38}, OCN=192, S=[2 x 2], PM=SAME, OCV/CPU)
IN=1083 Kb [ 1 192 38 38 ]    OUT=271 Kb [ 1 192 19 19 ]    Weights(parameters): 1296 Kb    MFLOPS=239.612
[ PERFSTAT ]    (samples=10   mean=14.58   median=14.58   min=14.43   stddev=0.09 (0.6%))
[       OK ] Conv.conv/187 (178 ms)
[ RUN      ] Conv.conv/188, where GetParam() = (GFLOPS=0.240, K=[3 x 3], IN={1, 192, 19, 19}, OCN=192, PM=SAME, BIAS, CUDA/CUDA)
IN=271 Kb [ 1 192 19 19 ]    OUT=271 Kb [ 1 192 19 19 ]    Weights(parameters): 1297 Kb    MFLOPS=239.612
[ PERFSTAT ]    (samples=10   mean=2.19   median=2.19   min=2.13   stddev=0.03 (1.6%))
[       OK ] Conv.conv/188 (57 ms)
[ RUN      ] Conv.conv/189, where GetParam() = (GFLOPS=0.240, K=[3 x 3], IN={1, 192, 19, 19}, OCN=192, PM=SAME, BIAS, OCV/CPU)
IN=271 Kb [ 1 192 19 19 ]    OUT=271 Kb [ 1 192 19 19 ]    Weights(parameters): 1297 Kb    MFLOPS=239.612
[ PERFSTAT ]    (samples=10   mean=13.95   median=13.94   min=13.82   stddev=0.07 (0.5%))
[       OK ] Conv.conv/189 (170 ms)
[ RUN      ] Conv.conv/190, where GetParam() = (GFLOPS=0.237, K=[7 x 7], IN={1, 3, 224, 224}, OCN=64, S=[2 x 2], P=[3 x 3], CUDA/CUDA)
IN=588 Kb [ 1 3 224 224 ]    OUT=3136 Kb [ 1 64 112 112 ]    Weights(parameters): 37 Kb    MFLOPS=236.831
[ PERFSTAT ]    (samples=10   mean=3.38   median=3.35   min=3.32   stddev=0.06 (1.8%))
[       OK ] Conv.conv/190 (66 ms)
[ RUN      ] Conv.conv/191, where GetParam() = (GFLOPS=0.237, K=[7 x 7], IN={1, 3, 224, 224}, OCN=64, S=[2 x 2], P=[3 x 3], OCV/CPU)
IN=588 Kb [ 1 3 224 224 ]    OUT=3136 Kb [ 1 64 112 112 ]    Weights(parameters): 37 Kb    MFLOPS=236.831
[ PERFSTAT ]    (samples=10   mean=11.95   median=11.96   min=11.74   stddev=0.11 (0.9%))
[       OK ] Conv.conv/191 (147 ms)
[ RUN      ] Conv.conv/192, where GetParam() = (GFLOPS=0.237, K=[7 x 7], IN={1, 3, 224, 224}, OCN=64, S=[2 x 2], PM=SAME, BIAS, CUDA/CUDA)
IN=588 Kb [ 1 3 224 224 ]    OUT=3136 Kb [ 1 64 112 112 ]    Weights(parameters): 37 Kb    MFLOPS=236.831
[ PERFSTAT ]    (samples=10   mean=3.83   median=3.84   min=3.75   stddev=0.06 (1.5%))
[       OK ] Conv.conv/192 (74 ms)
[ RUN      ] Conv.conv/193, where GetParam() = (GFLOPS=0.237, K=[7 x 7], IN={1, 3, 224, 224}, OCN=64, S=[2 x 2], PM=SAME, BIAS, OCV/CPU)
IN=588 Kb [ 1 3 224 224 ]    OUT=3136 Kb [ 1 64 112 112 ]    Weights(parameters): 37 Kb    MFLOPS=236.831
[ PERFSTAT ]    (samples=10   mean=11.90   median=11.91   min=11.73   stddev=0.10 (0.8%))
[       OK ] Conv.conv/193 (146 ms)
[ RUN      ] Conv.conv/194, where GetParam() = (GFLOPS=0.111, K=[3 x 3], IN={1, 192, 10, 10}, OCN=320, PM=SAME, BIAS, CUDA/CUDA)
IN=75 Kb [ 1 192 10 10 ]    OUT=125 Kb [ 1 320 10 10 ]    Weights(parameters): 2162 Kb    MFLOPS=110.624
[ PERFSTAT ]    (samples=10   mean=1.47   median=1.47   min=1.44   stddev=0.02 (1.5%))
[       OK ] Conv.conv/194 (53 ms)
[ RUN      ] Conv.conv/195, where GetParam() = (GFLOPS=0.111, K=[3 x 3], IN={1, 192, 10, 10}, OCN=320, PM=SAME, BIAS, OCV/CPU)
IN=75 Kb [ 1 192 10 10 ]    OUT=125 Kb [ 1 320 10 10 ]    Weights(parameters): 2162 Kb    MFLOPS=110.624
[ PERFSTAT ]    (samples=10   mean=7.33   median=7.31   min=7.27   stddev=0.06 (0.8%))
[       OK ] Conv.conv/195 (97 ms)
[ RUN      ] Conv.conv/196, where GetParam() = (GFLOPS=0.213, K=[3 x 3], IN={1, 128, 38, 38}, OCN=256, S=[2 x 2], P=[1 x 1], CUDA/CUDA)
IN=722 Kb [ 1 128 38 38 ]    OUT=361 Kb [ 1 256 19 19 ]    Weights(parameters): 1152 Kb    MFLOPS=213.019
[ PERFSTAT ]    (samples=10   mean=1.52   median=1.52   min=1.49   stddev=0.03 (2.0%))
[       OK ] Conv.conv/196 (49 ms)
[ RUN      ] Conv.conv/197, where GetParam() = (GFLOPS=0.213, K=[3 x 3], IN={1, 128, 38, 38}, OCN=256, S=[2 x 2], P=[1 x 1], OCV/CPU)
IN=722 Kb [ 1 128 38 38 ]    OUT=361 Kb [ 1 256 19 19 ]    Weights(parameters): 1152 Kb    MFLOPS=213.019
[ PERFSTAT ]    (samples=10   mean=12.63   median=12.64   min=12.58   stddev=0.03 (0.2%))
[       OK ] Conv.conv/197 (156 ms)
[ RUN      ] Conv.conv/198, where GetParam() = (GFLOPS=0.213, K=[3 x 3], IN={1, 128, 19, 19}, OCN=256, D=[2 x 2], P=[2 x 2], CUDA/CUDA)
IN=181 Kb [ 1 128 19 19 ]    OUT=361 Kb [ 1 256 19 19 ]    Weights(parameters): 1152 Kb    MFLOPS=213.019
[ PERFSTAT ]    (samples=10   mean=2.21   median=2.21   min=2.17   stddev=0.03 (1.4%))
[       OK ] Conv.conv/198 (55 ms)
[ RUN      ] Conv.conv/199, where GetParam() = (GFLOPS=0.213, K=[3 x 3], IN={1, 128, 19, 19}, OCN=256, D=[2 x 2], P=[2 x 2], OCV/CPU)
IN=181 Kb [ 1 128 19 19 ]    OUT=361 Kb [ 1 256 19 19 ]    Weights(parameters): 1152 Kb    MFLOPS=213.019
[ PERFSTAT ]    (samples=10   mean=12.28   median=12.27   min=12.22   stddev=0.04 (0.3%))
[       OK ] Conv.conv/199 (151 ms)
[----------] 200 tests from Conv (90897 ms total)

[----------] 32 tests from Conv3D
[ RUN      ] Conv3D.conv3d/0, where GetParam() = (GFLOPS=0.027, K=[3 x 3 x 3], IN={1, 6, 10, 38, 50}, OCN=6, PM=VALID, BIAS, CUDA/CUDA)
IN=446 Kb [ 1 6 10 38 50 ]    OUT=324 Kb [ 1 6 8 36 48 ]    Weights(parameters): 4 Kb    MFLOPS=26.9568
[ PERFSTAT ]    (samples=10   mean=2.09   median=2.08   min=2.04   stddev=0.05 (2.2%))
[       OK ] Conv3D.conv3d/0 (51 ms)
[ RUN      ] Conv3D.conv3d/1, where GetParam() = (GFLOPS=0.027, K=[3 x 3 x 3], IN={1, 6, 10, 38, 50}, OCN=6, PM=VALID, BIAS, OCV/CPU)
IN=446 Kb [ 1 6 10 38 50 ]    OUT=324 Kb [ 1 6 8 36 48 ]    Weights(parameters): 4 Kb    MFLOPS=26.9568
[ PERFSTAT ]    (samples=10   mean=4.07   median=4.05   min=4.01   stddev=0.06 (1.6%))
[       OK ] Conv3D.conv3d/1 (59 ms)
[ RUN      ] Conv3D.conv3d/2, where GetParam() = (GFLOPS=0.000, K=[3 x 3 x 3], IN={1, 2, 19, 19, 19}, OCN=2, G=2, S=[2 x 2 x 2], P=(1, 1) x (1, 1) x (1, 1), BIAS, CUDA/CUDA)
IN=54 Kb [ 1 2 19 19 19 ]    OUT=8 Kb [ 1 2 10 10 10 ]    Weights(parameters): 1 Kb    MFLOPS=0.218
[ PERFSTAT ]    (samples=58   mean=0.28   median=0.27   min=0.26   stddev=0.01 (3.0%))
[       OK ] Conv3D.conv3d/2 (43 ms)
[ RUN      ] Conv3D.conv3d/3, where GetParam() = (GFLOPS=0.000, K=[3 x 3 x 3], IN={1, 2, 19, 19, 19}, OCN=2, G=2, S=[2 x 2 x 2], P=(1, 1) x (1, 1) x (1, 1), BIAS, OCV/CPU)
IN=54 Kb [ 1 2 19 19 19 ]    OUT=8 Kb [ 1 2 10 10 10 ]    Weights(parameters): 1 Kb    MFLOPS=0.218
[ PERFSTAT ]    (samples=75   mean=0.15   median=0.15   min=0.15   stddev=0.00 (1.8%))
[       OK ] Conv3D.conv3d/3 (25 ms)
[ RUN      ] Conv3D.conv3d/4, where GetParam() = (GFLOPS=0.001, K=[3 x 3 x 3], IN={1, 2, 25, 19, 19}, OCN=2, G=2, S=[1 x 2 x 2], P=(2, 2) x (2, 2) x (2, 2), PM=SAME, CUDA/CUDA)
IN=71 Kb [ 1 2 25 19 19 ]    OUT=20 Kb [ 1 2 25 10 10 ]    Weights(parameters): 1 Kb    MFLOPS=0.545
[ PERFSTAT ]    (samples=100   mean=0.41   median=0.41   min=0.37   stddev=0.02 (4.5%))
[       OK ] Conv3D.conv3d/4 (69 ms)
[ RUN      ] Conv3D.conv3d/5, where GetParam() = (GFLOPS=0.001, K=[3 x 3 x 3], IN={1, 2, 25, 19, 19}, OCN=2, G=2, S=[1 x 2 x 2], P=(2, 2) x (2, 2) x (2, 2), PM=SAME, OCV/CPU)
IN=71 Kb [ 1 2 25 19 19 ]    OUT=20 Kb [ 1 2 25 10 10 ]    Weights(parameters): 1 Kb    MFLOPS=0.545
[ PERFSTAT ]    (samples=11   mean=0.30   median=0.29   min=0.29   stddev=0.01 (2.9%))
[       OK ] Conv3D.conv3d/5 (17 ms)
[ RUN      ] Conv3D.conv3d/6, where GetParam() = (GFLOPS=1.343, K=[3 x 3 x 3], IN={1, 11, 9, 150, 200}, OCN=11, PM=VALID, BIAS, CUDA/CUDA)
IN=11602 Kb [ 1 11 9 150 200 ]    OUT=8815 Kb [ 1 11 7 148 198 ]    Weights(parameters): 13 Kb    MFLOPS=1342.56
[ PERFSTAT ]    (samples=17   mean=46.95   median=47.03   min=43.00   stddev=1.40 (3.0%))
[       OK ] Conv3D.conv3d/6 (919 ms)
[ RUN      ] Conv3D.conv3d/7, where GetParam() = (GFLOPS=1.343, K=[3 x 3 x 3], IN={1, 11, 9, 150, 200}, OCN=11, PM=VALID, BIAS, OCV/CPU)
IN=11602 Kb [ 1 11 9 150 200 ]    OUT=8815 Kb [ 1 11 7 148 198 ]    Weights(parameters): 13 Kb    MFLOPS=1342.56
[ PERFSTAT ]    (samples=10   mean=151.69   median=151.56   min=151.06   stddev=0.49 (0.3%))
[       OK ] Conv3D.conv3d/7 (1712 ms)
[ RUN      ] Conv3D.conv3d/8, where GetParam() = (GFLOPS=0.053, K=[3 x 3 x 3], IN={1, 10, 98, 10, 10}, OCN=10, PM=SAME, CUDA/CUDA)
IN=383 Kb [ 1 10 98 10 10 ]    OUT=383 Kb [ 1 10 98 10 10 ]    Weights(parameters): 11 Kb    MFLOPS=53.018
[ PERFSTAT ]    (samples=10   mean=2.00   median=1.99   min=1.94   stddev=0.03 (1.7%))
[       OK ] Conv3D.conv3d/8 (51 ms)
[ RUN      ] Conv3D.conv3d/9, where GetParam() = (GFLOPS=0.053, K=[3 x 3 x 3], IN={1, 10, 98, 10, 10}, OCN=10, PM=SAME, OCV/CPU)
IN=383 Kb [ 1 10 98 10 10 ]    OUT=383 Kb [ 1 10 98 10 10 ]    Weights(parameters): 11 Kb    MFLOPS=53.018
[ PERFSTAT ]    (samples=10   mean=6.01   median=6.01   min=5.90   stddev=0.09 (1.6%))
[       OK ] Conv3D.conv3d/9 (80 ms)
[ RUN      ] Conv3D.conv3d/10, where GetParam() = (GFLOPS=0.030, K=[5 x 5 x 5], IN={1, 6, 19, 19, 19}, OCN=6, G=2, CUDA/CUDA)
IN=161 Kb [ 1 6 19 19 19 ]    OUT=80 Kb [ 1 6 15 15 15 ]    Weights(parameters): 9 Kb    MFLOPS=30.3952
[ PERFSTAT ]    (samples=10   mean=3.03   median=3.02   min=3.01   stddev=0.03 (1.0%))
[       OK ] Conv3D.conv3d/10 (61 ms)
[ RUN      ] Conv3D.conv3d/11, where GetParam() = (GFLOPS=0.030, K=[5 x 5 x 5], IN={1, 6, 19, 19, 19}, OCN=6, G=2, OCV/CPU)
IN=161 Kb [ 1 6 19 19 19 ]    OUT=80 Kb [ 1 6 15 15 15 ]    Weights(parameters): 9 Kb    MFLOPS=30.3952
[ PERFSTAT ]    (samples=10   mean=3.52   median=3.51   min=3.47   stddev=0.06 (1.6%))
[       OK ] Conv3D.conv3d/11 (53 ms)
[ RUN      ] Conv3D.conv3d/12, where GetParam() = (GFLOPS=0.006, K=[5 x 5 x 5], IN={1, 4, 50, 19, 19}, OCN=4, S=[2 x 2 x 2], P=(1, 1) x (1, 1) x (1, 1), PM=VALID, CUDA/CUDA)
IN=283 Kb [ 1 4 50 19 19 ]    OUT=23 Kb [ 1 4 23 8 8 ]    Weights(parameters): 8 Kb    MFLOPS=5.89389
[ PERFSTAT ]    (samples=10   mean=0.74   median=0.73   min=0.73   stddev=0.01 (1.3%))
[       OK ] Conv3D.conv3d/12 (37 ms)
[ RUN      ] Conv3D.conv3d/13, where GetParam() = (GFLOPS=0.006, K=[5 x 5 x 5], IN={1, 4, 50, 19, 19}, OCN=4, S=[2 x 2 x 2], P=(1, 1) x (1, 1) x (1, 1), PM=VALID, OCV/CPU)
IN=283 Kb [ 1 4 50 19 19 ]    OUT=23 Kb [ 1 4 23 8 8 ]    Weights(parameters): 8 Kb    MFLOPS=5.89389
[ PERFSTAT ]    (samples=13   mean=1.23   median=1.22   min=1.21   stddev=0.02 (1.3%))
[       OK ] Conv3D.conv3d/13 (31 ms)
[ RUN      ] Conv3D.conv3d/14, where GetParam() = (GFLOPS=1.267, K=[5 x 5 x 5], IN={1, 3, 75, 75, 100}, OCN=3, PM=SAME, BIAS, CUDA/CUDA)
IN=6592 Kb [ 1 3 75 75 100 ]    OUT=6592 Kb [ 1 3 75 75 100 ]    Weights(parameters): 5 Kb    MFLOPS=1267.31
[ PERFSTAT ]    (samples=10   mean=142.32   median=142.29   min=140.65   stddev=1.28 (0.9%))
[       OK ] Conv3D.conv3d/14 (1626 ms)
[ RUN      ] Conv3D.conv3d/15, where GetParam() = (GFLOPS=1.267, K=[5 x 5 x 5], IN={1, 3, 75, 75, 100}, OCN=3, PM=SAME, BIAS, OCV/CPU)
IN=6592 Kb [ 1 3 75 75 100 ]    OUT=6592 Kb [ 1 3 75 75 100 ]    Weights(parameters): 5 Kb    MFLOPS=1267.31
[ PERFSTAT ]    (samples=10   mean=279.25   median=279.38   min=276.70   stddev=2.20 (0.8%))
[       OK ] Conv3D.conv3d/15 (3103 ms)
[ RUN      ] Conv3D.conv3d/16, where GetParam() = (GFLOPS=0.116, K=[5 x 5 x 5], IN={1, 2, 21, 75, 100}, OCN=2, BIAS, CUDA/CUDA)
IN=1231 Kb [ 1 2 21 75 100 ]    OUT=906 Kb [ 1 2 17 71 96 ]    Weights(parameters): 2 Kb    MFLOPS=116.104
[ PERFSTAT ]    (samples=100   mean=26.01   median=26.31   min=21.10   stddev=1.17 (4.5%))
[       OK ] Conv3D.conv3d/16 (2693 ms)
[ RUN      ] Conv3D.conv3d/17, where GetParam() = (GFLOPS=0.116, K=[5 x 5 x 5], IN={1, 2, 21, 75, 100}, OCN=2, BIAS, OCV/CPU)
IN=1231 Kb [ 1 2 21 75 100 ]    OUT=906 Kb [ 1 2 17 71 96 ]    Weights(parameters): 2 Kb    MFLOPS=116.104
[ PERFSTAT ]    (samples=10   mean=32.66   median=32.64   min=32.61   stddev=0.05 (0.2%))
[       OK ] Conv3D.conv3d/17 (376 ms)
[ RUN      ] Conv3D.conv3d/18, where GetParam() = (GFLOPS=0.093, K=[5 x 5 x 5], IN={1, 4, 40, 75, 75}, OCN=4, S=[2 x 2 x 2], CUDA/CUDA)
IN=3516 Kb [ 1 4 40 75 75 ]    OUT=365 Kb [ 1 4 18 36 36 ]    Weights(parameters): 8 Kb    MFLOPS=93.4053
[ PERFSTAT ]    (samples=10   mean=6.99   median=6.93   min=6.83   stddev=0.14 (2.0%))
[       OK ] Conv3D.conv3d/18 (118 ms)
[ RUN      ] Conv3D.conv3d/19, where GetParam() = (GFLOPS=0.093, K=[5 x 5 x 5], IN={1, 4, 40, 75, 75}, OCN=4, S=[2 x 2 x 2], OCV/CPU)
IN=3516 Kb [ 1 4 40 75 75 ]    OUT=365 Kb [ 1 4 18 36 36 ]    Weights(parameters): 8 Kb    MFLOPS=93.4053
[ PERFSTAT ]    (samples=10   mean=18.70   median=18.70   min=18.60   stddev=0.07 (0.4%))
[       OK ] Conv3D.conv3d/19 (227 ms)
[ RUN      ] Conv3D.conv3d/20, where GetParam() = (GFLOPS=0.071, K=[7 x 7 x 7], IN={1, 6, 15, 19, 19}, OCN=6, S=[2 x 1 x 1], P=(3, 3) x (3, 3) x (3, 3), PM=SAME, BIAS, CUDA/CUDA)
IN=127 Kb [ 1 6 15 19 19 ]    OUT=68 Kb [ 1 6 8 19 19 ]    Weights(parameters): 49 Kb    MFLOPS=71.3394
[ PERFSTAT ]    (samples=10   mean=4.22   median=4.23   min=4.14   stddev=0.05 (1.2%))
[       OK ] Conv3D.conv3d/20 (73 ms)
[ RUN      ] Conv3D.conv3d/21, where GetParam() = (GFLOPS=0.071, K=[7 x 7 x 7], IN={1, 6, 15, 19, 19}, OCN=6, S=[2 x 1 x 1], P=(3, 3) x (3, 3) x (3, 3), PM=SAME, BIAS, OCV/CPU)
IN=127 Kb [ 1 6 15 19 19 ]    OUT=68 Kb [ 1 6 8 19 19 ]    Weights(parameters): 49 Kb    MFLOPS=71.3394
[ PERFSTAT ]    (samples=10   mean=10.01   median=10.00   min=9.82   stddev=0.16 (1.6%))
[       OK ] Conv3D.conv3d/21 (126 ms)
[ RUN      ] Conv3D.conv3d/22, where GetParam() = (GFLOPS=0.045, K=[7 x 7 x 7], IN={1, 2, 38, 38, 38}, OCN=2, S=[1 x 2 x 1], CUDA/CUDA)
IN=429 Kb [ 1 2 38 38 38 ]    OUT=128 Kb [ 1 2 32 16 32 ]    Weights(parameters): 6 Kb    MFLOPS=44.9905
[ PERFSTAT ]    (samples=10   mean=6.55   median=6.52   min=6.48   stddev=0.08 (1.1%))
[       OK ] Conv3D.conv3d/22 (104 ms)
[ RUN      ] Conv3D.conv3d/23, where GetParam() = (GFLOPS=0.045, K=[7 x 7 x 7], IN={1, 2, 38, 38, 38}, OCN=2, S=[1 x 2 x 1], OCV/CPU)
IN=429 Kb [ 1 2 38 38 38 ]    OUT=128 Kb [ 1 2 32 16 32 ]    Weights(parameters): 6 Kb    MFLOPS=44.9905
[ PERFSTAT ]    (samples=10   mean=11.38   median=11.37   min=11.30   stddev=0.07 (0.6%))
[       OK ] Conv3D.conv3d/23 (140 ms)
[ RUN      ] Conv3D.conv3d/24, where GetParam() = (GFLOPS=0.000, K=[1 x 1 x 1], IN={1, 4, 9, 10, 10}, OCN=4, S=[1 x 1 x 2], P=(1, 1) x (1, 1) x (1, 1), PM=VALID, CUDA/CUDA)
IN=15 Kb [ 1 4 9 10 10 ]    OUT=8 Kb [ 1 4 9 10 5 ]    Weights(parameters): 1 Kb    MFLOPS=0.0162
[ PERFSTAT ]    (samples=73   mean=0.20   median=0.20   min=0.20   stddev=0.01 (3.0%))
[       OK ] Conv3D.conv3d/24 (42 ms)
[ RUN      ] Conv3D.conv3d/25, where GetParam() = (GFLOPS=0.000, K=[1 x 1 x 1], IN={1, 4, 9, 10, 10}, OCN=4, S=[1 x 1 x 2], P=(1, 1) x (1, 1) x (1, 1), PM=VALID, OCV/CPU)
IN=15 Kb [ 1 4 9 10 10 ]    OUT=8 Kb [ 1 4 9 10 5 ]    Weights(parameters): 1 Kb    MFLOPS=0.0162
[ PERFSTAT ]    (samples=25   mean=0.04   median=0.04   min=0.03   stddev=0.00 (2.7%))
[       OK ] Conv3D.conv3d/25 (14 ms)
[ RUN      ] Conv3D.conv3d/26, where GetParam() = (GFLOPS=0.002, K=[3 x 1 x 4], IN={1, 14, 5, 10, 10}, OCN=14, PM=SAME, CUDA/CUDA)
IN=28 Kb [ 1 14 5 10 10 ]    OUT=28 Kb [ 1 14 5 10 10 ]    Weights(parameters): 10 Kb    MFLOPS=2.359
[ PERFSTAT ]    (samples=100   mean=0.34   median=0.33   min=0.29   stddev=0.01 (3.7%))
[       OK ] Conv3D.conv3d/26 (64 ms)
[ RUN      ] Conv3D.conv3d/27, where GetParam() = (GFLOPS=0.002, K=[3 x 1 x 4], IN={1, 14, 5, 10, 10}, OCN=14, PM=SAME, OCV/CPU)
IN=28 Kb [ 1 14 5 10 10 ]    OUT=28 Kb [ 1 14 5 10 10 ]    Weights(parameters): 10 Kb    MFLOPS=2.359
[ PERFSTAT ]    (samples=13   mean=0.42   median=0.42   min=0.41   stddev=0.01 (1.9%))
[       OK ] Conv3D.conv3d/27 (19 ms)
[ RUN      ] Conv3D.conv3d/28, where GetParam() = (GFLOPS=0.000, K=[1 x 1 x 1], IN={1, 8, 1, 10, 10}, OCN=8, G=8, P=(1, 1) x (1, 1) x (1, 1), BIAS, CUDA/CUDA)
IN=4 Kb [ 1 8 1 10 10 ]    OUT=14 Kb [ 1 8 3 12 12 ]    Weights(parameters): 1 Kb    MFLOPS=0.058752
[ PERFSTAT ]    (samples=13   mean=0.72   median=0.72   min=0.70   stddev=0.02 (2.9%))
[       OK ] Conv3D.conv3d/28 (37 ms)
[ RUN      ] Conv3D.conv3d/29, where GetParam() = (GFLOPS=0.000, K=[1 x 1 x 1], IN={1, 8, 1, 10, 10}, OCN=8, G=8, P=(1, 1) x (1, 1) x (1, 1), BIAS, OCV/CPU)
IN=4 Kb [ 1 8 1 10 10 ]    OUT=14 Kb [ 1 8 3 12 12 ]    Weights(parameters): 1 Kb    MFLOPS=0.058752
[ PERFSTAT ]    (samples=25   mean=0.08   median=0.08   min=0.08   stddev=0.00 (1.8%))
[       OK ] Conv3D.conv3d/29 (15 ms)
[ RUN      ] Conv3D.conv3d/30, where GetParam() = (GFLOPS=0.000, K=[3 x 4 x 2], IN={1, 4, 8, 10, 10}, OCN=4, G=4, S=[1 x 2 x 1], BIAS, CUDA/CUDA)
IN=13 Kb [ 1 4 8 10 10 ]    OUT=4 Kb [ 1 4 6 4 9 ]    Weights(parameters): 1 Kb    MFLOPS=0.166752
[ PERFSTAT ]    (samples=50   mean=0.42   median=0.41   min=0.40   stddev=0.01 (2.7%))
[       OK ] Conv3D.conv3d/30 (49 ms)
[ RUN      ] Conv3D.conv3d/31, where GetParam() = (GFLOPS=0.000, K=[3 x 4 x 2], IN={1, 4, 8, 10, 10}, OCN=4, G=4, S=[1 x 2 x 1], BIAS, OCV/CPU)
IN=13 Kb [ 1 4 8 10 10 ]    OUT=4 Kb [ 1 4 6 4 9 ]    Weights(parameters): 1 Kb    MFLOPS=0.166752
[ PERFSTAT ]    (samples=13   mean=0.12   median=0.12   min=0.12   stddev=0.00 (1.6%))
[       OK ] Conv3D.conv3d/31 (15 ms)
[----------] 32 tests from Conv3D (12049 ms total)

[----------] 38 tests from DNNTestNetwork
[ RUN      ] DNNTestNetwork.AlexNet/0, where GetParam() = CUDA/CUDA
[     SKIP ] OpenCV tests: Can't find data file: dnn/bvlc_alexnet.caffemodel
[       OK ] DNNTestNetwork.AlexNet/0 (14 ms)
[ RUN      ] DNNTestNetwork.AlexNet/1, where GetParam() = OCV/CPU
[     SKIP ] OpenCV tests: Can't find data file: dnn/bvlc_alexnet.caffemodel
[       OK ] DNNTestNetwork.AlexNet/1 (14 ms)
[ RUN      ] DNNTestNetwork.GoogLeNet/0, where GetParam() = CUDA/CUDA
[     SKIP ] OpenCV tests: Can't find data file: dnn/bvlc_googlenet.caffemodel
[       OK ] DNNTestNetwork.GoogLeNet/0 (14 ms)
[ RUN      ] DNNTestNetwork.GoogLeNet/1, where GetParam() = OCV/CPU
[     SKIP ] OpenCV tests: Can't find data file: dnn/bvlc_googlenet.caffemodel
[       OK ] DNNTestNetwork.GoogLeNet/1 (14 ms)
[ RUN      ] DNNTestNetwork.ResNet_50/0, where GetParam() = CUDA/CUDA
[     SKIP ] OpenCV tests: Can't find data file: dnn/ResNet-50-model.caffemodel
[       OK ] DNNTestNetwork.ResNet_50/0 (14 ms)
[ RUN      ] DNNTestNetwork.ResNet_50/1, where GetParam() = OCV/CPU
[     SKIP ] OpenCV tests: Can't find data file: dnn/ResNet-50-model.caffemodel
[       OK ] DNNTestNetwork.ResNet_50/1 (14 ms)
[ RUN      ] DNNTestNetwork.SqueezeNet_v1_1/0, where GetParam() = CUDA/CUDA
[     SKIP ] OpenCV tests: Can't find data file: dnn/squeezenet_v1.1.caffemodel
[       OK ] DNNTestNetwork.SqueezeNet_v1_1/0 (14 ms)
[ RUN      ] DNNTestNetwork.SqueezeNet_v1_1/1, where GetParam() = OCV/CPU
[     SKIP ] OpenCV tests: Can't find data file: dnn/squeezenet_v1.1.caffemodel
[       OK ] DNNTestNetwork.SqueezeNet_v1_1/1 (14 ms)
[ RUN      ] DNNTestNetwork.Inception_5h/0, where GetParam() = CUDA/CUDA
[     SKIP ] OpenCV tests: Can't find data file: dnn/tensorflow_inception_graph.pb
[       OK ] DNNTestNetwork.Inception_5h/0 (14 ms)
[ RUN      ] DNNTestNetwork.Inception_5h/1, where GetParam() = OCV/CPU
[     SKIP ] OpenCV tests: Can't find data file: dnn/tensorflow_inception_graph.pb
[       OK ] DNNTestNetwork.Inception_5h/1 (14 ms)
[ RUN      ] DNNTestNetwork.ENet/0, where GetParam() = CUDA/CUDA
[     SKIP ] OpenCV tests: Can't find data file: dnn/Enet-model-best.net
[       OK ] DNNTestNetwork.ENet/0 (15 ms)
[ RUN      ] DNNTestNetwork.ENet/1, where GetParam() = OCV/CPU
[     SKIP ] OpenCV tests: Can't find data file: dnn/Enet-model-best.net
[       OK ] DNNTestNetwork.ENet/1 (16 ms)
[ RUN      ] DNNTestNetwork.SSD/0, where GetParam() = CUDA/CUDA
[     SKIP ] OpenCV tests: Can't find data file: dnn/VGG_ILSVRC2016_SSD_300x300_iter_440000.caffemodel
[       OK ] DNNTestNetwork.SSD/0 (15 ms)
[ RUN      ] DNNTestNetwork.SSD/1, where GetParam() = OCV/CPU
[     SKIP ] OpenCV tests: Can't find data file: dnn/VGG_ILSVRC2016_SSD_300x300_iter_440000.caffemodel
[       OK ] DNNTestNetwork.SSD/1 (14 ms)
[ RUN      ] DNNTestNetwork.OpenFace/0, where GetParam() = CUDA/CUDA
[     SKIP ] OpenCV tests: Can't find data file: dnn/openface_nn4.small2.v1.t7
[       OK ] DNNTestNetwork.OpenFace/0 (13 ms)
[ RUN      ] DNNTestNetwork.OpenFace/1, where GetParam() = OCV/CPU
[     SKIP ] OpenCV tests: Can't find data file: dnn/openface_nn4.small2.v1.t7
[       OK ] DNNTestNetwork.OpenFace/1 (13 ms)
[ RUN      ] DNNTestNetwork.MobileNet_SSD_Caffe/0, where GetParam() = CUDA/CUDA
[     SKIP ] OpenCV tests: Can't find data file: dnn/MobileNetSSD_deploy.caffemodel
[       OK ] DNNTestNetwork.MobileNet_SSD_Caffe/0 (15 ms)
[ RUN      ] DNNTestNetwork.MobileNet_SSD_Caffe/1, where GetParam() = OCV/CPU
[     SKIP ] OpenCV tests: Can't find data file: dnn/MobileNetSSD_deploy.caffemodel
[       OK ] DNNTestNetwork.MobileNet_SSD_Caffe/1 (15 ms)
[ RUN      ] DNNTestNetwork.MobileNet_SSD_v1_TensorFlow/0, where GetParam() = CUDA/CUDA
[     SKIP ] OpenCV tests: Can't find data file: dnn/ssd_mobilenet_v1_coco_2017_11_17.pb
[       OK ] DNNTestNetwork.MobileNet_SSD_v1_TensorFlow/0 (14 ms)
[ RUN      ] DNNTestNetwork.MobileNet_SSD_v1_TensorFlow/1, where GetParam() = OCV/CPU
[     SKIP ] OpenCV tests: Can't find data file: dnn/ssd_mobilenet_v1_coco_2017_11_17.pb
[       OK ] DNNTestNetwork.MobileNet_SSD_v1_TensorFlow/1 (14 ms)
[ RUN      ] DNNTestNetwork.MobileNet_SSD_v2_TensorFlow/0, where GetParam() = CUDA/CUDA
[     SKIP ] OpenCV tests: Can't find data file: dnn/ssd_mobilenet_v2_coco_2018_03_29.pb
[       OK ] DNNTestNetwork.MobileNet_SSD_v2_TensorFlow/0 (15 ms)
[ RUN      ] DNNTestNetwork.MobileNet_SSD_v2_TensorFlow/1, where GetParam() = OCV/CPU
[     SKIP ] OpenCV tests: Can't find data file: dnn/ssd_mobilenet_v2_coco_2018_03_29.pb
[       OK ] DNNTestNetwork.MobileNet_SSD_v2_TensorFlow/1 (15 ms)
[ RUN      ] DNNTestNetwork.DenseNet_121/0, where GetParam() = CUDA/CUDA
[     SKIP ] OpenCV tests: Can't find data file: dnn/DenseNet_121.caffemodel
[       OK ] DNNTestNetwork.DenseNet_121/0 (14 ms)
[ RUN      ] DNNTestNetwork.DenseNet_121/1, where GetParam() = OCV/CPU
[     SKIP ] OpenCV tests: Can't find data file: dnn/DenseNet_121.caffemodel
[       OK ] DNNTestNetwork.DenseNet_121/1 (13 ms)
[ RUN      ] DNNTestNetwork.OpenPose_pose_mpi_faster_4_stages/0, where GetParam() = CUDA/CUDA
[     SKIP ] OpenCV tests: Can't find data file: dnn/openpose_pose_mpi.caffemodel
[       OK ] DNNTestNetwork.OpenPose_pose_mpi_faster_4_stages/0 (16 ms)
[ RUN      ] DNNTestNetwork.OpenPose_pose_mpi_faster_4_stages/1, where GetParam() = OCV/CPU
[     SKIP ] OpenCV tests: Can't find data file: dnn/openpose_pose_mpi.caffemodel
[       OK ] DNNTestNetwork.OpenPose_pose_mpi_faster_4_stages/1 (16 ms)
[ RUN      ] DNNTestNetwork.opencv_face_detector/0, where GetParam() = CUDA/CUDA
[     SKIP ] OpenCV tests: Can't find data file: dnn/opencv_face_detector.caffemodel
[       OK ] DNNTestNetwork.opencv_face_detector/0 (15 ms)
[ RUN      ] DNNTestNetwork.opencv_face_detector/1, where GetParam() = OCV/CPU
[     SKIP ] OpenCV tests: Can't find data file: dnn/opencv_face_detector.caffemodel
[       OK ] DNNTestNetwork.opencv_face_detector/1 (14 ms)
[ RUN      ] DNNTestNetwork.Inception_v2_SSD_TensorFlow/0, where GetParam() = CUDA/CUDA
[     SKIP ] OpenCV tests: Can't find data file: dnn/ssd_inception_v2_coco_2017_11_17.pb
[       OK ] DNNTestNetwork.Inception_v2_SSD_TensorFlow/0 (15 ms)
[ RUN      ] DNNTestNetwork.Inception_v2_SSD_TensorFlow/1, where GetParam() = OCV/CPU
[     SKIP ] OpenCV tests: Can't find data file: dnn/ssd_inception_v2_coco_2017_11_17.pb
[       OK ] DNNTestNetwork.Inception_v2_SSD_TensorFlow/1 (15 ms)
[ RUN      ] DNNTestNetwork.YOLOv3/0, where GetParam() = CUDA/CUDA
/home/dan/Projects/opencv/modules/ts/src/ts_perf.cpp:2028: Failure
Failed
Expected: PerfTestBody() doesn't throw an exception.
  Actual: it throws cv::Exception:
  OpenCV(4.1.1-dev) /home/dan/Projects/opencv/modules/ts/src/ts.cpp:1014: error: (-2:Unspecified error) OpenCV tests: Can't find required data file: dnn/dog416.png in function 'findData'

params    =   CUDA/CUDA
termination reason:  unhandled exception
bytesIn   =          0
bytesOut  =          0
samples   =          0 of 100
outliers  =          0
frequency =          0
[  FAILED  ] DNNTestNetwork.YOLOv3/0, where GetParam() = CUDA/CUDA (13 ms)
[ RUN      ] DNNTestNetwork.YOLOv3/1, where GetParam() = OCV/CPU
/home/dan/Projects/opencv/modules/ts/src/ts_perf.cpp:2028: Failure
Failed
Expected: PerfTestBody() doesn't throw an exception.
  Actual: it throws cv::Exception:
  OpenCV(4.1.1-dev) /home/dan/Projects/opencv/modules/ts/src/ts.cpp:1014: error: (-2:Unspecified error) OpenCV tests: Can't find required data file: dnn/dog416.png in function 'findData'

params    =     OCV/CPU
termination reason:  unhandled exception
bytesIn   =          0
bytesOut  =          0
samples   =          0 of 100
outliers  =          0
frequency =          0
[  FAILED  ] DNNTestNetwork.YOLOv3/1, where GetParam() = OCV/CPU (13 ms)
[ RUN      ] DNNTestNetwork.EAST_text_detection/0, where GetParam() = CUDA/CUDA
[     SKIP ] OpenCV tests: Can't find data file: dnn/frozen_east_text_detection.pb
[       OK ] DNNTestNetwork.EAST_text_detection/0 (15 ms)
[ RUN      ] DNNTestNetwork.EAST_text_detection/1, where GetParam() = OCV/CPU
[     SKIP ] OpenCV tests: Can't find data file: dnn/frozen_east_text_detection.pb
[       OK ] DNNTestNetwork.EAST_text_detection/1 (15 ms)
[ RUN      ] DNNTestNetwork.FastNeuralStyle_eccv16/0, where GetParam() = CUDA/CUDA
[     SKIP ] OpenCV tests: Can't find data file: dnn/fast_neural_style_eccv16_starry_night.t7
[       OK ] DNNTestNetwork.FastNeuralStyle_eccv16/0 (14 ms)
[ RUN      ] DNNTestNetwork.FastNeuralStyle_eccv16/1, where GetParam() = OCV/CPU
[     SKIP ] OpenCV tests: Can't find data file: dnn/fast_neural_style_eccv16_starry_night.t7
[       OK ] DNNTestNetwork.FastNeuralStyle_eccv16/1 (15 ms)
[ RUN      ] DNNTestNetwork.Inception_v2_Faster_RCNN/0, where GetParam() = CUDA/CUDA
[     SKIP ] OpenCV tests: Can't find data file: dnn/faster_rcnn_inception_v2_coco_2018_01_28.pb
[       OK ] DNNTestNetwork.Inception_v2_Faster_RCNN/0 (22 ms)
[ RUN      ] DNNTestNetwork.Inception_v2_Faster_RCNN/1, where GetParam() = OCV/CPU
[     SKIP ] OpenCV tests: Can't find data file: dnn/faster_rcnn_inception_v2_coco_2018_01_28.pb
[       OK ] DNNTestNetwork.Inception_v2_Faster_RCNN/1 (23 ms)
[----------] 38 tests from DNNTestNetwork (563 ms total)

[----------] Global test environment tear-down
[==========] 270 tests from 3 test cases ran. (103509 ms total)
[  PASSED  ] 268 tests.
[  FAILED  ] 2 tests, listed below:
[  FAILED  ] DNNTestNetwork.YOLOv3/0, where GetParam() = CUDA/CUDA
[  FAILED  ] DNNTestNetwork.YOLOv3/1, where GetParam() = OCV/CPU

 2 FAILED TESTS